mtmd: support Qwen3-TTS (note: breaking change to llama-tts binary) (#26254)

* convert text model

* main model load ok

* convert encoder ok

* speaker encoder loading ok

* speaker enc graph

* adapt vocab for backbone (with some tricks)

* add suppress_tokens

* poc new mtmd gen api

* convert code_predictor to gguf

* load gen_code model ok

* add clip_encode

* wire up

* code gen cgraph init version

Co-authored-by: Pascal <admin@serveurperso.com>

* code2wav convert to gguf

* code2wav graph ok

* wire up in/out

* (wip) subgraph

* wire up

* wip, correct code2wav

* demo (to be removed)

* code2wav preserve kv between calls

* demo voice clone

* llama: add llama_model_get_tok_embd

* mtmd_helper_gen_audio API

* fix clamp cold prefix

Co-authored-by: Pascal <admin@serveurperso.com>

* fuse snake op

Co-authored-by: Pascal <admin@serveurperso.com>

* demo: use proper sampling

* update dev docs

* polymorphism helper

* revamp llama-tts binary

* update docs

* fix compile

* fix lint

* nits

* add guide + docs

* more timings info

* clean up code comments

* security fixes

* update docs

* use ggml_build_forward_select, clean up comments

* fix ci

* use ISO 639-1 language code

* rename CODE2WAV --> GEN_WAV, update docs

* clean up

* clean up tts.cpp

* add seq_id

* add step_prompt()

* mtmd_helper_model_can_chat

* clean up comments

---------

Co-authored-by: Pascal <admin@serveurperso.com>

.github/workflows/build-apple.yml

@@ -63,7 +63,8 @@ jobs:
             -DGGML_METAL_USE_BF16=ON \
             -DGGML_METAL_EMBED_LIBRARY=OFF \
             -DGGML_METAL_SHADER_DEBUG=ON \
-            -DGGML_RPC=ON
+            -DGGML_RPC=ON \
+            -DCMAKE_OSX_DEPLOYMENT_TARGET=13.3
           time cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
           leaks -atExit -- ./build/bin/test-thread-safety -hf ggml-org/gemma-3-270m-qat-GGUF -ngl 99 -p "$(printf 'hello %.0s' {1..128})" -n 16 -c 512 -ub 32 -np 2 -t 2 -lv 1
 

.github/workflows/build-vulkan.yml

@@ -119,6 +119,7 @@ jobs:
         run: |
           source ./vulkan_sdk/setup-env.sh
           cmake -B build \
+            -DGGML_NATIVE=OFF \
             -DGGML_VULKAN=ON
           cmake --build build --config Release -j $(nproc)
 

.github/workflows/release.yml

@@ -93,13 +93,13 @@ jobs:
           - build: 'arm64'
             arch: 'arm64'
             os: macos-26
-            defines: "-DGGML_METAL_USE_BF16=ON -DGGML_METAL_EMBED_LIBRARY=ON"
+            defines: "-DGGML_METAL_USE_BF16=ON -DGGML_METAL_EMBED_LIBRARY=ON -DCMAKE_OSX_DEPLOYMENT_TARGET=13.3"
           # TODO: this build is disabled to save Github Actions resources (https://github.com/ggml-org/llama.cpp/pull/23780)
           #       in order to enable it again, we have to provision dedicated runners  to run it
           #- build: 'arm64-kleidiai'
           #  arch: 'arm64'
           #  os: macos-14
-          #  defines: "-DGGML_METAL_USE_BF16=ON -DGGML_METAL_EMBED_LIBRARY=ON -DGGML_CPU_KLEIDIAI=ON"
+          #  defines: "-DGGML_METAL_USE_BF16=ON -DGGML_METAL_EMBED_LIBRARY=ON -DCMAKE_OSX_DEPLOYMENT_TARGET=13.3 -DGGML_CPU_KLEIDIAI=ON"
           - build: 'x64'
             arch: 'x64'
             os: macos-15-intel

common/arg.cpp

@@ -61,6 +61,7 @@ static std::initializer_list<enum llama_example> mmproj_examples = {
     LLAMA_EXAMPLE_MTMD,
     LLAMA_EXAMPLE_SERVER,
     LLAMA_EXAMPLE_CLI,
+    LLAMA_EXAMPLE_TTS,
 };
 
 static std::string read_file(const std::string & fname) {
@@ -360,7 +361,6 @@ static bool spec_types_is_default(const common_params & params) {
 common_models_handler common_models_handler_init(const common_params & params, llama_example curr_ex) {
     common_download_hf_plan plan;
     common_download_hf_plan plan_spec;
-    common_download_hf_plan plan_voc;
     common_download_opts opts;
 
     const bool spec_type_draft_mtp = std::find(params.speculative.types.begin(),
@@ -413,11 +413,7 @@ common_models_handler common_models_handler_init(const common_params & params, l
         plan_spec = common_download_get_hf_plan(params.speculative.draft.mparams, opts_spec);
     }
 
-    if (!params.vocoder.model.hf_repo.empty()) {
-        plan_voc = common_download_get_hf_plan(params.vocoder.model, opts);
-    }
-
-    return common_models_handler{plan, plan_spec, plan_voc, opts};
+    return common_models_handler{plan, plan_spec, opts};
 }
 
 bool common_models_handler_is_preset_repo(const common_models_handler & handler) {
@@ -467,7 +463,6 @@ void common_models_handler_apply(common_models_handler & handler, common_params
 
     auto & plan      = handler.plan;
     auto & plan_spec = handler.plan_spec;
-    auto & plan_voc  = handler.plan_voc;
 
     auto opts = handler.opts; // copy
     opts.callback = callback;
@@ -482,7 +477,6 @@ void common_models_handler_apply(common_models_handler & handler, common_params
     };
     handle_url(params.model);
     handle_url(params.mmproj);
-    handle_url(params.vocoder.model);
     handle_url(params.speculative.draft.mparams);
 
     // optionally, if docker repo is set, resolve it
@@ -510,14 +504,6 @@ void common_models_handler_apply(common_models_handler & handler, common_params
         task.opts       = opts;
         tasks.push_back(task);
     }
-    if (!params.vocoder.model.url.empty()) {
-        common_download_task task;
-        task.url        = params.vocoder.model.url;
-        task.local_path = params.vocoder.model.path;
-        task.opts       = opts;
-        tasks.push_back(task);
-    }
-
     bool had_spec_url = false;
     if (!params.speculative.draft.mparams.url.empty()) {
         common_download_task task;
@@ -631,11 +617,6 @@ void common_models_handler_apply(common_models_handler & handler, common_params
         had_spec_url = true;
     }
 
-    // handle vocoder plan (e.g. --hf-repo-v)
-    if (!plan_voc.model_files.empty()) {
-        add_tasks(plan_voc.model_files, plan_voc.primary, params.vocoder.model);
-    }
-
     if (!plan.model_files.empty()) {
         add_tasks(plan.model_files, plan.primary, params.model);
     }
@@ -1361,6 +1342,10 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         params.n_parallel = -1;     // auto by default
     } else if (ex == LLAMA_EXAMPLE_TOKENIZE) {
         params.parse_special = true; // parse special tokens by default, like the old tokenize tool
+    } else if (ex == LLAMA_EXAMPLE_TTS) {
+        params.out_file = "output.wav";
+        params.sampling.penalty_repeat = 1.05f;
+        params.sampling.penalty_last_n = -1;
     }
 
     params.use_color = tty_can_use_colors();
@@ -2983,20 +2968,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
             params.model.hf_file = value;
         }
     ).set_examples({LLAMA_EXAMPLE_COMMON, LLAMA_EXAMPLE_DOWNLOAD, LLAMA_EXAMPLE_TOKENIZE}).set_env("LLAMA_ARG_HF_FILE"));
-    add_opt(common_arg(
-        {"-hfv", "-hfrv", "--hf-repo-v"}, "<user>/<model>[:quant]",
-        "Hugging Face model repository for the vocoder model (default: unused)",
-        [](common_params & params, const std::string & value) {
-            params.vocoder.model.hf_repo = value;
-        }
-    ).set_env("LLAMA_ARG_HF_REPO_V"));
-    add_opt(common_arg(
-        {"-hffv", "--hf-file-v"}, "FILE",
-        "Hugging Face model file for the vocoder model (default: unused)",
-        [](common_params & params, const std::string & value) {
-            params.vocoder.model.hf_file = value;
-        }
-    ).set_env("LLAMA_ARG_HF_FILE_V"));
     add_opt(common_arg(
         {"-hft", "--hf-token"}, "TOKEN",
         "Hugging Face access token (default: value from HF_TOKEN environment variable)",
@@ -3337,16 +3308,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
             params.server_tools = parse_csv_row(value);
         }
     ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_TOOLS"));
-    add_opt(common_arg(
-        {"--tools-runtime"}, "OPTION",
-        "experimental: run tools in a separate runtime environment (default: none, use host environment)\n"
-        "available options:\n"
-        "  'docker:<image>': spin up a new Docker container and reuse it for all invocations, clean up on server exit\n"
-        "  'docker-container:<id>': use an existing Docker container by ID, won't stop on server exit\n",
-        [](common_params & params, const std::string & value) {
-            params.server_tools_runtime = value;
-        }
-    ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_TOOLS_RUNTIME"));
     add_opt(common_arg(
         {"--mcp-servers-config"}, "PATH",
         "experimental: path to JSON file with MCP server definitions (Cursor-compatible format) - do not enable in untrusted environments (default: none)\n"
@@ -4282,24 +4243,18 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
     //
 
     add_opt(common_arg(
-        {"-mv", "--model-vocoder"}, "FNAME",
-        "vocoder model for audio generation (default: unused)",
+        {"--tts-lang"}, "FNAME",
+        "language (ISO 639-1) for audio generation\n"
+        "see tts/README.md for per-model usage notes",
         [](common_params & params, const std::string & value) {
-            params.vocoder.model.path = value;
+            params.tts_lang = value;
         }
-    ).set_examples({LLAMA_EXAMPLE_TTS, LLAMA_EXAMPLE_SERVER}));
-     add_opt(common_arg(
-        {"--tts-use-guide-tokens"},
-        "Use guide tokens to improve TTS word recall",
-        [](common_params & params) {
-            params.vocoder.use_guide_tokens = true;
-        }
-    ).set_examples({LLAMA_EXAMPLE_TTS, LLAMA_EXAMPLE_SERVER}));
+    ).set_examples({LLAMA_EXAMPLE_TTS}));
     add_opt(common_arg(
         {"--tts-speaker-file"}, "FNAME",
         "speaker file path for audio generation",
         [](common_params & params, const std::string & value) {
-            params.vocoder.speaker_file = value;
+            params.tts_speaker_file = value;
         }
     ).set_examples({LLAMA_EXAMPLE_TTS}));
 
@@ -4419,16 +4374,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
     ).set_examples({LLAMA_EXAMPLE_DEBUG}));
 
     // presets
-    add_opt(common_arg(
-        {"--tts-oute-default"},
-        string_format("use default OuteTTS models (note: can download weights from the internet)"),
-        [](common_params & params) {
-            params.model.hf_repo = "OuteAI/OuteTTS-0.2-500M-GGUF";
-            params.model.hf_file = "OuteTTS-0.2-500M-Q8_0.gguf";
-            params.vocoder.model.hf_repo = "ggml-org/WavTokenizer";
-            params.vocoder.model.hf_file = "WavTokenizer-Large-75-F16.gguf";
-        }
-    ).set_examples({LLAMA_EXAMPLE_TTS}));
 
     add_opt(common_arg(
         {"--embd-gemma-default"},

common/arg.h

@@ -137,7 +137,6 @@ void common_params_add_preset_options(std::vector<common_arg> & args);
 struct common_models_handler {
     common_download_hf_plan plan;
     common_download_hf_plan plan_spec;
-    common_download_hf_plan plan_voc;
     common_download_opts opts;
 };
 

common/chat.cpp

@@ -2114,6 +2114,11 @@ static common_chat_params common_chat_params_init_deepseek_v3_2(const common_cha
     auto extract_reasoning   = inputs.reasoning_format != COMMON_REASONING_FORMAT_NONE;
     auto include_grammar     = has_response_format || (has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE);
 
+    std::optional<json> additional_context;
+    if (is_v4 && has_response_format) {
+        additional_context = json{ { "response_format", inputs.json_schema } };
+    }
+
     const std::string DSML         = "｜DSML｜";
     const std::string THINK_START  = "<think>";
     const std::string THINK_END    = "</think>";
@@ -2125,9 +2130,12 @@ static common_chat_params common_chat_params_init_deepseek_v3_2(const common_cha
     const std::string PARAM_START  = "<" + DSML + "parameter";
     const std::string PARAM_END    = "</" + DSML + "parameter>";
     const std::string GEN_PROMPT   = "<｜Assistant｜>";
+    const std::string TC_SEPARATOR = "\n\n";
 
-    data.prompt             = common_chat_template_direct_apply_impl(tmpl, inputs, adjusted_messages);
-    data.generation_prompt  = common_chat_template_generation_prompt_impl(tmpl, inputs, adjusted_messages);
+    data.prompt = common_chat_template_direct_apply_impl(
+        tmpl, inputs, adjusted_messages, std::nullopt, additional_context);
+    data.generation_prompt = common_chat_template_generation_prompt_impl(
+        tmpl, inputs, adjusted_messages, std::nullopt, additional_context);
     data.format             = COMMON_CHAT_FORMAT_PEG_NATIVE;
     data.supports_thinking  = true;
     data.thinking_start_tag = THINK_START;
@@ -2141,9 +2149,16 @@ static common_chat_params common_chat_params_init_deepseek_v3_2(const common_cha
     if (inputs.has_continuation()) {
         const auto & msg = inputs.continue_msg;
 
-        data.generation_prompt = GEN_PROMPT + THINK_START + msg.reasoning_content;
-        if (inputs.continue_final_message == COMMON_CHAT_CONTINUATION_CONTENT) {
-            data.generation_prompt += THINK_END + msg.render_content();
+        if (is_v4 && msg.reasoning_content.empty()) {
+            data.generation_prompt = GEN_PROMPT + THINK_END;
+            if (inputs.continue_final_message == COMMON_CHAT_CONTINUATION_CONTENT) {
+                data.generation_prompt += msg.render_content();
+            }
+        } else {
+            data.generation_prompt = GEN_PROMPT + THINK_START + msg.reasoning_content;
+            if (inputs.continue_final_message == COMMON_CHAT_CONTINUATION_CONTENT) {
+                data.generation_prompt += THINK_END + msg.render_content();
+            }
         }
 
         data.prompt += data.generation_prompt;
@@ -2242,7 +2257,9 @@ static common_chat_params common_chat_params_init_deepseek_v3_2(const common_cha
 
         if (extract_reasoning && inputs.enable_thinking) {
             reasoning = p.optional(THINK_START + p.reasoning(p.until(THINK_END)) + THINK_END);
-            reasoning_with_tc = THINK_START + p.reasoning(p.until_one_of({ FC_START, THINK_END })) + obligatory_tool_calls;
+            reasoning_with_tc = THINK_START +
+                p.reasoning(p.until_one_of({ TC_SEPARATOR + FC_START, FC_START, THINK_END })) +
+                p.space() + obligatory_tool_calls;
             allow_reasoning_with_tc = true;
         } else if (extract_reasoning) {
             // Thinking disabled but reasoning extraction requested: the generation prompt
@@ -2265,7 +2282,9 @@ static common_chat_params common_chat_params_init_deepseek_v3_2(const common_cha
             return generation_prompt + reasoning + p.content(p.rest()) + end;
         }
 
-        auto content_before_tools = p.negate(p.literal(THINK_START)) + p.content(p.until(FC_START));
+        auto content_before_tools = p.negate(p.literal(THINK_START)) +
+            p.content(p.until_one_of({ TC_SEPARATOR + FC_START, FC_START })) +
+            p.space();
         return allow_reasoning_with_tc ? generation_prompt + (reasoning_with_tc | (reasoning + content_before_tools + tool_calls)) + end :
             generation_prompt + reasoning + content_before_tools + tool_calls + end;
     });

common/common.cpp

@@ -998,6 +998,23 @@ bool fs_is_directory(const std::string & path) {
     return std::filesystem::exists(dir) && std::filesystem::is_directory(dir);
 }
 
+std::string common_get_env(const std::string & name) {
+    const char * value = std::getenv(name.c_str());
+    return value == nullptr ? "" : value;
+}
+
+void common_set_env(const std::string & name, const std::string & value) {
+#if defined(_WIN32)
+    _putenv_s(name.c_str(), value.c_str());
+#else
+    if (value.empty()) {
+        unsetenv(name.c_str());
+    } else {
+        setenv(name.c_str(), value.c_str(), 1);
+    }
+#endif
+}
+
 std::string fs_get_cache_directory() {
     std::string cache_directory = "";
     auto ensure_trailing_slash = [](std::string p) {
@@ -1463,18 +1480,18 @@ common_init_result_ptr common_init_from_params(common_params & params, bool mode
 common_init_result::~common_init_result() = default;
 
 std::string common_get_model_endpoint() {
-    const char * model_endpoint_env = getenv("MODEL_ENDPOINT");
-    // We still respect the use of environment-variable "HF_ENDPOINT" for backward-compatibility.
-    const char * hf_endpoint_env = getenv("HF_ENDPOINT");
-    const char * endpoint_env = model_endpoint_env ? model_endpoint_env : hf_endpoint_env;
-    std::string model_endpoint = "https://huggingface.co/";
-    if (endpoint_env) {
-        model_endpoint = endpoint_env;
-        if (model_endpoint.back() != '/') {
-            model_endpoint += '/';
-        }
+    std::string endpoint = common_get_env("MODEL_ENDPOINT");
+    if (endpoint.empty()) {
+        // the HF_ENDPOINT variable is respected for backward compatibility
+        endpoint = common_get_env("HF_ENDPOINT");
     }
-    return model_endpoint;
+    if (endpoint.empty()) {
+        return "https://huggingface.co/";
+    }
+    if (endpoint.back() != '/') {
+        endpoint += '/';
+    }
+    return endpoint;
 }
 
 char * common_get_model_or_exit(int argc, char * argv[]) {

common/common.h

@@ -392,14 +392,6 @@ struct common_params_speculative {
     }
 };
 
-struct common_params_vocoder {
-    struct common_params_model model;
-
-    std::string speaker_file; // speaker file path
-
-    bool use_guide_tokens = false; // enable guide tokens to improve TTS accuracy
-};
-
 struct common_params_diffusion {
     int32_t steps         = 128;
     bool    visual_mode   = false;
@@ -497,7 +489,6 @@ struct common_params {
 
     struct common_params_sampling    sampling;
     struct common_params_speculative speculative;
-    struct common_params_vocoder     vocoder;
     struct common_params_diffusion   diffusion;
 
     struct common_params_model model;
@@ -664,7 +655,6 @@ struct common_params {
 
     // enable built-in tools
     std::vector<std::string> server_tools;
-    std::string server_tools_runtime;
 
     // MCP server configs (Cursor-compatible JSON)
     std::string mcp_servers_config;   // path to JSON file with MCP server definitions
@@ -741,6 +731,10 @@ struct common_params {
     void *                  load_progress_callback_user_data = NULL;
     bool no_alloc = false; // Don't allocate model buffers
 
+    // TTS params
+    std::string tts_lang = "";
+    std::string tts_speaker_file = "";
+
     bool is_gen_docs = false; // whether we are running inside llama-gen-docs
 };
 
@@ -866,6 +860,15 @@ std::string string_from(const struct llama_context * ctx, const struct llama_bat
 
 bool glob_match(const std::string & pattern, const std::string & str);
 
+//
+// Environment utils
+//
+
+// portable environment access, an unset variable reads as an empty string
+// and setting an empty value unsets the variable
+std::string common_get_env(const std::string & name);
+void        common_set_env(const std::string & name, const std::string & value);
+
 //
 // Filesystem utils
 //

common/jinja/caps.cpp

@@ -482,6 +482,7 @@ caps caps_get(jinja::program & prog) {
             });
         },
         [&](context & ctx) {
+            ctx.set_val("enable_thinking", mk_val<value_bool>(true));
             caps_apply_preserve_reasoning(ctx, true);
         },
         nullptr, // tools_fn

common/sampling.cpp

@@ -383,7 +383,7 @@ struct common_sampler * common_sampler_init(
                     samplers.push_back(llama_sampler_init_infill(vocab));
                     break;
                 case COMMON_SAMPLER_TYPE_PENALTIES:
-                    samplers.push_back(llama_sampler_init_penalties(params.penalty_last_n, params.penalty_repeat, params.penalty_freq, params.penalty_present));
+                    samplers.push_back(llama_sampler_init_penalties(llama_vocab_n_tokens(vocab), params.penalty_last_n, params.penalty_repeat, params.penalty_freq, params.penalty_present));
                     break;
                 case COMMON_SAMPLER_TYPE_ADAPTIVE_P:
                     // the `adaptive-p` sampler is like `dist` and `mirostat` in that it selects

common/speculative.cpp

@@ -2385,57 +2385,28 @@ common_speculative * common_speculative_init(common_params_speculative & params,
     {
         uint32_t enabled_configs = common_get_enabled_speculative_configs(params.types);
 
-        bool has_draft_simple = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_DRAFT_SIMPLE));
-        bool has_draft_eagle3 = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3)) && params.draft.ctx_dft != nullptr;
-        bool has_draft_mtp    = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_DRAFT_MTP))    && params.draft.ctx_dft != nullptr;
-        bool has_draft_dflash = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_DRAFT_DFLASH)) && params.draft.ctx_dft != nullptr;
-        bool has_draft_dspark = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_DRAFT_DSPARK)) && params.draft.ctx_dft != nullptr;
-
-
-
-        bool has_ngram_cache   = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_NGRAM_CACHE));
-        bool has_ngram_simple  = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_NGRAM_SIMPLE));
-        bool has_ngram_map_k   = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K));
-        bool has_ngram_map_k4v = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K4V));
-        bool has_ngram_mod     = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_NGRAM_MOD));
+        auto add_config_if_enabled = [&](common_speculative_type type, bool available = true) {
+            if (available && (enabled_configs & (1u << type))) {
+                configs.emplace_back(type, params);
+            }
+        };
 
         // when adding a new type - update here the logic above
         static_assert(COMMON_SPECULATIVE_TYPE_COUNT == 11);
 
         // this list here defines the priority of the speculators
         // the one with highest priority are listed first
-        if (has_ngram_simple) {
-            // This implementation can guess a lot of tokens without any draft model.
-            configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_NGRAM_SIMPLE, params));
-        }
-        if (has_ngram_map_k) {
-            configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K, params));
-        }
-        if (has_ngram_map_k4v) {
-            // This implementation can guess tokens with high acceptance rate but is more expensive.
-            configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K4V, params));
-        }
-        if (has_ngram_mod) {
-            configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_NGRAM_MOD, params));
-        }
-        if (has_ngram_cache) {
-            configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_NGRAM_CACHE, params));
-        }
-        if (has_draft_simple) {
-            configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_DRAFT_SIMPLE, params));
-        }
-        if (has_draft_eagle3) {
-            configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3, params));
-        }
-        if (has_draft_mtp) {
-            configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_DRAFT_MTP, params));
-        }
-        if (has_draft_dflash) {
-            configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_DRAFT_DFLASH, params));
-        }
-        if (has_draft_dspark) {
-            configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_DRAFT_DSPARK, params));
-        }
+        add_config_if_enabled(COMMON_SPECULATIVE_TYPE_NGRAM_SIMPLE);
+        add_config_if_enabled(COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K);
+        add_config_if_enabled(COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K4V);
+        add_config_if_enabled(COMMON_SPECULATIVE_TYPE_NGRAM_MOD);
+        add_config_if_enabled(COMMON_SPECULATIVE_TYPE_NGRAM_CACHE);
+
+        add_config_if_enabled(COMMON_SPECULATIVE_TYPE_DRAFT_SIMPLE);
+        add_config_if_enabled(COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3, params.draft.ctx_dft != nullptr);
+        add_config_if_enabled(COMMON_SPECULATIVE_TYPE_DRAFT_MTP,    params.draft.ctx_dft != nullptr);
+        add_config_if_enabled(COMMON_SPECULATIVE_TYPE_DRAFT_DFLASH, params.draft.ctx_dft != nullptr);
+        add_config_if_enabled(COMMON_SPECULATIVE_TYPE_DRAFT_DSPARK, params.draft.ctx_dft != nullptr);
     }
 
     std::vector<std::unique_ptr<common_speculative_impl>> impls = {};

conversion/__init__.py

@@ -210,6 +210,7 @@ TEXT_MODEL_MAP: dict[str, str] = {
     "Qwen3MoeForCausalLM": "qwen",
     "Qwen3NextForCausalLM": "qwen",
     "Qwen3OmniMoeForConditionalGeneration": "qwen3vl",
+    "Qwen3TTSForConditionalGeneration": "qwen3tts",
     "Qwen3VLForConditionalGeneration": "qwen3vl",
     "Qwen3VLMoeForConditionalGeneration": "qwen3vl",
     "Qwen3_5ForCausalLM": "qwen",
@@ -304,6 +305,7 @@ MMPROJ_MODEL_MAP: dict[str, str] = {
     "Qwen2_5_VLForConditionalGeneration": "qwenvl",
     "Qwen3ASRForConditionalGeneration": "qwen3vl",
     "Qwen3OmniMoeForConditionalGeneration": "qwen3vl",
+    "Qwen3TTSForConditionalGeneration": "qwen3tts",
     "Qwen3VLForConditionalGeneration": "qwen3vl",
     "Qwen3VLMoeForConditionalGeneration": "qwen3vl",
     "Qwen3_5ForConditionalGeneration": "qwen3vl",

conversion/chatglm.py

@@ -81,7 +81,7 @@ class ChatGLMModel(TextModel):
 
     @staticmethod
     def token_bytes_to_string(b):
-        from transformers.models.gpt2.tokenization_gpt2 import bytes_to_unicode  # ty: ignore[unresolved-import]
+        from transformers.convert_slow_tokenizer import bytes_to_unicode
         byte_encoder = bytes_to_unicode()
         return ''.join([byte_encoder[ord(char)] for char in b.decode('latin-1')])
 

conversion/deepseek.py

@@ -535,7 +535,10 @@ class DeepseekV4Model(TextModel):
             logger.info("Skipping %d DeepSeek-V4 MTP tensor(s) for conversion v0", type(self)._skipped_mtp_tensors)
 
         # add a default chat template; if the model has a built-in template, it will be overridden later
-        template_path = Path(__file__).parent.parent / "models" / "templates" / "deepseek-ai-DeepSeek-V4.jinja"
+        model_id_hint = self.remote_hf_model_id or self.dir_model.name
+        is_0731 = "0731" in model_id_hint
+        template_name = "deepseek-ai-DeepSeek-V4-Flash-0731.jinja" if is_0731 else "deepseek-ai-DeepSeek-V4.jinja"
+        template_path = Path(__file__).parent.parent / "models" / "templates" / template_name
         if template_path.is_file():
             with open(template_path, "r", encoding="utf-8") as f:
                 self.gguf_writer.add_chat_template(f.read())

conversion/glm.py

@@ -206,10 +206,70 @@ class Glm4MoeModel(TextModel):
 @ModelBase.register("Glm4MoeLiteForCausalLM")
 class Glm4MoeLiteModel(DeepseekV2Model):
     model_arch = gguf.MODEL_ARCH.DEEPSEEK2
+    skip_mtp = False
+    supports_mtp_export = True
+    _n_main_layers: int | None = None
 
     def set_vocab(self):
         return self._set_vocab_glm()
 
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+
+        num_hidden_layers = self.hparams["num_hidden_layers"]
+        self.num_nextn_predict_layers = self.hparams.get("num_nextn_predict_layers", 0)
+        self.skip_mtp = self.no_mtp or self.num_nextn_predict_layers == 0
+
+        if self.skip_mtp:
+            self.block_count = num_hidden_layers
+        else:
+            self.block_count = num_hidden_layers + self.num_nextn_predict_layers
+
+        self.tensor_map = gguf.get_tensor_name_map(self.model_arch, self.block_count)
+
+    def set_gguf_parameters(self):
+        super().set_gguf_parameters()
+
+        if self.skip_mtp:
+            return
+
+        self.gguf_writer.add_nextn_predict_layers(self.num_nextn_predict_layers)
+
+    def index_tensors(self, remote_hf_model_id: str | None = None):
+        type(self)._n_main_layers = self.hparams["num_hidden_layers"]
+        return super().index_tensors(remote_hf_model_id=remote_hf_model_id)
+
+    @classmethod
+    def filter_tensors(cls, item):
+        if (titem := super().filter_tensors(item)) is None:
+            return None
+        name, gen = titem
+
+        if cls._n_main_layers is not None:
+            match = re.match(r"model\.layers\.(\d+)\.", name)
+            is_mtp = match is not None and int(match.group(1)) >= cls._n_main_layers
+            if is_mtp and cls.no_mtp:
+                return None
+            if cls.mtp_only and not is_mtp and name not in (
+                "model.embed_tokens.weight", "model.norm.weight", "lm_head.weight",
+            ):
+                return None
+
+        return name, gen
+
+    def prepare_metadata(self, vocab_only: bool):
+        from_dir = self.fname_out.is_dir()
+        super().prepare_metadata(vocab_only=vocab_only)
+
+        if not self.mtp_only or not from_dir:
+            return
+
+        output_type: str = self.ftype.name.partition("_")[2]
+        fname_default: str = gguf.naming_convention(
+            self.metadata.name, self.metadata.basename, self.metadata.finetune,
+            self.metadata.version, size_label=None, output_type=output_type, model_type=None)
+        self.fname_out = self.fname_out.parent / f"mtp-{fname_default}.gguf"
+
 
 @ModelBase.register("GlmMoeDsaForCausalLM")
 class GlmMoeDsaModel(DeepseekV2Model):

conversion/llama.py

@@ -119,7 +119,7 @@ class LlamaModel(TextModel):
         path_tekken_json = self.dir_model / "tekken.json"
         path_tokenizer_json = self.dir_model / "tokenizer.json"
         if path_tekken_json.is_file() and not path_tokenizer_json.is_file():
-            self._set_vocab_mistral()
+            return self._set_vocab_mistral()
 
         tokenizer_config_file = self.dir_model / 'tokenizer_config.json'
         if tokenizer_config_file.is_file():

conversion/qwen.py

@@ -18,7 +18,7 @@ class QwenModel(TextModel):
 
     @staticmethod
     def token_bytes_to_string(b):
-        from transformers.models.gpt2.tokenization_gpt2 import bytes_to_unicode  # ty: ignore[unresolved-import]
+        from transformers.convert_slow_tokenizer import bytes_to_unicode
         byte_encoder = bytes_to_unicode()
         return ''.join([byte_encoder[ord(char)] for char in b.decode('latin-1')])
 

conversion/qwen3tts.py

@@ -0,0 +1,471 @@
+from __future__ import annotations
+
+import json
+from pathlib import Path
+from typing import Any, Callable, Iterable, TYPE_CHECKING
+
+import torch
+import torch.nn.functional as F
+
+if TYPE_CHECKING:
+    from torch import Tensor
+
+from .base import ModelBase, MmprojModel, TextModel, gguf
+
+# Tricks being used to support this model via existing llama.cpp code paths:
+# - Text projection MLP is folded into the embedding table
+# - codec_embedding is concat to the text embedding table, vocab is extended
+#   example: codec_bos_id(2149) --> "<|codec_bos|>"
+#            codec_eos_token_id(2150) --> "<|codec_eos_token|>"
+#            codec_language_id.chinese(2055) --> "<|codec_language_chinese|>"
+#            other rows --> "<|codec_0|>", "<|codec_1|>", ..., "<|codec_1023|>"
+# - output tensor codec_head is smaller than vocab, so logits will be padded at inference time
+# - suppress_tokens is used to limit the backbone to only sample either semantic or EOS (stop) token
+
+# pipeline stage mapping:
+#   speaker reference encoder --> mapped to normal mtmd audio encoder
+#   backbone --> mapped to normal libllama text model (autoregressive)
+#   code_predictor --> MTMD_GEN_PROCESS_TYPE_GEN_CODE
+#   code2wav --> MTMD_GEN_PROCESS_TYPE_GEN_WAV
+
+# torch activation functions used by Qwen3TTSTalkerResizeMLP (config's hidden_act)
+_ACT2FN = {
+    "silu": F.silu,
+    "gelu": F.gelu,
+    "relu": F.relu,
+}
+
+
+@ModelBase.register("Qwen3TTSForConditionalGeneration")
+class Qwen3TTSTalkerModel(TextModel):
+    model_arch = gguf.MODEL_ARCH.QWEN3TTS
+
+    _TEXT_PROJ_KEYS = (
+        "model.text_embedding.weight",
+        "text_projection.linear_fc1.weight",
+        "text_projection.linear_fc1.bias",
+        "text_projection.linear_fc2.weight",
+        "text_projection.linear_fc2.bias",
+    )
+
+    _text_proj_buffer: dict[str, Tensor]
+    _folded_text_embed: Tensor | None
+    _codec_embed: Tensor | None
+
+    def __init__(self, dir_model: Path, *args, **kwargs):
+        hparams = kwargs.pop("hparams", None)
+        if hparams is None:
+            hparams = ModelBase.load_hparams(dir_model, is_mistral_format=False)
+        raw_talker_config = dict(hparams["talker_config"])
+        self._talker_config = raw_talker_config
+        self.n_codec_vocab = raw_talker_config["vocab_size"]
+        talker_config = dict(raw_talker_config)
+        talker_config["vocab_size"] = talker_config["text_vocab_size"]
+        hparams["text_config"] = talker_config
+        super().__init__(dir_model, *args, hparams=hparams, **kwargs)
+        self._text_proj_buffer = {}
+        self._folded_text_embed = None
+        self._codec_embed = None
+
+    def _codec_token_names(self) -> list[str]:
+        # start every row with a generic name, then override the ones with a
+        # known meaning (bos/eos/language/etc, derived from the *_id fields
+        # of talker_config) with a more descriptive one
+        names = [f"<|codec_{i}|>" for i in range(self.n_codec_vocab)]
+        for key, val in self._talker_config.items():
+            if not key.endswith("_id"):
+                continue
+            prefix = key[:-len("_id")]
+            if isinstance(val, int):
+                names[val] = f"<|{prefix}|>"
+            elif isinstance(val, dict):
+                for subkey, subval in val.items():
+                    names[subval] = f"<|{prefix}_{subkey}|>"
+        return names
+
+    def set_vocab(self):
+        codec_tokens = self._codec_token_names()
+        codec_toktypes = [gguf.TokenType.CONTROL] * len(codec_tokens)
+
+        try:
+            tokens, scores, toktypes = self._create_vocab_sentencepiece()
+            self.gguf_writer.add_tokenizer_model("llama")
+            self.gguf_writer.add_tokenizer_pre("default")
+            tokens += [t.encode("utf-8") for t in codec_tokens]
+            scores += [0.0] * len(codec_tokens)
+            toktypes += codec_toktypes
+            self.gguf_writer.add_token_list(tokens)
+            self.gguf_writer.add_token_scores(scores)
+            self.gguf_writer.add_token_types(toktypes)
+            special_vocab = gguf.SpecialVocab(self.dir_model, n_vocab=len(tokens))
+            special_vocab.add_to_gguf(self.gguf_writer)
+            return
+        except FileNotFoundError:
+            pass
+
+        tokens, toktypes, tokpre = self.get_vocab_base()
+        tokens += codec_tokens
+        toktypes += codec_toktypes
+        self.gguf_writer.add_tokenizer_model("gpt2")
+        self.gguf_writer.add_tokenizer_pre(tokpre)
+        self.gguf_writer.add_token_list(tokens)
+        self.gguf_writer.add_token_types(toktypes)
+
+        special_vocab = gguf.SpecialVocab(self.dir_model, load_merges=True)
+        special_vocab.add_to_gguf(self.gguf_writer)
+
+        # make sure that the model has no chat template, so chat will be disabled
+        self.gguf_writer.add_chat_template(None)
+
+    def set_gguf_parameters(self):
+        super().set_gguf_parameters()
+
+        # note: final vocab layout is [text_vocab | codec_vocab], with text_vocab is actually padded with -inf in cgraph
+        # for codec_vocab, only first 2048 rows can be sampled for semantic code
+        # plus codec_eos_token_id that used for signaling end of generation
+        # ref: https://github.com/QwenLM/Qwen3-TTS/blob/022e286b98fbec7e1e916cb940cdf532cd9f488e/qwen_tts/core/models/modeling_qwen3_tts.py#L2059-L2063
+
+        vocab_size = self.hparams["vocab_size"] + self.n_codec_vocab
+        codec_eos_token_id = self.hparams["vocab_size"] + self._talker_config["codec_eos_token_id"]
+        self.gguf_writer.add_suppress_tokens([
+            i for i in range(vocab_size - 1024, vocab_size)
+            if i != codec_eos_token_id
+        ])
+        self.gguf_writer.add_eos_token_id(codec_eos_token_id)
+        self.gguf_writer.add_add_eos_token(False)
+
+    @classmethod
+    def filter_tensors(cls, item: tuple[str, Callable[[], Tensor]]) -> tuple[str, Callable[[], Tensor]] | None:
+        name, gen = item
+
+        if not name.startswith("talker.") or name.startswith("talker.code_predictor."):
+            return None
+
+        name = name[len("talker."):]
+        return super().filter_tensors((name, gen))
+
+    def _maybe_emit_token_embd(self) -> Iterable[tuple[str, Tensor]]:
+        if self._folded_text_embed is None or self._codec_embed is None:
+            return
+        combined = torch.cat([self._folded_text_embed, self._codec_embed], dim=0)
+        yield (self.format_tensor_name(gguf.MODEL_TENSOR.TOKEN_EMBD), combined)
+
+    def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
+        # codec_embedding rows are appended after the text vocab, extending the embedding table
+        if name == "model.codec_embedding.weight":
+            self._codec_embed = data_torch
+            yield from self._maybe_emit_token_embd()
+            return
+
+        # codec_head is the output head for the (smaller) codec vocab; logits get padded to
+        # the extended vocab size at inference time
+        if name == "codec_head.weight":
+            yield (self.format_tensor_name(gguf.MODEL_TENSOR.OUTPUT), data_torch)
+            return
+
+        if name in self._TEXT_PROJ_KEYS:
+            self._text_proj_buffer[name] = data_torch
+            if len(self._text_proj_buffer) < len(self._TEXT_PROJ_KEYS):
+                return
+
+            # fold MLP into the embedding table at conversion time, MLP won't be used at inference time anyway
+            act_fn = _ACT2FN[self.hparams["hidden_act"]]
+            embed = self._text_proj_buffer["model.text_embedding.weight"]
+            hidden = act_fn(F.linear(embed,
+                                     self._text_proj_buffer["text_projection.linear_fc1.weight"],
+                                     self._text_proj_buffer["text_projection.linear_fc1.bias"]))
+            folded = F.linear(hidden,
+                              self._text_proj_buffer["text_projection.linear_fc2.weight"],
+                              self._text_proj_buffer["text_projection.linear_fc2.bias"])
+            self._folded_text_embed = folded
+            yield from self._maybe_emit_token_embd()
+            return
+
+        yield from super().modify_tensors(data_torch, name, bid)
+
+
+@ModelBase.register("Qwen3TTSForConditionalGeneration")
+class Qwen3TTSSpeakerEncoderModel(MmprojModel):
+    has_vision_encoder = False
+    has_audio_encoder = True
+
+    # talker.code_predictor.model.layers.{bid}.<key> -> A_GEN_CODE_*
+    # bypass tensor_mapping.py for now to make it simple
+    _CODE_LAYER_TENSOR_MAP = {
+        "input_layernorm": gguf.MODEL_TENSOR.A_GEN_CODE_ATTN_NORM,
+        "self_attn.q_proj": gguf.MODEL_TENSOR.A_GEN_CODE_ATTN_Q,
+        "self_attn.q_norm": gguf.MODEL_TENSOR.A_GEN_CODE_ATTN_Q_NORM,
+        "self_attn.k_proj": gguf.MODEL_TENSOR.A_GEN_CODE_ATTN_K,
+        "self_attn.k_norm": gguf.MODEL_TENSOR.A_GEN_CODE_ATTN_K_NORM,
+        "self_attn.v_proj": gguf.MODEL_TENSOR.A_GEN_CODE_ATTN_V,
+        "self_attn.o_proj": gguf.MODEL_TENSOR.A_GEN_CODE_ATTN_OUT,
+        "post_attention_layernorm": gguf.MODEL_TENSOR.A_GEN_CODE_FFN_NORM,
+        "mlp.gate_proj": gguf.MODEL_TENSOR.A_GEN_CODE_FFN_GATE,
+        "mlp.up_proj": gguf.MODEL_TENSOR.A_GEN_CODE_FFN_UP,
+        "mlp.down_proj": gguf.MODEL_TENSOR.A_GEN_CODE_FFN_DOWN,
+    }
+
+    # note: codebook pages will be stacked to 3D
+    _CODE_GEN_N_CODEBOOKS = 15
+    _code_embed_buffer: dict[int, Tensor] = {}
+    _code_head_buffer: dict[int, Tensor] = {}
+    _wav_config_cache: dict[str, Any] | None = None
+
+    def __init__(self, dir_model: Path, *args, **kwargs):
+        hparams = kwargs.pop("hparams", None)
+        if hparams is None:
+            hparams = ModelBase.load_hparams(dir_model, is_mistral_format=False)
+        hparams["text_config"] = {"hidden_size": hparams["talker_config"]["hidden_size"]}
+        # ECAPA-TDNN has a fixed 4-stage backbone, but MmprojModel.__init__ needs a n_block_keys
+        hparams["speaker_encoder_config"]["n_layers"] = 4
+        super().__init__(dir_model, *args, hparams=hparams, **kwargs)
+        self._wav_config_cache = None
+
+    def get_audio_config(self) -> dict[str, Any] | None:
+        return self.global_config.get("speaker_encoder_config")
+
+    def set_gguf_parameters(self):
+        self.gguf_writer.add_file_type(self.ftype)
+        self.gguf_writer.add_clip_has_audio_encoder(True)
+        self.gguf_writer.add_clip_audio_projector_type(gguf.VisionProjectorType.QWEN3TTS_SPKENC)
+
+        # handle speaker encoder config
+        self.gguf_writer.add_audio_projection_dim(self.n_embd_text)
+        # mel_spectrogram() front-end: sr=24000, n_fft=1024, hop=256, n_mels=128, fmin=0, fmax=12000 (=sr/2, the clip.cpp default)
+        self.gguf_writer.add_audio_num_mel_bins(128)
+        # 3 SE-Res2Net stages; the stem conv, mfa, asp and fc are not counted here
+        self.gguf_writer.add_audio_block_count(3)
+        # ECAPA-TDNN has no attention/FFN, these are dummy to allow clip.cpp to load it
+        self.gguf_writer.add_audio_embedding_length(1536)
+        self.gguf_writer.add_audio_head_count(1)
+        self.gguf_writer.add_audio_feed_forward_length(1536)
+        self.gguf_writer.add_audio_attention_layernorm_eps(1e-5)
+
+        # handle code predictor config
+        self.gguf_writer.add_clip_has_gen_audio_encoder(True)
+        self.gguf_writer.add_clip_gen_audio_projector_type(gguf.VisionProjectorType.QWEN3TTS_GEN)
+        code_predictor_config = self.global_config["talker_config"]["code_predictor_config"]
+        self.gguf_writer.add_gen_audio_projection_dim(self.n_embd_text)
+        self.gguf_writer.add_gen_audio_embedding_length(code_predictor_config["hidden_size"])
+        self.gguf_writer.add_gen_audio_feed_forward_length(code_predictor_config["intermediate_size"])
+        self.gguf_writer.add_gen_audio_block_count(code_predictor_config["num_hidden_layers"])
+        self.gguf_writer.add_gen_audio_head_count(code_predictor_config["num_attention_heads"])
+        self.gguf_writer.add_gen_audio_head_count_kv(code_predictor_config["num_key_value_heads"])
+        self.gguf_writer.add_gen_audio_attention_layernorm_eps(code_predictor_config["rms_norm_eps"])
+        # note: code2wav hparams are hardcoded on the mtmd/clip.cpp side for now, not written here
+
+    def _wav_decoder_config(self) -> dict[str, Any] | None:
+        # code2wav has its own config.json, inside the speech_tokenizer dir
+        if self._wav_config_cache is None:
+            path = self.dir_model / "speech_tokenizer" / "config.json"
+            with open(path, "r", encoding="utf-8") as f:
+                cfg = json.load(f)
+            self._wav_config_cache = cfg["decoder_config"]
+        return self._wav_config_cache
+
+    def tensor_force_quant(self, name, new_name, bid, n_dims):
+        # conv1d/conv1d_dw kernels must be F16, ggml_conv_1d(_dw) has no BF16 path
+        if new_name.endswith(".weight") and (
+            new_name in ("a.gen.wav.pre_conv.weight", "a.gen.wav.dac.entry.weight", "a.gen.wav.dac.post_conv.weight")
+            or (".up.blk." in new_name and new_name.endswith(".dwconv.weight"))
+            or (".dac.blk." in new_name and (new_name.endswith(".conv1.weight") or new_name.endswith(".conv2.weight")))
+        ):
+            return gguf.GGMLQuantizationType.F16
+        # ConvTranspose1d kernels: only F16/F32 are implemented, no BF16
+        if new_name.endswith(".conv.weight") and (".up.blk." in new_name or ".dac.blk." in new_name):
+            return gguf.GGMLQuantizationType.F32
+        return super().tensor_force_quant(name, new_name, bid, n_dims)
+
+    @classmethod
+    def filter_tensors(cls, item: tuple[str, Callable[[], Tensor]]) -> tuple[str, Callable[[], Tensor]] | None:
+        name, gen = item
+
+        if not (
+            name.startswith("speaker_encoder.")
+            or name.startswith("talker.code_predictor.")
+            or name == "talker.model.codec_embedding.weight"
+        ):
+            return None
+
+        return super().filter_tensors((name, gen))
+
+    def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
+        # code2wav tensors are already named by generate_extra_tensors(), pass them through
+        if name.startswith("a.gen.wav."):
+            yield (name, data_torch)
+            return
+
+        # codebook-0 embedding, fed back to the talker backbone (codebooks 1-15 live in code_predictor)
+        if name == "talker.model.codec_embedding.weight":
+            yield (self.format_tensor_name(gguf.MODEL_TENSOR.A_GEN_CODE_OUT_EMBD), data_torch)
+            return
+
+        if name == "talker.code_predictor.model.norm.weight":
+            yield (self.format_tensor_name(gguf.MODEL_TENSOR.A_GEN_CODE_OUTPUT_NORM), data_torch)
+            return
+
+        if name.startswith("talker.code_predictor.small_to_mtp_projection."):
+            suffix = "." + name.rsplit(".", 1)[1]
+            yield (self.format_tensor_name(gguf.MODEL_TENSOR.A_GEN_CODE_PROJ_IN, suffix=suffix), data_torch)
+            return
+
+        if name.startswith("talker.code_predictor.model.codec_embedding."):
+            idx = int(name.split("codec_embedding.")[1].split(".")[0])
+            self._code_embed_buffer[idx] = data_torch
+            if len(self._code_embed_buffer) < self._CODE_GEN_N_CODEBOOKS:
+                return
+            stacked = torch.stack([self._code_embed_buffer.pop(i) for i in range(self._CODE_GEN_N_CODEBOOKS)], dim=0)
+            yield (self.format_tensor_name(gguf.MODEL_TENSOR.A_GEN_CODE_EMBD), stacked)
+            return
+
+        if name.startswith("talker.code_predictor.lm_head."):
+            idx = int(name.split("lm_head.")[1].split(".")[0])
+            self._code_head_buffer[idx] = data_torch
+            if len(self._code_head_buffer) < self._CODE_GEN_N_CODEBOOKS:
+                return
+            stacked = torch.stack([self._code_head_buffer.pop(i) for i in range(self._CODE_GEN_N_CODEBOOKS)], dim=0)
+            yield (self.format_tensor_name(gguf.MODEL_TENSOR.A_GEN_CODE_HEAD), stacked)
+            return
+
+        if name.startswith("talker.code_predictor.model.layers."):
+            rest = name.split("model.layers.")[1]        # "{bid}.<key>.weight"
+            _, key_with_suffix = rest.split(".", 1)       # "<key>.weight"
+            key = key_with_suffix.rsplit(".", 1)[0]        # "<key>"
+            tensor = self._CODE_LAYER_TENSOR_MAP.get(key)
+            if tensor is not None:
+                yield (self.format_tensor_name(tensor, bid), data_torch)
+                return
+
+        if "res2net_block.blocks." in name:
+            assert bid is not None  # the outer stage index, picked up from the tensor name automatically
+            xid = int(name.split("res2net_block.blocks.")[1].split(".")[0])
+            suffix = "." + name.rsplit(".", 1)[1]
+            new_name = gguf.TENSOR_NAMES[gguf.MODEL_TENSOR.A_ENC_CONV_RES2].format(bid=bid, xid=xid) + suffix
+            yield (new_name, data_torch)
+            return
+
+        yield from super().modify_tensors(data_torch, name, bid)
+
+    def generate_extra_tensors(self) -> Iterable[tuple[str, Tensor]]:
+        yield from self._generate_code2wav_tensors()
+
+    def _generate_code2wav_tensors(self) -> Iterable[tuple[str, Tensor]]:
+        # code2wav weights live in speech_tokenizer/model.safetensors, not the main safetensors
+        from safetensors.torch import load_file
+
+        wav_config = self._wav_decoder_config()
+        state_dict = load_file(self.dir_model / "speech_tokenizer" / "model.safetensors")
+
+        def get(name: str) -> Tensor:
+            return state_dict[name]
+
+        def snake_fold(alpha: Tensor, beta: Tensor) -> tuple[Tensor, Tensor]:
+            # fold SnakeBeta's exp()/reciprocal here, so the graph is only mul/sin/sqr/mul/add
+            return torch.exp(alpha), 1.0 / (torch.exp(beta) + 1e-9)
+
+        def rvq_codebook(prefix: str, n_layers: int) -> Tensor:
+            # checkpoint has EMA accumulators, so codebook[i] = embedding_sum[i] / cluster_usage[i]
+            books = []
+            for i in range(n_layers):
+                embedding_sum = get(f"{prefix}.vq.layers.{i}._codebook.embedding_sum")
+                cluster_usage = get(f"{prefix}.vq.layers.{i}._codebook.cluster_usage")
+                books.append(embedding_sum / cluster_usage.clamp_min(1e-5).unsqueeze(-1))
+            return torch.stack(books, dim=0) if n_layers > 1 else books[0]
+
+        T = gguf.MODEL_TENSOR
+
+        # --- quantizer: RVQ codebook decode ---
+        yield (self.format_tensor_name(T.A_GEN_WAV_QUANT_FIRST_IN), get("decoder.quantizer.rvq_first.input_proj.weight").squeeze(-1))
+        yield (self.format_tensor_name(T.A_GEN_WAV_QUANT_FIRST_OUT), get("decoder.quantizer.rvq_first.output_proj.weight").squeeze(-1))
+        yield (self.format_tensor_name(T.A_GEN_WAV_QUANT_FIRST_CB), rvq_codebook("decoder.quantizer.rvq_first", 1))
+        yield (self.format_tensor_name(T.A_GEN_WAV_QUANT_REST_IN), get("decoder.quantizer.rvq_rest.input_proj.weight").squeeze(-1))
+        yield (self.format_tensor_name(T.A_GEN_WAV_QUANT_REST_OUT), get("decoder.quantizer.rvq_rest.output_proj.weight").squeeze(-1))
+        yield (self.format_tensor_name(T.A_GEN_WAV_QUANT_REST_CB), rvq_codebook("decoder.quantizer.rvq_rest", self._CODE_GEN_N_CODEBOOKS))
+
+        # --- pre_conv ---
+        yield (self.format_tensor_name(T.A_GEN_WAV_PRE_CONV, suffix=".weight"), get("decoder.pre_conv.conv.weight"))
+        yield (self.format_tensor_name(T.A_GEN_WAV_PRE_CONV, suffix=".bias"), get("decoder.pre_conv.conv.bias"))
+
+        # --- pre_transformer ---
+        yield (self.format_tensor_name(T.A_GEN_WAV_TFM_IN_PROJ, suffix=".weight"), get("decoder.pre_transformer.input_proj.weight"))
+        yield (self.format_tensor_name(T.A_GEN_WAV_TFM_IN_PROJ, suffix=".bias"), get("decoder.pre_transformer.input_proj.bias"))
+        yield (self.format_tensor_name(T.A_GEN_WAV_TFM_OUT_PROJ, suffix=".weight"), get("decoder.pre_transformer.output_proj.weight"))
+        yield (self.format_tensor_name(T.A_GEN_WAV_TFM_OUT_PROJ, suffix=".bias"), get("decoder.pre_transformer.output_proj.bias"))
+        yield (self.format_tensor_name(T.A_GEN_WAV_TFM_OUTPUT_NORM), get("decoder.pre_transformer.norm.weight"))
+
+        tfm_layer_map = {
+            "input_layernorm.weight":         T.A_GEN_WAV_TFM_ATTN_NORM,
+            "self_attn.q_proj.weight":        T.A_GEN_WAV_TFM_ATTN_Q,
+            "self_attn.k_proj.weight":        T.A_GEN_WAV_TFM_ATTN_K,
+            "self_attn.v_proj.weight":        T.A_GEN_WAV_TFM_ATTN_V,
+            "self_attn.o_proj.weight":        T.A_GEN_WAV_TFM_ATTN_OUT,
+            "self_attn_layer_scale.scale":    T.A_GEN_WAV_TFM_ATTN_SCALE,
+            "post_attention_layernorm.weight": T.A_GEN_WAV_TFM_FFN_NORM,
+            "mlp.gate_proj.weight":           T.A_GEN_WAV_TFM_FFN_GATE,
+            "mlp.up_proj.weight":             T.A_GEN_WAV_TFM_FFN_UP,
+            "mlp.down_proj.weight":           T.A_GEN_WAV_TFM_FFN_DOWN,
+            "mlp_layer_scale.scale":          T.A_GEN_WAV_TFM_FFN_SCALE,
+        }
+        assert wav_config is not None
+        for bid in range(wav_config["num_hidden_layers"]):
+            for key, tensor_id in tfm_layer_map.items():
+                yield (self.format_tensor_name(tensor_id, bid), get(f"decoder.pre_transformer.layers.{bid}.{key}"))
+
+        # --- upsample: 2x (causal ConvTranspose1d + ConvNeXt block) ---
+        up_map = {
+            "0.conv.weight":     (T.A_GEN_WAV_UP_CONV, ".weight"),
+            "0.conv.bias":       (T.A_GEN_WAV_UP_CONV, ".bias"),
+            "1.dwconv.conv.weight": (T.A_GEN_WAV_UP_DWCONV, ".weight"),
+            "1.dwconv.conv.bias":   (T.A_GEN_WAV_UP_DWCONV, ".bias"),
+            "1.norm.weight":     (T.A_GEN_WAV_UP_NORM, ".weight"),
+            "1.norm.bias":       (T.A_GEN_WAV_UP_NORM, ".bias"),
+            "1.pwconv1.weight":  (T.A_GEN_WAV_UP_PW1, ".weight"),
+            "1.pwconv1.bias":    (T.A_GEN_WAV_UP_PW1, ".bias"),
+            "1.pwconv2.weight":  (T.A_GEN_WAV_UP_PW2, ".weight"),
+            "1.pwconv2.bias":    (T.A_GEN_WAV_UP_PW2, ".bias"),
+            "1.gamma":           (T.A_GEN_WAV_UP_GAMMA, ""),
+        }
+        for bid in range(len(wav_config["upsampling_ratios"])):
+            for key, (tensor_id, suffix) in up_map.items():
+                yield (self.format_tensor_name(tensor_id, bid, suffix=suffix), get(f"decoder.upsample.{bid}.{key}"))
+
+        # --- DAC decoder ---
+        yield (self.format_tensor_name(T.A_GEN_WAV_DAC_ENTRY, suffix=".weight"), get("decoder.decoder.0.conv.weight"))
+        yield (self.format_tensor_name(T.A_GEN_WAV_DAC_ENTRY, suffix=".bias"), get("decoder.decoder.0.conv.bias"))
+
+        n_dac_blocks = len(wav_config["upsample_rates"])
+        for bid in range(n_dac_blocks):
+            py = bid + 1  # decoder.decoder.0 is the entry conv, blocks start at 1
+
+            a, b = snake_fold(get(f"decoder.decoder.{py}.block.0.alpha"), get(f"decoder.decoder.{py}.block.0.beta"))
+            yield (self.format_tensor_name(T.A_GEN_WAV_DAC_UP_SNAKE, bid, suffix=".alpha"), a)
+            yield (self.format_tensor_name(T.A_GEN_WAV_DAC_UP_SNAKE, bid, suffix=".beta"), b)
+            yield (self.format_tensor_name(T.A_GEN_WAV_DAC_UP_CONV, bid, suffix=".weight"), get(f"decoder.decoder.{py}.block.1.conv.weight"))
+            yield (self.format_tensor_name(T.A_GEN_WAV_DAC_UP_CONV, bid, suffix=".bias"), get(f"decoder.decoder.{py}.block.1.conv.bias"))
+
+            for xid in range(3):
+                ridx = xid + 2  # block.2/3/4 are the 3 residual units
+
+                a1, b1 = snake_fold(get(f"decoder.decoder.{py}.block.{ridx}.act1.alpha"), get(f"decoder.decoder.{py}.block.{ridx}.act1.beta"))
+                name1 = gguf.TENSOR_NAMES[T.A_GEN_WAV_DAC_RES_ACT1].format(bid=bid, xid=xid)
+                yield (name1 + ".alpha", a1)
+                yield (name1 + ".beta", b1)
+
+                name_conv1 = gguf.TENSOR_NAMES[T.A_GEN_WAV_DAC_RES_CONV1].format(bid=bid, xid=xid)
+                yield (name_conv1 + ".weight", get(f"decoder.decoder.{py}.block.{ridx}.conv1.conv.weight"))
+                yield (name_conv1 + ".bias", get(f"decoder.decoder.{py}.block.{ridx}.conv1.conv.bias"))
+
+                a2, b2 = snake_fold(get(f"decoder.decoder.{py}.block.{ridx}.act2.alpha"), get(f"decoder.decoder.{py}.block.{ridx}.act2.beta"))
+                name2 = gguf.TENSOR_NAMES[T.A_GEN_WAV_DAC_RES_ACT2].format(bid=bid, xid=xid)
+                yield (name2 + ".alpha", a2)
+                yield (name2 + ".beta", b2)
+
+                name_conv2 = gguf.TENSOR_NAMES[T.A_GEN_WAV_DAC_RES_CONV2].format(bid=bid, xid=xid)
+                yield (name_conv2 + ".weight", get(f"decoder.decoder.{py}.block.{ridx}.conv2.conv.weight"))
+                yield (name_conv2 + ".bias", get(f"decoder.decoder.{py}.block.{ridx}.conv2.conv.bias"))
+
+        a5, b5 = snake_fold(get("decoder.decoder.5.alpha"), get("decoder.decoder.5.beta"))
+        yield (self.format_tensor_name(T.A_GEN_WAV_DAC_POST_SNAKE, suffix=".alpha"), a5)
+        yield (self.format_tensor_name(T.A_GEN_WAV_DAC_POST_SNAKE, suffix=".beta"), b5)
+        yield (self.format_tensor_name(T.A_GEN_WAV_DAC_POST_CONV, suffix=".weight"), get("decoder.decoder.6.conv.weight"))
+        yield (self.format_tensor_name(T.A_GEN_WAV_DAC_POST_CONV, suffix=".bias"), get("decoder.decoder.6.conv.bias"))

docs/development/HOWTO-add-model.md

@@ -133,6 +133,7 @@ Note:
 - To debug the multimodal preprocessor and encoder, you can use [llama-mtmd-debug](tools/mtmd/debug/mtmd-debug.cpp).
 - Adding a model-specific API or CLI is an anti-pattern in `libmtmd`. The goal of `libmtmd` is to provide an easy-to-use, model-agnostic library for multimodal pipeline.
 - In most cases, `llama-mtmd-cli` should not be modified. If a model requires a specific prompt, either let the user provide it or bake it into the Jinja chat template.
+- For audio generation models, see `tools/mtmd/README-dev.md`
 
 ## Tips and tricks
 

docs/ops.md

@@ -23,16 +23,16 @@ Legend:
 |                           ARGMAX | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                          ARGSORT | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                             CEIL | ❌ | ❌ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
-|                            CLAMP | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | 🟡 | ✅ | 🟡 | ✅ | ❌ | ❌ |
-|                        COL2IM_1D | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
+|                            CLAMP | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ |
+|                        COL2IM_1D | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
 |                           CONCAT | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | 🟡 | ❌ | ❌ |
 |                             CONT | ❌ | 🟡 | ✅ | ✅ | 🟡 | ✅ | 🟡 | ✅ | ✅ | 🟡 | ❌ | ❌ |
-|                          CONV_2D | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
+|                          CONV_2D | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ❌ | ❌ |
 |                       CONV_2D_DW | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
-|                          CONV_3D | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
+|                          CONV_3D | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
 |                CONV_TRANSPOSE_1D | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
 |                CONV_TRANSPOSE_2D | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
-|                              COS | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | 🟡 | ✅ | ❌ | ❌ |
+|                              COS | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                      COUNT_EQUAL | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
 |                              CPY | ❌ | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | ❌ | ❌ |
 |               CROSS_ENTROPY_LOSS | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
@@ -51,8 +51,8 @@ Legend:
 |                             FILL | ❌ | ❌ | ✅ | ✅ | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                   FLASH_ATTN_EXT | ❌ | 🟡 | ✅ | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | ❌ | ❌ |
 |                            FLOOR | ❌ | ❌ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
-|                  GATED_DELTA_NET | ❌ | ❌ | ✅ | ❌ | ✅ | 🟡 | ❌ | ✅ | 🟡 | ✅ | ❌ | ❌ |
-|                GATED_LINEAR_ATTN | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
+|                  GATED_DELTA_NET | ❌ | ❌ | ✅ | ❌ | ✅ | 🟡 | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
+|                GATED_LINEAR_ATTN | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
 |                            GEGLU | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                        GEGLU_ERF | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                      GEGLU_QUICK | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
@@ -60,14 +60,14 @@ Legend:
 |                         GELU_ERF | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                       GELU_QUICK | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                         GET_ROWS | ❌ | 🟡 | ✅ | 🟡 | 🟡 | 🟡 | 🟡 | ✅ | ✅ | 🟡 | ❌ | ❌ |
-|                    GET_ROWS_BACK | ❌ | ❌ | 🟡 | 🟡 | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
+|                    GET_ROWS_BACK | ❌ | ❌ | 🟡 | 🟡 | ❌ | ❌ | ❌ | ❌ | 🟡 | ❌ | ❌ | ❌ |
 |                       GROUP_NORM | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ |
 |                      HARDSIGMOID | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                        HARDSWISH | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                           IM2COL | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                        IM2COL_3D | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
 |                          L2_NORM | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ❌ | ✅ | ✅ | 🟡 | ❌ | ❌ |
-|                       LEAKY_RELU | ❌ | ✅ | ✅ | ✅ | ❌ | 🟡 | ❌ | ✅ | 🟡 | ❌ | ❌ | ❌ |
+|                       LEAKY_RELU | ❌ | ✅ | ✅ | ✅ | ❌ | 🟡 | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
 |                LIGHTNING_INDEXER | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
 |                              LOG | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                             MEAN | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ |
@@ -76,13 +76,13 @@ Legend:
 |                 MUL_MAT_HADAMARD | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                       MUL_MAT_ID | ❌ | 🟡 | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | ✅ | 🟡 | 🟡 | ❌ |
 |                              NEG | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
-|                             NORM | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ✅ | ✅ | 🟡 | 🟡 | ❌ | ❌ |
+|                             NORM | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ✅ | ✅ | ✅ | 🟡 | ❌ | ❌ |
 |                   OPT_STEP_ADAMW | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ |
 |                     OPT_STEP_SGD | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ |
-|                         OUT_PROD | 🟡 | 🟡 | 🟡 | 🟡 | ❌ | ❌ | ❌ | 🟡 | ❌ | ❌ | ❌ | 🟡 |
+|                         OUT_PROD | 🟡 | 🟡 | 🟡 | 🟡 | ❌ | ❌ | ❌ | 🟡 | 🟡 | ❌ | ❌ | 🟡 |
 |                              PAD | ❌ | 🟡 | ✅ | 🟡 | ❌ | 🟡 | 🟡 | 🟡 | ✅ | ✅ | ❌ | ❌ |
 |                   PAD_REFLECT_1D | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
-|                          POOL_1D | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
+|                          POOL_1D | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
 |                          POOL_2D | ❌ | 🟡 | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
 |                            REGLU | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                             RELU | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ |
@@ -103,13 +103,13 @@ Legend:
 |                          SIGMOID | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                             SILU | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                        SILU_BACK | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ |
-|                              SIN | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | 🟡 | ✅ | ❌ | ❌ |
+|                              SIN | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                         SOFTPLUS | ❌ | ❌ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                         SOFT_MAX | ❌ | 🟡 | ✅ | ✅ | 🟡 | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                    SOFT_MAX_BACK | ❌ | ❌ | 🟡 | 🟡 | ❌ | ❌ | ❌ | 🟡 | ✅ | ❌ | ❌ | ❌ |
 |                        SOLVE_TRI | ❌ | ❌ | ✅ | 🟡 | 🟡 | ✅ | ❌ | 🟡 | ✅ | ✅ | ❌ | ❌ |
-|                              SQR | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ✅ | ✅ | 🟡 | ✅ | ❌ | ❌ |
-|                             SQRT | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ❌ | ❌ |
+|                              SQR | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
+|                             SQRT | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                         SSM_CONV | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
 |                         SSM_SCAN | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | 🟡 | 🟡 | ✅ | ❌ | ❌ |
 |                             STEP | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |

ggml/CMakeLists.txt

@@ -5,7 +5,7 @@ project("ggml" C CXX ASM)
 ### GGML Version
 set(GGML_VERSION_MAJOR 0)
 set(GGML_VERSION_MINOR 18)
-set(GGML_VERSION_PATCH 0)
+set(GGML_VERSION_PATCH 1)
 set(GGML_VERSION_BASE "${GGML_VERSION_MAJOR}.${GGML_VERSION_MINOR}.${GGML_VERSION_PATCH}")
 
 list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/cmake/")

ggml/src/ggml-sycl/concat.cpp

@@ -127,7 +127,15 @@ static void concat_T_sycl_non_cont(
     int64_t ne2, int64_t ne3, uint64_t nb0, uint64_t nb1, uint64_t nb2,
     uint64_t nb3, int32_t dim) {
   sycl::range<3> gridDim(ne3, ne2, ne1);
-  stream->parallel_for(sycl::nd_range<3>(gridDim, sycl::range<3>(1, 1, 1)), [=](sycl::nd_item<3> item_ct1) {
+
+  // Avoid oversubscribing device when there is not enough elements along the innermost dim to
+  // fill a full SYCL_CONCAT_BLOCK_SIZE. For larger # of elements, the full SYCL_CONCAT_BLOCK_SIZE
+  // is used.
+  const int64_t ne0_pad   = GGML_PAD(ne0, WARP_SIZE);
+  const int64_t block_ne0 = ne0_pad < SYCL_CONCAT_BLOCK_SIZE ? ne0_pad : (int64_t) SYCL_CONCAT_BLOCK_SIZE;
+  sycl::range<3> blockDim(1, 1, block_ne0);
+
+  stream->parallel_for(sycl::nd_range<3>(gridDim * blockDim, blockDim), [=](sycl::nd_item<3> item_ct1) {
       int64_t i3 = item_ct1.get_group(0);
       int64_t i2 = item_ct1.get_group(1);
       int64_t i1 = item_ct1.get_group(2);

ggml/src/ggml-sycl/fattn-onednn.cpp

@@ -2,11 +2,13 @@
 #include <cstdio>
 #include <cstring>
 #include <string>
+#include <optional>
 #include <unordered_map>
 #include <vector>
 
 #include "fattn-onednn.hpp"
 #include "fattn-tile.hpp"
+#include "convert.hpp"
 
 // set minimum query length to treat as prefill (32)
 #define GGML_SYCL_FA_ONEDNN_MIN_Q 32
@@ -33,10 +35,30 @@ bool ggml_sycl_flash_attn_ext_onednn_supported(const ggml_tensor * dst) {
     const ggml_tensor * mask  = dst->src[3];
     const ggml_tensor * sinks = dst->src[4];
 
-    // gate for f16 KV only for now
-    // need to implement quantized KV
+    // F16 KV: native SDPA at any KV length.
+    // Non-F16: dequant to F16 then SDPA at prefill lengths. Only the
+    // standard quantized KV cache types (Q4_0-Q8_0) and F32 are accepted
+    // because their to_fp16_sycl conversion is verified. BF16 and IQ*
+    // are excluded: BF16 needs a strided conversion kernel that does not
+    // exist yet; IQ types are model-weight-only quants with no dequant
+    // registration and are never used as KV caches.
     if (K->type != GGML_TYPE_F16 || V->type != GGML_TYPE_F16) {
-        return false;
+        auto kt = K->type, vt = V->type;
+        bool k_ok = kt == GGML_TYPE_F32 || kt == GGML_TYPE_Q4_0 || kt == GGML_TYPE_Q4_1 ||
+                    kt == GGML_TYPE_Q5_0 || kt == GGML_TYPE_Q5_1 || kt == GGML_TYPE_Q8_0;
+        bool v_ok = vt == GGML_TYPE_F32 || vt == GGML_TYPE_Q4_0 || vt == GGML_TYPE_Q4_1 ||
+                    vt == GGML_TYPE_Q5_0 || vt == GGML_TYPE_Q5_1 || vt == GGML_TYPE_Q8_0;
+        if (!k_ok || !v_ok) {
+            return false;
+        }
+        if (Q->ne[1] < 32 || K->ne[1] < 1024) {
+            return false;
+        }
+        for (const ggml_tensor * t : {K, V}) {
+            if (t->type == GGML_TYPE_F16 && t->nb[1] % (t->ne[0] * 2) != 0) {
+                return false;
+            }
+        }
     }
     // Optional KV-length ceiling (GGML_SYCL_FA_ONEDNN_MAX_KV, 0 = unlimited). Escape hatch:
     // very long sequences make the fused SDPA slow enough to risk the xe driver watchdog on
@@ -205,13 +227,101 @@ void ggml_sycl_flash_attn_ext_onednn(ggml_backend_sycl_context & ctx, ggml_tenso
     dnnl::engine    eng    = ctx.engine_dnnl(stream);
     dnnl::stream    strm   = ctx.stream_dnnl(stream);
 
-    // cont/cast inputs to contiguous f16 (head-major) -- the layout the fast systolic path wants.
-    ggml_sycl_pool_alloc<sycl::half> Qf(ctx.pool(), (size_t) H   * q   * d);
-    ggml_sycl_pool_alloc<sycl::half> Kf(ctx.pool(), (size_t) Hkv * seq * d);
-    ggml_sycl_pool_alloc<sycl::half> Vf(ctx.pool(), (size_t) Hkv * seq * d);
-    cont_to_f16_sycl<float>     ((const char *) Q->data, Qf.get(), d, q,   H,   mb, Q->nb[1], Q->nb[2], Q->nb[3], stream);
-    cont_to_f16_sycl<sycl::half>((const char *) K->data, Kf.get(), d, seq, Hkv, mb, K->nb[1], K->nb[2], K->nb[3], stream);
-    cont_to_f16_sycl<sycl::half>((const char *) V->data, Vf.get(), d, seq, Hkv, mb, V->nb[1], V->nb[2], V->nb[3], stream);
+    // Q: always f32 -- copy to dense f16.
+    ggml_sycl_pool_alloc<sycl::half> Qf(ctx.pool(), (size_t) H * q * d);
+    cont_to_f16_sycl<float>((const char *) Q->data, Qf.get(), d, q, H, mb, Q->nb[1], Q->nb[2], Q->nb[3], stream);
+
+    // K/V: use pool-alloc for both F16 and dequant paths.
+    sycl::half * K_ptr = nullptr;
+    sycl::half * V_ptr = nullptr;
+    std::optional<ggml_sycl_pool_alloc<sycl::half>> Kf_pool;
+    std::optional<ggml_sycl_pool_alloc<sycl::half>> Vf_pool;
+
+    if (K->type == GGML_TYPE_F16 && V->type == GGML_TYPE_F16) {
+        Kf_pool.emplace(ctx.pool(), (size_t) Hkv * seq * d);
+        Vf_pool.emplace(ctx.pool(), (size_t) Hkv * seq * d);
+        cont_to_f16_sycl<sycl::half>((const char *) K->data, Kf_pool->get(), d, seq, Hkv, mb, K->nb[1], K->nb[2], K->nb[3], stream);
+        cont_to_f16_sycl<sycl::half>((const char *) V->data, Vf_pool->get(), d, seq, Hkv, mb, V->nb[1], V->nb[2], V->nb[3], stream);
+        K_ptr = Kf_pool->get();
+        V_ptr = Vf_pool->get();
+    } else if (ggml_is_quantized(K->type)) {
+        // Quantized K/V: dequant to dense F16 using pool, same lifetime as F16 path.
+        Kf_pool.emplace(ctx.pool(), ggml_nelements(K));
+        K_ptr = Kf_pool->get();
+        {
+            const char * K_data = (const char *)K->data;
+            const bool k_non_dense = ((int64_t)K->ne[1] * K->nb[1] != K->nb[2]) && K->ne[2] > 1;
+            const bool k_gemma = k_non_dense &&
+                ((int64_t)K->nb[2] < (int64_t)K->ne[1] * (int64_t)K->nb[1]);
+            if (ggml_is_contiguously_allocated(K) && !k_non_dense) {
+                to_fp16_sycl_t to_fp16 = ggml_get_to_fp16_sycl(K->type, dst);
+                to_fp16(K_data, K_ptr, ggml_nelements(K), stream);
+            } else {
+                const size_t bs = ggml_blck_size(K->type);
+                const size_t ts = ggml_type_size(K->type);
+                to_fp16_nc_sycl_t to_fp16 = ggml_get_to_fp16_nc_sycl(K->type);
+                int64_t s01, s02, s03;
+                if (k_gemma) {
+                    const int64_t blk_per_row = (int64_t)K->ne[0] / bs;
+                    s01 = (int64_t)Hkv * blk_per_row;
+                    s02 = blk_per_row;
+                    s03 = (int64_t)K->ne[1] * s01;
+                } else {
+                    s01 = (int64_t)K->nb[1] / ts;
+                    s02 = (int64_t)K->nb[2] / ts;
+                    s03 = (int64_t)K->nb[3] / ts;
+                }
+                to_fp16(K_data, K_ptr,
+                        K->ne[0], K->ne[1], K->ne[2], K->ne[3],
+                        s01, s02, s03, stream);
+            }
+        }
+        // Quantized V: always dequant separately. Even when K and V share
+        // the same underlying allocation (V is a view of K with the same
+        // data pointer), their logical values differ because the quantized
+        // elements at different positions/offsets represent different K/V
+        // data. Master's F16 path also never aliases K and V.
+        Vf_pool.emplace(ctx.pool(), ggml_nelements(V));
+        V_ptr = Vf_pool->get();
+        {
+            const char * V_data = (const char *)V->data;
+            const bool v_non_dense = ((int64_t)V->ne[1] * V->nb[1] != V->nb[2]) && V->ne[2] > 1;
+            const bool v_gemma = v_non_dense &&
+                ((int64_t)V->nb[2] < (int64_t)V->ne[1] * (int64_t)V->nb[1]);
+            if (ggml_is_contiguously_allocated(V) && !v_non_dense) {
+                to_fp16_sycl_t to_fp16 = ggml_get_to_fp16_sycl(V->type, dst);
+                to_fp16(V_data, V_ptr, ggml_nelements(V), stream);
+            } else {
+                const size_t bs = ggml_blck_size(V->type);
+                const size_t ts = ggml_type_size(V->type);
+                to_fp16_nc_sycl_t to_fp16 = ggml_get_to_fp16_nc_sycl(V->type);
+                int64_t s01, s02, s03;
+                if (v_gemma) {
+                    const int64_t blk_per_row = (int64_t)V->ne[0] / bs;
+                    s01 = (int64_t)V->ne[2] * blk_per_row;
+                    s02 = blk_per_row;
+                    s03 = (int64_t)V->ne[1] * s01;
+                } else {
+                    s01 = (int64_t)V->nb[1] / ts;
+                    s02 = (int64_t)V->nb[2] / ts;
+                    s03 = (int64_t)V->nb[3] / ts;
+                }
+                to_fp16(V_data, V_ptr,
+                        V->ne[0], V->ne[1], V->ne[2], V->ne[3],
+                        s01, s02, s03, stream);
+            }
+        }
+    } else {
+        // F32: strided copy to dense F16 via cont_to_f16_sycl<float>.
+        Kf_pool.emplace(ctx.pool(), ggml_nelements(K));
+        K_ptr = Kf_pool->get();
+        cont_to_f16_sycl<float>((const char *) K->data, K_ptr, K->ne[0], K->ne[1], K->ne[2], K->ne[3],
+                                K->nb[1], K->nb[2], K->nb[3], stream);
+        Vf_pool.emplace(ctx.pool(), ggml_nelements(V));
+        V_ptr = Vf_pool->get();
+        cont_to_f16_sycl<float>((const char *) V->data, V_ptr, V->ne[0], V->ne[1], V->ne[2], V->ne[3],
+                                V->nb[1], V->nb[2], V->nb[3], stream);
+    }
 
     // divide-by-(1/scale) reproduces ggml's score *= kq_scale on the proven probe graph.
     //
@@ -244,8 +354,8 @@ void ggml_sycl_flash_attn_ext_onednn(ggml_backend_sycl_context & ctx, ggml_tenso
 
     auto id2ptr = [&](size_t r) -> void * {
         if (r == E.id_q)     return Qf.get();
-        if (r == E.id_k)     return Kf.get();
-        if (r == E.id_v)     return Vf.get();
+        if (r == E.id_k)     return K_ptr;
+        if (r == E.id_v)     return V_ptr;
         if (r == E.id_scale) return scale_dev;
         if (r == E.id_mask)  return (void *) mask->data;
         return nullptr;

ggml/src/ggml-sycl/fattn.cpp

@@ -97,7 +97,7 @@ static void ggml_sycl_flash_attn_ext_vec(ggml_backend_sycl_context & ctx, ggml_t
 enum best_fattn_kernel {
     BEST_FATTN_KERNEL_NONE     =   0,
     BEST_FATTN_KERNEL_VEC      = 100,
-    BEST_FATTN_KERNEL_ONEDNN   = 150, // added enum for onednn==150
+    BEST_FATTN_KERNEL_ONEDNN   = 150, // oneDNN SDPA: native F16 (PR #25222)
     BEST_FATTN_KERNEL_TILE     = 200,
     BEST_FATTN_KERNEL_MKL      = 300,
 };
@@ -130,6 +130,14 @@ static best_fattn_kernel ggml_sycl_get_best_fattn_kernel(const int device, const
 
     bool gqa_opt_applies = gqa_ratio >= 2 && mask && max_bias == 0.0f && K->ne[1] % FATTN_KQ_STRIDE == 0;
 
+    // XMX-accelerated path: oneDNN SDPA (native F16 and dequant+non-F16).
+    // ONEDNN requires min 32 query tokens — short-circuit decode to avoid
+    // calling _supported() on every decode FA call.
+    if (Q->ne[1] >= 32
+        && ggml_sycl_flash_attn_ext_onednn_supported(dst)) {
+        return BEST_FATTN_KERNEL_ONEDNN;
+    }
+
     // MKL path: XMX-accelerated GEMM for prompt processing (all KV cache types).
     // The MKL kernel converts non-F16 K/V to F16 via to_fp16_sycl before GEMM,
     // so quantized, F16, BF16, and F32 caches all benefit from XMX acceleration.
@@ -167,7 +175,6 @@ static best_fattn_kernel ggml_sycl_get_best_fattn_kernel(const int device, const
             return BEST_FATTN_KERNEL_MKL;
         }
     }
-
     for (const ggml_tensor * t : {Q, K, V, mask}) {
         if (t == nullptr || ggml_is_quantized(t->type)) {
             continue;
@@ -215,6 +222,7 @@ static best_fattn_kernel ggml_sycl_get_best_fattn_kernel(const int device, const
     switch (K->type) {
         case GGML_TYPE_F32:
         case GGML_TYPE_F16:
+        case GGML_TYPE_BF16:
             break;
         case GGML_TYPE_Q4_1:
         case GGML_TYPE_Q5_0:
@@ -233,8 +241,11 @@ static best_fattn_kernel ggml_sycl_get_best_fattn_kernel(const int device, const
         return BEST_FATTN_KERNEL_NONE;
     }
 
-    // For small batch sizes the vector kernel may be preferable over the kernels optimized for large batch sizes:
-    const bool can_use_vector_kernel = Q->ne[0] <= 512 && Q->ne[0] % 64 == 0 && K->ne[1] % FATTN_KQ_STRIDE == 0;
+    // For small batch sizes the vector kernel may be preferable over the kernels optimized for large batch sizes.
+    // BF16 is excluded: the VEC kernel has no BF16 template (it needs GGML_SYCL_FA_ALL_QUANTS for non-F16/Q4_0/Q8_0).
+    const bool has_bf16 = (K->type == GGML_TYPE_BF16 || V->type == GGML_TYPE_BF16);
+    const bool can_use_vector_kernel = Q->ne[0] <= 512 && Q->ne[0] % 64 == 0 && K->ne[1] % FATTN_KQ_STRIDE == 0
+        && !has_bf16;
 
     // Fused-XMX path: oneDNN Graph SDPA (flash attention). Strictly
     // additive -- taken only when statically supported, otherwise falls through to VEC/TILE below.
@@ -276,6 +287,7 @@ void ggml_sycl_flash_attn_ext(ggml_backend_sycl_context & ctx, ggml_tensor * dst
         const char * kname = "TILE";
         best_fattn_kernel k = ggml_sycl_get_best_fattn_kernel(ctx.device, dst);
         if (k == BEST_FATTN_KERNEL_MKL)  kname = "MKL";
+        if (k == BEST_FATTN_KERNEL_ONEDNN)  kname = "ONEDNN";
         if (k == BEST_FATTN_KERNEL_VEC)  kname = "VEC";
         int64_t delta = 0;
         if (Dk == 256) {
@@ -292,7 +304,8 @@ void ggml_sycl_flash_attn_ext(ggml_backend_sycl_context & ctx, ggml_tensor * dst
                 (long long)V_dbg->ne[1]);
     }
 
-    switch (ggml_sycl_get_best_fattn_kernel(ggml_sycl_get_device(), dst)) {
+    const best_fattn_kernel fk = ggml_sycl_get_best_fattn_kernel(ggml_sycl_get_device(), dst);
+    switch (fk) {
         case BEST_FATTN_KERNEL_NONE:
             GGML_ABORT("Not support Flash-Attention");
         case BEST_FATTN_KERNEL_ONEDNN:
@@ -331,6 +344,7 @@ void ggml_sycl_flash_attn_ext(ggml_backend_sycl_context & ctx, ggml_tensor * dst
             q->wait();
             const char * kname = "???";
             best_fattn_kernel kb = ggml_sycl_get_best_fattn_kernel(ctx.device, dst);
+            if (kb == BEST_FATTN_KERNEL_ONEDNN) kname = "ONEDNN";
             if (kb == BEST_FATTN_KERNEL_MKL) kname = "MKL";
             if (kb == BEST_FATTN_KERNEL_TILE) kname = "TILE";
             if (kb == BEST_FATTN_KERNEL_VEC) kname = "VEC";
@@ -354,6 +368,7 @@ void ggml_sycl_flash_attn_ext(ggml_backend_sycl_context & ctx, ggml_tensor * dst
             }
         }
     }
+
 }
 
 bool ggml_sycl_flash_attn_ext_supported(int device, const ggml_tensor * dst) {

ggml/src/ggml-vulkan/ggml-vulkan.cpp

@@ -1026,6 +1026,7 @@ struct vk_device_struct {
     vk_pipeline pipeline_pool2d_f32;
     vk_pipeline pipeline_rwkv_wkv6_f32;
     vk_pipeline pipeline_rwkv_wkv7_f32;
+    vk_pipeline pipeline_gated_linear_attn_f32;
     // [size_idx][kda] where size_idx: 0=d16, 1=d32, 2=d64, 3=d128
     vk_pipeline pipeline_gated_delta_net[4][2];
     vk_pipeline pipeline_ssm_scan_f32_d128;
@@ -1747,6 +1748,13 @@ struct vk_op_rwkv_wkv7_push_constants {
     uint32_t C;
     uint32_t H;
 };
+struct vk_op_gated_linear_attn_push_constants {
+    uint32_t B;
+    uint32_t T;
+    uint32_t C;
+    uint32_t H;
+    float scale;
+};
 struct vk_op_gated_delta_net_push_constants {
     uint32_t H;
     uint32_t n_tokens;
@@ -5665,6 +5673,8 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {
 
     ggml_vk_create_pipeline(device, device->pipeline_rwkv_wkv7_f32, "rwkv_wkv7_f32", rwkv_wkv7_f32_len, rwkv_wkv7_f32_data, "main", 8, sizeof(vk_op_rwkv_wkv7_push_constants), {1, 1, 1}, {device->subgroup_size}, 1);
 
+    ggml_vk_create_pipeline(device, device->pipeline_gated_linear_attn_f32, "gated_linear_attn_f32", gated_linear_attn_f32_len, gated_linear_attn_f32_data, "main", 6, sizeof(vk_op_gated_linear_attn_push_constants), {1, 1, 1}, {}, 1);
+
     {
         const uint32_t gdn_sizes[] = {16, 32, 64, 128};
         const char * gdn_names[][2] = {
@@ -11392,6 +11402,11 @@ static vk_pipeline ggml_vk_op_get_pipeline(ggml_backend_vk_context * ctx, const
             return ctx->device->pipeline_rwkv_wkv7_f32;
         }
         return nullptr;
+    case GGML_OP_GATED_LINEAR_ATTN:
+        if (src0->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32) {
+            return ctx->device->pipeline_gated_linear_attn_f32;
+        }
+        return nullptr;
     case GGML_OP_GATED_DELTA_NET:
         if (src0->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32) {
             const uint32_t S_v = dst->src[2]->ne[0];
@@ -12422,6 +12437,41 @@ static void ggml_vk_rwkv_wkv7(ggml_backend_vk_context * ctx, vk_context& subctx,
     );
 }
 
+static void ggml_vk_gated_linear_attn(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst) {
+    const size_t seq_length = dst->src[0]->ne[2];
+    const size_t n_embed    = dst->ne[0];
+    const size_t n_heads    = dst->src[0]->ne[1];
+    const size_t n_seqs     = dst->src[4]->ne[1];
+
+    float scale;
+    memcpy(&scale, dst->op_params, sizeof(float));
+
+    GGML_ASSERT(dst->buffer != nullptr);
+
+    vk_pipeline pipeline = ggml_vk_op_get_pipeline(ctx, dst->src[0], dst->src[1], dst->src[2], dst, dst->op);
+    GGML_ASSERT(pipeline != nullptr);
+
+    ggml_pipeline_request_descriptor_sets(ctx, pipeline, 1);
+
+    vk_subbuffer dst_buf = ggml_vk_tensor_subbuffer(ctx, dst);
+    vk_subbuffer src_buf[5] = {};
+    for (int i = 0; i < 5; i++) {
+        src_buf[i] = ggml_vk_tensor_subbuffer(ctx, dst->src[i]);
+    }
+
+    const vk_op_gated_linear_attn_push_constants pc = {
+        (uint32_t)n_seqs,
+        (uint32_t)seq_length,
+        (uint32_t)n_embed,
+        (uint32_t)n_heads,
+        scale,
+    };
+
+    ggml_vk_dispatch_pipeline(ctx, subctx, pipeline,
+        {src_buf[0], src_buf[1], src_buf[2], src_buf[3], src_buf[4], dst_buf},
+        pc, { (uint32_t)(n_seqs * n_heads), 1, 1 });
+}
+
 static void ggml_vk_gated_delta_net(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst) {
     const ggml_tensor * src_q     = dst->src[0];
     const ggml_tensor * src_v     = dst->src[2];
@@ -15421,6 +15471,11 @@ static bool ggml_vk_build_graph(ggml_backend_vk_context * ctx, ggml_cgraph * cgr
 
         break;
 
+    case GGML_OP_GATED_LINEAR_ATTN:
+        ggml_vk_gated_linear_attn(ctx, compute_ctx, node);
+
+        break;
+
     case GGML_OP_GATED_DELTA_NET:
         ggml_vk_gated_delta_net(ctx, compute_ctx, node);
 
@@ -18128,6 +18183,9 @@ static bool ggml_backend_vk_device_supports_op(ggml_backend_dev_t dev, const ggm
         case GGML_OP_RWKV_WKV6:
         case GGML_OP_RWKV_WKV7:
             return true; // all inputs are contiguous, see ggml.c
+        case GGML_OP_GATED_LINEAR_ATTN:
+            // the shader block size is hardcoded to head_size 64
+            return op->src[0]->type == GGML_TYPE_F32 && op->type == GGML_TYPE_F32 && op->src[0]->ne[0] == 64;
         case GGML_OP_GATED_DELTA_NET:
             {
                 const uint32_t S_v = op->src[2]->ne[0];
@@ -19117,6 +19175,10 @@ static void ggml_vk_check_results_0(ggml_backend_vk_context * ctx, ggml_cgraph *
         } else if (tensor->op == GGML_OP_RWKV_WKV7) {
             tensor_clone = ggml_rwkv_wkv7(ggml_ctx, src_clone[0], src_clone[1], src_clone[2], src_clone[3],
             src_clone[4], src_clone[5], src_clone[6]);
+        } else if (tensor->op == GGML_OP_GATED_LINEAR_ATTN) {
+            const float * op_params = (const float *)tensor->op_params;
+            tensor_clone = ggml_gated_linear_attn(ggml_ctx, src_clone[0], src_clone[1],
+            src_clone[2], src_clone[3], src_clone[4], op_params[0]);
         } else if (tensor->op == GGML_OP_GATED_DELTA_NET) {
             tensor_clone = ggml_gated_delta_net(ggml_ctx, src_clone[0], src_clone[1],
             src_clone[2], src_clone[3], src_clone[4], src_clone[5],

ggml/src/ggml-vulkan/vulkan-shaders/gla.comp

@@ -0,0 +1,82 @@
+#version 450
+
+#extension GL_EXT_control_flow_attributes : require
+
+#define BLOCK_SIZE 64
+layout(local_size_x = BLOCK_SIZE, local_size_y = 1, local_size_z = 1) in;
+
+layout(push_constant) uniform Parameters {
+    uint B;
+    uint T;
+    uint C;
+    uint H;
+    float scale;
+};
+
+layout(binding = 0) readonly buffer KBuf { A_TYPE k[]; };
+layout(binding = 1) readonly buffer VBuf { A_TYPE v[]; };
+layout(binding = 2) readonly buffer QBuf { A_TYPE q[]; };
+layout(binding = 3) readonly buffer GBuf { A_TYPE g[]; };
+layout(binding = 4) readonly buffer StateBuf { A_TYPE state_in[]; };
+layout(binding = 5) buffer DstBuf { A_TYPE dst[]; };
+
+shared A_TYPE _k[BLOCK_SIZE], _q[BLOCK_SIZE], _g[BLOCK_SIZE];
+
+void main() {
+    const uint head_size = BLOCK_SIZE;
+    const uint batch_id = gl_WorkGroupID.x / H;
+    const uint head_id = gl_WorkGroupID.x % H;
+    const uint tid = gl_LocalInvocationID.x;
+
+    const uint state_size = C * head_size;
+    const uint n_seq_tokens = T / B;
+
+    if (batch_id >= B || head_id >= H) {
+        return;
+    }
+
+    // state[i] holds column tid of this head's state matrix: S[i][tid]
+    A_TYPE state[BLOCK_SIZE];
+    [[unroll]] for (uint i = 0; i < head_size; i++) {
+        state[i] = state_in[batch_id * state_size + head_id * head_size * head_size
+                          + i * head_size + tid];
+    }
+
+    const uint start_t = batch_id * n_seq_tokens * C + head_id * head_size + tid;
+    const uint end_t = (batch_id + 1) * n_seq_tokens * C + head_id * head_size + tid;
+
+    for (uint t = start_t; t < end_t; t += C) {
+        barrier();
+        _k[tid] = k[t];
+        _q[tid] = q[t];
+        _g[tid] = g[t];
+        barrier();
+
+        const A_TYPE v_val = v[t];
+        A_TYPE y = 0.0;
+
+        [[unroll]] for (uint i = 0; i < head_size; i += 4) {
+            vec4 k_vec = vec4(_k[i], _k[i+1], _k[i+2], _k[i+3]);
+            vec4 q_vec = vec4(_q[i], _q[i+1], _q[i+2], _q[i+3]);
+            vec4 g_vec = vec4(_g[i], _g[i+1], _g[i+2], _g[i+3]);
+            vec4 s_vec = vec4(state[i], state[i+1], state[i+2], state[i+3]);
+
+            vec4 kv = k_vec * v_val;
+
+            s_vec = s_vec * g_vec + kv;
+            y += dot(q_vec, s_vec);
+
+            state[i]   = s_vec.x;
+            state[i+1] = s_vec.y;
+            state[i+2] = s_vec.z;
+            state[i+3] = s_vec.w;
+        }
+
+        dst[t] = y * scale;
+    }
+
+    [[unroll]] for (uint i = 0; i < head_size; i++) {
+        dst[T * C + batch_id * state_size + head_id * head_size * head_size
+            + i * head_size + tid] = state[i];
+    }
+}

ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp

@@ -1057,6 +1057,8 @@ void process_shaders() {
 
     string_to_spv("rwkv_wkv6_f32", "wkv6.comp", merge_maps(base_dict, {{"A_TYPE", "float"}}));
 
+    string_to_spv("gated_linear_attn_f32", "gla.comp", merge_maps(base_dict, {{"A_TYPE", "float"}}));
+
     string_to_spv("rwkv_wkv7_f32", "wkv7.comp", merge_maps(base_dict, {{"A_TYPE", "float"}}));
 
     string_to_spv("gated_delta_net_f32", "gated_delta_net.comp", merge_maps(base_dict, {{"FLOAT_TYPE", "float"}, {"USE_SUBGROUP_ADD", "1"}, {"USE_SUBGROUP_CLUSTERED", "1"}}));

gguf-py/gguf/constants.py

@@ -11,6 +11,7 @@ GGUF_MAGIC             = 0x46554747  # "GGUF"
 GGUF_VERSION           = 3
 GGUF_DEFAULT_ALIGNMENT = 32
 GGML_QUANT_VERSION     = 2  # GGML_QNT_VERSION from ggml.h
+GGML_MAX_DIMS          = 4  # GGML_MAX_DIMS from ggml.h
 
 #
 # metadata keys
@@ -322,6 +323,7 @@ class Keys:
         PROJECTOR_TYPE        = "clip.projector_type"
         HAS_VISION_ENCODER    = "clip.has_vision_encoder"
         HAS_AUDIO_ENCODER     = "clip.has_audio_encoder"
+        HAS_GEN_AUDIO_ENCODER = "clip.has_gen_audio_encoder"
         HAS_LLAVA_PROJECTOR   = "clip.has_llava_projector"
 
     class ClipVision:
@@ -396,6 +398,18 @@ class Keys:
             DOWNSAMPLE_RATE = "clip.audio.projector.downsample_rate"
             HEAD_COUNT      = "clip.audio.projector.head_count"
 
+    class ClipGenAudio:
+        PROJECTOR_TYPE      = "clip.gen.audio.projector_type" # for mixed modality models
+        EMBEDDING_LENGTH    = "clip.gen.audio.embedding_length"
+        FEED_FORWARD_LENGTH = "clip.gen.audio.feed_forward_length"
+        BLOCK_COUNT         = "clip.gen.audio.block_count"
+        PROJECTION_DIM      = "clip.gen.audio.projection_dim"
+
+        class Attention:
+            HEAD_COUNT      = "clip.gen.audio.attention.head_count"
+            HEAD_COUNT_KV   = "clip.gen.audio.attention.head_count_kv"
+            LAYERNORM_EPS   = "clip.gen.audio.attention.layer_norm_epsilon"
+
     class Diffusion:
         SHIFT_LOGITS        = "diffusion.shift_logits"
 
@@ -557,6 +571,7 @@ class MODEL_ARCH(IntEnum):
     TALKIE           = auto()
     MELLUM           = auto()
     NANBEIGE         = auto()
+    QWEN3TTS         = auto()
 
 
 class VISION_PROJECTOR_TYPE(IntEnum):
@@ -957,6 +972,65 @@ class MODEL_TENSOR(IntEnum):
     A_ENC_DOWNSAMPLE_CONV = auto() # mimo-audio-tokenizer: post-transformer downsample conv
     A_ENC_DOWNSAMPLE_NORM = auto() # mimo-audio-tokenizer: post-transformer downsample norm
     A_ENC_RVQ_CODEBOOK    = auto() # mimo-audio-tokenizer: residual vector quantizer codebook, per quantizer index
+    A_ENC_CONV_RES2       = auto() # qwen3tts
+    A_ENC_SE_CONV1        = auto() # qwen3tts
+    A_ENC_SE_CONV2        = auto() # qwen3tts
+    A_ENC_ASP_ATTN        = auto() # qwen3tts
+    A_ENC_ASP_TDNN        = auto() # qwen3tts
+    # qwen3tts code_predictor: predicts the remaining RVQ codebooks
+    A_GEN_CODE_PROJ_IN     = auto() # small_to_mtp_projection
+    A_GEN_CODE_EMBD        = auto() # per-codebook embedding table, merged 3D [n_codebooks, vocab, dim]
+    A_GEN_CODE_HEAD        = auto() # per-codebook output head, merged 3D [n_codebooks, vocab, dim]
+    A_GEN_CODE_OUT_EMBD    = auto() # codebook-0 embedding, re-fed into the talker backbone (talker.model.codec_embedding)
+    A_GEN_CODE_ATTN_NORM   = auto()
+    A_GEN_CODE_ATTN_Q      = auto()
+    A_GEN_CODE_ATTN_Q_NORM = auto()
+    A_GEN_CODE_ATTN_K      = auto()
+    A_GEN_CODE_ATTN_K_NORM = auto()
+    A_GEN_CODE_ATTN_V      = auto()
+    A_GEN_CODE_ATTN_OUT    = auto()
+    A_GEN_CODE_FFN_NORM    = auto()
+    A_GEN_CODE_FFN_GATE    = auto()
+    A_GEN_CODE_FFN_UP      = auto()
+    A_GEN_CODE_FFN_DOWN    = auto()
+    A_GEN_CODE_OUTPUT_NORM = auto()
+    # qwen3tts code2wav: RVQ codes -> raw PCM
+    A_GEN_WAV_QUANT_FIRST_IN       = auto() # semantic RVQ, in_proj (1x1 conv, loaded as 2D)
+    A_GEN_WAV_QUANT_FIRST_OUT      = auto() # semantic RVQ, out_proj
+    A_GEN_WAV_QUANT_FIRST_CB = auto() # semantic RVQ codebook (1 layer), folded from embedding_sum/cluster_usage
+    A_GEN_WAV_QUANT_REST_IN        = auto() # acoustic RVQ, in_proj
+    A_GEN_WAV_QUANT_REST_OUT       = auto() # acoustic RVQ, out_proj
+    A_GEN_WAV_QUANT_REST_CB  = auto() # acoustic RVQ codebooks, merged 3D [15, vocab, dim]
+    A_GEN_WAV_PRE_CONV             = auto()
+    A_GEN_WAV_TFM_IN_PROJ          = auto()
+    A_GEN_WAV_TFM_OUT_PROJ         = auto()
+    A_GEN_WAV_TFM_OUTPUT_NORM      = auto()
+    A_GEN_WAV_TFM_ATTN_NORM        = auto()
+    A_GEN_WAV_TFM_ATTN_Q           = auto()
+    A_GEN_WAV_TFM_ATTN_K           = auto()
+    A_GEN_WAV_TFM_ATTN_V           = auto()
+    A_GEN_WAV_TFM_ATTN_OUT         = auto()
+    A_GEN_WAV_TFM_ATTN_SCALE       = auto() # layer scale (gamma) on the attn output
+    A_GEN_WAV_TFM_FFN_NORM         = auto()
+    A_GEN_WAV_TFM_FFN_GATE         = auto()
+    A_GEN_WAV_TFM_FFN_UP           = auto()
+    A_GEN_WAV_TFM_FFN_DOWN         = auto()
+    A_GEN_WAV_TFM_FFN_SCALE        = auto() # layer scale (gamma) on the FFN output
+    A_GEN_WAV_UP_CONV              = auto() # causal ConvTranspose1d, 2x upsample
+    A_GEN_WAV_UP_DWCONV            = auto() # ConvNeXt depthwise conv
+    A_GEN_WAV_UP_NORM              = auto() # ConvNeXt LayerNorm
+    A_GEN_WAV_UP_PW1               = auto() # ConvNeXt pointwise conv 1 (expand)
+    A_GEN_WAV_UP_PW2               = auto() # ConvNeXt pointwise conv 2 (project)
+    A_GEN_WAV_UP_GAMMA             = auto() # ConvNeXt layer scale
+    A_GEN_WAV_DAC_ENTRY            = auto() # DAC conv_pre
+    A_GEN_WAV_DAC_UP_SNAKE         = auto() # DAC per-block SnakeBeta before the upsample conv
+    A_GEN_WAV_DAC_UP_CONV          = auto() # DAC per-block causal ConvTranspose1d
+    A_GEN_WAV_DAC_RES_ACT1         = auto() # DAC residual unit, SnakeBeta before conv1
+    A_GEN_WAV_DAC_RES_CONV1        = auto() # DAC residual unit, dilated causal conv
+    A_GEN_WAV_DAC_RES_ACT2         = auto() # DAC residual unit, SnakeBeta before conv2
+    A_GEN_WAV_DAC_RES_CONV2        = auto() # DAC residual unit, pointwise causal conv
+    A_GEN_WAV_DAC_POST_SNAKE       = auto() # DAC final SnakeBeta
+    A_GEN_WAV_DAC_POST_CONV        = auto() # DAC conv_post -> 1-channel PCM
     A_MMPROJ              = auto()
     A_MMPROJ_FC           = auto()
     A_MM_NORM_PRE         = auto()
@@ -1169,6 +1243,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
     MODEL_ARCH.TALKIE:           "talkie",
     MODEL_ARCH.MELLUM:           "mellum",
     MODEL_ARCH.NANBEIGE:         "nanbeige",
+    MODEL_ARCH.QWEN3TTS:         "qwen3tts",
 }
 
 VISION_PROJECTOR_TYPE_NAMES: dict[VISION_PROJECTOR_TYPE, str] = {
@@ -1566,6 +1641,63 @@ TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
     MODEL_TENSOR.A_ENC_DOWNSAMPLE_CONV:     "a.downsample.conv",
     MODEL_TENSOR.A_ENC_DOWNSAMPLE_NORM:     "a.downsample.norm",
     MODEL_TENSOR.A_ENC_RVQ_CODEBOOK:        "a.rvq.codebook",
+    MODEL_TENSOR.A_ENC_CONV_RES2:           "a.blk.{bid}.res2.{xid}",
+    MODEL_TENSOR.A_ENC_SE_CONV1:            "a.blk.{bid}.se_conv1",
+    MODEL_TENSOR.A_ENC_SE_CONV2:            "a.blk.{bid}.se_conv2",
+    MODEL_TENSOR.A_ENC_ASP_ATTN:            "a.asp_attn",
+    MODEL_TENSOR.A_ENC_ASP_TDNN:            "a.asp_tdnn",
+    MODEL_TENSOR.A_GEN_CODE_PROJ_IN:        "a.gen.code.proj_in",
+    MODEL_TENSOR.A_GEN_CODE_EMBD:           "a.gen.code.embd",
+    MODEL_TENSOR.A_GEN_CODE_HEAD:           "a.gen.code.head",
+    MODEL_TENSOR.A_GEN_CODE_OUT_EMBD:       "a.gen.code.out_embd",
+    MODEL_TENSOR.A_GEN_CODE_ATTN_NORM:      "a.gen.code.blk.{bid}.ln1", # reuses the generic clip.cpp block loader (TN_LN_1)
+    MODEL_TENSOR.A_GEN_CODE_ATTN_Q:         "a.gen.code.blk.{bid}.attn_q",
+    MODEL_TENSOR.A_GEN_CODE_ATTN_Q_NORM:    "a.gen.code.blk.{bid}.attn_q_norm",
+    MODEL_TENSOR.A_GEN_CODE_ATTN_K:         "a.gen.code.blk.{bid}.attn_k",
+    MODEL_TENSOR.A_GEN_CODE_ATTN_K_NORM:    "a.gen.code.blk.{bid}.attn_k_norm",
+    MODEL_TENSOR.A_GEN_CODE_ATTN_V:         "a.gen.code.blk.{bid}.attn_v",
+    MODEL_TENSOR.A_GEN_CODE_ATTN_OUT:       "a.gen.code.blk.{bid}.attn_out",
+    MODEL_TENSOR.A_GEN_CODE_FFN_NORM:       "a.gen.code.blk.{bid}.ln2", # reuses the generic clip.cpp block loader (TN_LN_2)
+    MODEL_TENSOR.A_GEN_CODE_FFN_GATE:       "a.gen.code.blk.{bid}.ffn_gate",
+    MODEL_TENSOR.A_GEN_CODE_FFN_UP:         "a.gen.code.blk.{bid}.ffn_up",
+    MODEL_TENSOR.A_GEN_CODE_FFN_DOWN:       "a.gen.code.blk.{bid}.ffn_down",
+    MODEL_TENSOR.A_GEN_CODE_OUTPUT_NORM:    "a.gen.code.output_norm",
+    MODEL_TENSOR.A_GEN_WAV_QUANT_FIRST_IN:  "a.gen.wav.quant.first.in_proj",
+    MODEL_TENSOR.A_GEN_WAV_QUANT_FIRST_OUT: "a.gen.wav.quant.first.out_proj",
+    MODEL_TENSOR.A_GEN_WAV_QUANT_FIRST_CB:  "a.gen.wav.quant.first.codebook",
+    MODEL_TENSOR.A_GEN_WAV_QUANT_REST_IN:   "a.gen.wav.quant.rest.in_proj",
+    MODEL_TENSOR.A_GEN_WAV_QUANT_REST_OUT:  "a.gen.wav.quant.rest.out_proj",
+    MODEL_TENSOR.A_GEN_WAV_QUANT_REST_CB:   "a.gen.wav.quant.rest.codebook",
+    MODEL_TENSOR.A_GEN_WAV_PRE_CONV:        "a.gen.wav.pre_conv",
+    MODEL_TENSOR.A_GEN_WAV_TFM_IN_PROJ:     "a.gen.wav.tfm.in_proj",
+    MODEL_TENSOR.A_GEN_WAV_TFM_OUT_PROJ:    "a.gen.wav.tfm.out_proj",
+    MODEL_TENSOR.A_GEN_WAV_TFM_OUTPUT_NORM: "a.gen.wav.tfm.output_norm",
+    MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_NORM:   "a.gen.wav.tfm.blk.{bid}.ln1",
+    MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_Q:      "a.gen.wav.tfm.blk.{bid}.attn_q",
+    MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_K:      "a.gen.wav.tfm.blk.{bid}.attn_k",
+    MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_V:      "a.gen.wav.tfm.blk.{bid}.attn_v",
+    MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_OUT:    "a.gen.wav.tfm.blk.{bid}.attn_out",
+    MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_SCALE:  "a.gen.wav.tfm.blk.{bid}.ls1",
+    MODEL_TENSOR.A_GEN_WAV_TFM_FFN_NORM:    "a.gen.wav.tfm.blk.{bid}.ln2",
+    MODEL_TENSOR.A_GEN_WAV_TFM_FFN_GATE:    "a.gen.wav.tfm.blk.{bid}.ffn_gate",
+    MODEL_TENSOR.A_GEN_WAV_TFM_FFN_UP:      "a.gen.wav.tfm.blk.{bid}.ffn_up",
+    MODEL_TENSOR.A_GEN_WAV_TFM_FFN_DOWN:    "a.gen.wav.tfm.blk.{bid}.ffn_down",
+    MODEL_TENSOR.A_GEN_WAV_TFM_FFN_SCALE:   "a.gen.wav.tfm.blk.{bid}.ls2",
+    MODEL_TENSOR.A_GEN_WAV_UP_CONV:         "a.gen.wav.up.blk.{bid}.conv",
+    MODEL_TENSOR.A_GEN_WAV_UP_DWCONV:       "a.gen.wav.up.blk.{bid}.dwconv",
+    MODEL_TENSOR.A_GEN_WAV_UP_NORM:         "a.gen.wav.up.blk.{bid}.norm",
+    MODEL_TENSOR.A_GEN_WAV_UP_PW1:          "a.gen.wav.up.blk.{bid}.pw1",
+    MODEL_TENSOR.A_GEN_WAV_UP_PW2:          "a.gen.wav.up.blk.{bid}.pw2",
+    MODEL_TENSOR.A_GEN_WAV_UP_GAMMA:        "a.gen.wav.up.blk.{bid}.gamma",
+    MODEL_TENSOR.A_GEN_WAV_DAC_ENTRY:       "a.gen.wav.dac.entry",
+    MODEL_TENSOR.A_GEN_WAV_DAC_UP_SNAKE:    "a.gen.wav.dac.blk.{bid}.snake",
+    MODEL_TENSOR.A_GEN_WAV_DAC_UP_CONV:     "a.gen.wav.dac.blk.{bid}.conv",
+    MODEL_TENSOR.A_GEN_WAV_DAC_RES_ACT1:    "a.gen.wav.dac.blk.{bid}.res.{xid}.act1",
+    MODEL_TENSOR.A_GEN_WAV_DAC_RES_CONV1:   "a.gen.wav.dac.blk.{bid}.res.{xid}.conv1",
+    MODEL_TENSOR.A_GEN_WAV_DAC_RES_ACT2:    "a.gen.wav.dac.blk.{bid}.res.{xid}.act2",
+    MODEL_TENSOR.A_GEN_WAV_DAC_RES_CONV2:   "a.gen.wav.dac.blk.{bid}.res.{xid}.conv2",
+    MODEL_TENSOR.A_GEN_WAV_DAC_POST_SNAKE:  "a.gen.wav.dac.post_snake",
+    MODEL_TENSOR.A_GEN_WAV_DAC_POST_CONV:   "a.gen.wav.dac.post_conv",
     MODEL_TENSOR.A_MMPROJ:                  "mm.a.mlp.{bid}",
     MODEL_TENSOR.A_MMPROJ_FC:               "mm.a.fc",
     MODEL_TENSOR.A_MM_NORM_PRE:             "mm.a.norm_pre",
@@ -1820,6 +1952,63 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
         MODEL_TENSOR.A_ENC_CONV_NORM,
         MODEL_TENSOR.A_ENC_CONV_PW1,
         MODEL_TENSOR.A_ENC_CONV_PW2,
+        MODEL_TENSOR.A_ENC_CONV_RES2,
+        MODEL_TENSOR.A_ENC_SE_CONV1,
+        MODEL_TENSOR.A_ENC_SE_CONV2,
+        MODEL_TENSOR.A_ENC_ASP_ATTN,
+        MODEL_TENSOR.A_ENC_ASP_TDNN,
+        MODEL_TENSOR.A_GEN_CODE_PROJ_IN,
+        MODEL_TENSOR.A_GEN_CODE_EMBD,
+        MODEL_TENSOR.A_GEN_CODE_HEAD,
+        MODEL_TENSOR.A_GEN_CODE_OUT_EMBD,
+        MODEL_TENSOR.A_GEN_CODE_ATTN_NORM,
+        MODEL_TENSOR.A_GEN_CODE_ATTN_Q,
+        MODEL_TENSOR.A_GEN_CODE_ATTN_Q_NORM,
+        MODEL_TENSOR.A_GEN_CODE_ATTN_K,
+        MODEL_TENSOR.A_GEN_CODE_ATTN_K_NORM,
+        MODEL_TENSOR.A_GEN_CODE_ATTN_V,
+        MODEL_TENSOR.A_GEN_CODE_ATTN_OUT,
+        MODEL_TENSOR.A_GEN_CODE_FFN_NORM,
+        MODEL_TENSOR.A_GEN_CODE_FFN_GATE,
+        MODEL_TENSOR.A_GEN_CODE_FFN_UP,
+        MODEL_TENSOR.A_GEN_CODE_FFN_DOWN,
+        MODEL_TENSOR.A_GEN_CODE_OUTPUT_NORM,
+        MODEL_TENSOR.A_GEN_WAV_QUANT_FIRST_IN,
+        MODEL_TENSOR.A_GEN_WAV_QUANT_FIRST_OUT,
+        MODEL_TENSOR.A_GEN_WAV_QUANT_FIRST_CB,
+        MODEL_TENSOR.A_GEN_WAV_QUANT_REST_IN,
+        MODEL_TENSOR.A_GEN_WAV_QUANT_REST_OUT,
+        MODEL_TENSOR.A_GEN_WAV_QUANT_REST_CB,
+        MODEL_TENSOR.A_GEN_WAV_PRE_CONV,
+        MODEL_TENSOR.A_GEN_WAV_TFM_IN_PROJ,
+        MODEL_TENSOR.A_GEN_WAV_TFM_OUT_PROJ,
+        MODEL_TENSOR.A_GEN_WAV_TFM_OUTPUT_NORM,
+        MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_NORM,
+        MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_Q,
+        MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_K,
+        MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_V,
+        MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_OUT,
+        MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_SCALE,
+        MODEL_TENSOR.A_GEN_WAV_TFM_FFN_NORM,
+        MODEL_TENSOR.A_GEN_WAV_TFM_FFN_GATE,
+        MODEL_TENSOR.A_GEN_WAV_TFM_FFN_UP,
+        MODEL_TENSOR.A_GEN_WAV_TFM_FFN_DOWN,
+        MODEL_TENSOR.A_GEN_WAV_TFM_FFN_SCALE,
+        MODEL_TENSOR.A_GEN_WAV_UP_CONV,
+        MODEL_TENSOR.A_GEN_WAV_UP_DWCONV,
+        MODEL_TENSOR.A_GEN_WAV_UP_NORM,
+        MODEL_TENSOR.A_GEN_WAV_UP_PW1,
+        MODEL_TENSOR.A_GEN_WAV_UP_PW2,
+        MODEL_TENSOR.A_GEN_WAV_UP_GAMMA,
+        MODEL_TENSOR.A_GEN_WAV_DAC_ENTRY,
+        MODEL_TENSOR.A_GEN_WAV_DAC_UP_SNAKE,
+        MODEL_TENSOR.A_GEN_WAV_DAC_UP_CONV,
+        MODEL_TENSOR.A_GEN_WAV_DAC_RES_ACT1,
+        MODEL_TENSOR.A_GEN_WAV_DAC_RES_CONV1,
+        MODEL_TENSOR.A_GEN_WAV_DAC_RES_ACT2,
+        MODEL_TENSOR.A_GEN_WAV_DAC_RES_CONV2,
+        MODEL_TENSOR.A_GEN_WAV_DAC_POST_SNAKE,
+        MODEL_TENSOR.A_GEN_WAV_DAC_POST_CONV,
         MODEL_TENSOR.A_ENC_CONV_NORM_MEAN,
         MODEL_TENSOR.A_ENC_CONV_NORM_VAR,
         MODEL_TENSOR.A_ENC_MEL_FILTERS,
@@ -3221,6 +3410,13 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
         MODEL_TENSOR.FFN_DOWN_SHEXP,
         MODEL_TENSOR.FFN_UP_SHEXP,
         MODEL_TENSOR.FFN_EXP_PROBS_B,
+        # NextN/MTP tensors
+        MODEL_TENSOR.NEXTN_EH_PROJ,
+        MODEL_TENSOR.NEXTN_EMBED_TOKENS,
+        MODEL_TENSOR.NEXTN_ENORM,
+        MODEL_TENSOR.NEXTN_HNORM,
+        MODEL_TENSOR.NEXTN_SHARED_HEAD_HEAD,
+        MODEL_TENSOR.NEXTN_SHARED_HEAD_NORM,
     ],
     MODEL_ARCH.DEEPSEEK2OCR: [
         MODEL_TENSOR.TOKEN_EMBD,
@@ -4640,6 +4836,22 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
         MODEL_TENSOR.FFN_DOWN,
         MODEL_TENSOR.FFN_UP,
     ],
+    MODEL_ARCH.QWEN3TTS: [
+        MODEL_TENSOR.TOKEN_EMBD,
+        MODEL_TENSOR.OUTPUT_NORM,
+        MODEL_TENSOR.OUTPUT,
+        MODEL_TENSOR.ATTN_NORM,
+        MODEL_TENSOR.ATTN_Q,
+        MODEL_TENSOR.ATTN_Q_NORM,
+        MODEL_TENSOR.ATTN_K,
+        MODEL_TENSOR.ATTN_K_NORM,
+        MODEL_TENSOR.ATTN_V,
+        MODEL_TENSOR.ATTN_OUT,
+        MODEL_TENSOR.FFN_NORM,
+        MODEL_TENSOR.FFN_GATE,
+        MODEL_TENSOR.FFN_DOWN,
+        MODEL_TENSOR.FFN_UP,
+    ],
 }
 
 # tensors that will not be serialized
@@ -4914,6 +5126,8 @@ class VisionProjectorType:
     GLM4V = "glm4v"
     YOUTUVL = "youtuvl"
     NEMOTRON_V2_VL = "nemotron_v2_vl"
+    QWEN3TTS_SPKENC = "qwen3tts_spkenc" # audio: ECAPA-TDNN speaker encoder
+    QWEN3TTS_GEN = "qwen3tts_gen" # audio generation: code_predictor
     HUNYUANVL      = "hunyuanvl"
     PARAKEET       = "parakeet"  # audio
     MINIMAXM3      = "minimax_m3"

gguf-py/gguf/gguf_reader.py

@@ -22,6 +22,7 @@ if __name__ == "__main__":
     sys.path.insert(0, str(Path(__file__).parent.parent))
 
 from gguf.constants import (
+    GGML_MAX_DIMS,
     GGML_QUANT_SIZES,
     GGUF_DEFAULT_ALIGNMENT,
     GGUF_MAGIC,
@@ -266,6 +267,8 @@ class GGUFReader:
         # Get Tensor Dimensions Count
         n_dims = self._get(offs, np.uint32)
         offs += int(n_dims.nbytes)
+        if n_dims[0] > GGML_MAX_DIMS:
+            raise ValueError(f'Tensor dimensions count {n_dims[0]} exceeds GGML_MAX_DIMS ({GGML_MAX_DIMS})')
 
         # Get Tensor Dimension Array
         dims = self._get(offs, np.uint64, n_dims[0])
@@ -326,7 +329,10 @@ class GGUFReader:
                 raise ValueError(f'Found duplicated tensor with name {tensor_name}')
             tensor_names.add(tensor_name)
             ggml_type = GGMLQuantizationType(raw_dtype[0])
-            n_elems = int(np.prod(dims))
+            # use Python ints: np.prod on uint64 wraps silently on overflow
+            n_elems = 1
+            for dim in dims.tolist():
+                n_elems *= int(dim)
             np_dims = tuple(reversed(dims.tolist()))
             block_size, type_size = GGML_QUANT_SIZES[ggml_type]
             n_bytes = n_elems * type_size // block_size

gguf-py/gguf/gguf_writer.py

@@ -280,6 +280,10 @@ class GGUFWriter:
 
         self.kv_data[0][key] = GGUFValue(value=val, type=vtype, sub_type=sub_type)
 
+    def remove_key(self, key: str) -> None:
+        for kv_data in self.kv_data:
+            kv_data.pop(key, None)
+
     def add_uint8(self, key: str, val: int) -> None:
         self.add_key_value(key,val, GGUFValueType.UINT8)
 
@@ -1144,7 +1148,11 @@ class GGUFWriter:
     def add_precompiled_charsmap(self, charsmap: bytes) -> None:
         self.add_array(Keys.Tokenizer.PRECOMPILED_CHARSMAP, charsmap)
 
-    def add_chat_template(self, value: str | Sequence[Mapping[str, str]]) -> None:
+    def add_chat_template(self, value: str | Sequence[Mapping[str, str]] | None) -> None:
+        if value is None:
+            self.remove_key(Keys.Tokenizer.CHAT_TEMPLATE)
+            return
+
         if not isinstance(value, str):
             template_default = None
             template_names = set()
@@ -1199,6 +1207,9 @@ class GGUFWriter:
     def add_clip_has_audio_encoder(self, value: bool) -> None:
         self.add_bool(Keys.Clip.HAS_AUDIO_ENCODER, value)
 
+    def add_clip_has_gen_audio_encoder(self, value: bool) -> None:
+        self.add_bool(Keys.Clip.HAS_GEN_AUDIO_ENCODER, value)
+
     def add_clip_projector_type(self, value: str) -> None:
         self.add_string(Keys.Clip.PROJECTOR_TYPE, value)
 
@@ -1401,6 +1412,32 @@ class GGUFWriter:
     def add_audio_projector_head_count(self, value: int) -> None:
         self.add_uint32(Keys.ClipAudio.Projector.HEAD_COUNT, value)
 
+    # audio generation (mmproj)
+
+    def add_clip_gen_audio_projector_type(self, value: str) -> None:
+        self.add_string(Keys.ClipGenAudio.PROJECTOR_TYPE, value)
+
+    def add_gen_audio_projection_dim(self, value: int) -> None:
+        self.add_uint32(Keys.ClipGenAudio.PROJECTION_DIM, value)
+
+    def add_gen_audio_embedding_length(self, value: int) -> None:
+        self.add_uint32(Keys.ClipGenAudio.EMBEDDING_LENGTH, value)
+
+    def add_gen_audio_feed_forward_length(self, value: int) -> None:
+        self.add_uint32(Keys.ClipGenAudio.FEED_FORWARD_LENGTH, value)
+
+    def add_gen_audio_block_count(self, value: int) -> None:
+        self.add_uint32(Keys.ClipGenAudio.BLOCK_COUNT, value)
+
+    def add_gen_audio_head_count(self, value: int) -> None:
+        self.add_uint32(Keys.ClipGenAudio.Attention.HEAD_COUNT, value)
+
+    def add_gen_audio_head_count_kv(self, value: int) -> None:
+        self.add_uint32(Keys.ClipGenAudio.Attention.HEAD_COUNT_KV, value)
+
+    def add_gen_audio_attention_layernorm_eps(self, value: float) -> None:
+        self.add_float32(Keys.ClipGenAudio.Attention.LAYERNORM_EPS, value)
+
     def add_xielu_alpha_p(self, values: Sequence[float]):
         self.add_array(Keys.xIELU.ALPHA_P, values)
 

gguf-py/gguf/tensor_mapping.py

@@ -2109,6 +2109,7 @@ class TensorNameMap:
             "conformer.subsample_conv_projection.layer{bid}.conv", # gemma4
             "sound_encoder.encoder.subsampling.layers.{bid}", # parakeet
             "encoder.conv{bid}", # mimo-audio-tokenizer
+            "speaker_encoder.blocks.{bid}.conv", # qwen3tts speaker encoder (only bid=0, the stem TDNN)
         ),
 
         MODEL_TENSOR.A_ENC_CONV1D_NORM: (
@@ -2126,6 +2127,7 @@ class TensorNameMap:
 
         MODEL_TENSOR.A_ENC_CONV_OUT: (
             "audio_tower.conv_out", # qwen3omni
+            "speaker_encoder.mfa.conv", # qwen3tts speaker encoder: multi-layer feature aggregation
         ),
 
         MODEL_TENSOR.A_PRE_NORM: (),
@@ -2336,7 +2338,8 @@ class TensorNameMap:
         MODEL_TENSOR.A_MMPROJ_FC: (
             "audio.multi_modal_projector.linear", # qwen2audio
             "audio_tower.proj", # qwen2omni
-            "model.audio_tower.output_proj" # gemma4
+            "model.audio_tower.output_proj", # gemma4
+            "speaker_encoder.fc", # qwen3tts speaker encoder: final speaker embedding projection
         ),
 
         MODEL_TENSOR.A_MM_NORM_PRE: (
@@ -2411,6 +2414,7 @@ class TensorNameMap:
             "conformer.layers.{bid}.lconv1d.linear_start", # gemma3n
             "sound_encoder.encoder.layers.{bid}.conv.pointwise_conv1", # parakeet
             "encoder.layers.{bid}.conv.up_conv", # granite_speech
+            "speaker_encoder.blocks.{bid}.tdnn1.conv", # qwen3tts speaker encoder
         ),
 
         MODEL_TENSOR.A_ENC_CONV_PW2: (
@@ -2418,6 +2422,23 @@ class TensorNameMap:
             "conformer.layers.{bid}.lconv1d.linear_end", # gemma3n
             "sound_encoder.encoder.layers.{bid}.conv.pointwise_conv2", # parakeet
             "encoder.layers.{bid}.conv.down_conv", # granite_speech
+            "speaker_encoder.blocks.{bid}.tdnn2.conv", # qwen3tts speaker encoder
+        ),
+
+        MODEL_TENSOR.A_ENC_SE_CONV1: (
+            "speaker_encoder.blocks.{bid}.se_block.conv1", # qwen3tts
+        ),
+
+        MODEL_TENSOR.A_ENC_SE_CONV2: (
+            "speaker_encoder.blocks.{bid}.se_block.conv2", # qwen3tts
+        ),
+
+        MODEL_TENSOR.A_ENC_ASP_ATTN: (
+            "speaker_encoder.asp.conv", # qwen3tts
+        ),
+
+        MODEL_TENSOR.A_ENC_ASP_TDNN: (
+            "speaker_encoder.asp.tdnn.conv", # qwen3tts
         ),
 
         MODEL_TENSOR.A_ENC_NORM_CONV: (

gguf-py/tests/test_gguf_reader_validation.py

@@ -0,0 +1,37 @@
+import struct
+import numpy as np
+import pytest
+
+from gguf.gguf_reader import GGUFReader
+
+
+def _write_gguf(path, n_dims_field, dims):
+    buf = b'GGUF' + struct.pack('<IQQ', 3, 1, 0)  # version 3, 1 tensor, 0 kv
+    name = b'bad_tensor'
+    buf += struct.pack('<Q', len(name)) + name
+    buf += struct.pack('<I', n_dims_field)
+    for d in dims:
+        buf += struct.pack('<Q', d)
+    buf += struct.pack('<I', 0)  # dtype F32
+    buf += struct.pack('<Q', 0)  # tensor offset
+    buf += b'\x00' * 64
+    path.write_bytes(buf)
+
+
+def test_n_dims_upper_bound(tmp_path):
+    # crafted file claims 1_000_000 dims; must be rejected, not read past EOF
+    p = tmp_path / 'evil_ndims.gguf'
+    _write_gguf(p, 1_000_000, [1] * 8)
+    with pytest.raises(ValueError, match='exceeds GGML_MAX_DIMS'):
+        GGUFReader(p)
+
+
+def test_dims_product_no_uint64_wraparound(tmp_path):
+    # dims whose true product overflows uint64; np.prod would wrap to 4 and
+    # silently pass an undersized read. The reader must not accept it.
+    dims = [4194305, 4194305, 211106198978564]
+    assert int(np.prod(np.array(dims, dtype=np.uint64))) == 4  # the wrap bug
+    p = tmp_path / 'evil_overflow.gguf'
+    _write_gguf(p, len(dims), dims)
+    with pytest.raises(ValueError):
+        GGUFReader(p)

include/llama.h

@@ -1256,7 +1256,6 @@ extern "C" {
         struct ggml_tensor * probs;
         struct ggml_tensor * sampled;
         struct ggml_tensor * candidates;
-        int64_t              n_vocab;
     };
 
     // user code can implement the interface below in order to create custom llama_sampler
@@ -1425,6 +1424,7 @@ extern "C" {
 
     /// NOTE: Avoid using on the full vocabulary as searching for repeated tokens can become slow. For example, apply top-k or top-p sampling first.
     LLAMA_API struct llama_sampler * llama_sampler_init_penalties(
+                             int32_t   n_vocab,
                              int32_t   penalty_last_n,   // last n tokens to penalize (0 = disable penalty, -1 = context size)
                                float   penalty_repeat,   // must be > 0.0, 1.0 = disabled
                                float   penalty_freq,     // must be finite, 0.0 = disabled

models/templates/deepseek-ai-DeepSeek-V4-Flash-0731.jinja

@@ -0,0 +1,140 @@
+{%- if not add_generation_prompt is defined -%}
+  {%- set add_generation_prompt = false -%}
+{%- endif -%}
+{%- if not thinking is defined -%}
+  {%- if enable_thinking is defined -%}
+    {%- set thinking = enable_thinking -%}
+  {%- else -%}
+    {%- set thinking = false -%}
+  {%- endif -%}
+{%- endif -%}
+{%- if not drop_thinking is defined -%}
+  {%- set drop_thinking = true -%}
+{%- endif -%}
+{%- set dsml_token = '｜DSML｜' -%}
+{%- set thinking_start_token = '<think>' -%}
+{%- set thinking_end_token = '</think>' -%}
+{%- set reasoning_effort_high = 'Reasoning Effort: Absolute maximum with no shortcuts permitted.\nYou MUST be very thorough in your thinking and comprehensively decompose the problem to resolve the root cause, rigorously stress-testing your logic against all potential paths, edge cases, and adversarial scenarios.\nExplicitly write out your entire deliberation process, documenting every intermediate step, considered alternative, and rejected hypothesis to ensure absolutely no assumption is left unchecked.\n\n' -%}
+{%- set reasoning_effort_max = 'Reasoning Effort: Beyond maximum — exhaustive, relentless, and uncompromising.\nYou MUST reason with the utmost depth and rigor, leaving absolutely nothing to chance: exhaustively decompose the problem into its most fundamental components, trace every causal chain to its root, and resolve the underlying cause rather than any surface symptom.\nDo not stop reasoning until you have independently verified the solution from multiple angles and are certain that no assumption remains unchecked and no error remains undiscovered.\n\n' -%}
+{%- set response_format_template = '## Response Format:\n\nYou MUST strictly adhere to the following schema to reply:\n' -%}
+{%- set has_tools = false -%}
+{%- set tools_header = '## Tools\n\nYou have access to a set of tools to help answer the user\'s question. You can invoke tools by writing a "<' + dsml_token + 'tool_calls>" block like the following:\n\n<' + dsml_token + 'tool_calls>\n<' + dsml_token + 'invoke name="$TOOL_NAME">\n<' + dsml_token + 'parameter name="$PARAMETER_NAME" string="true|false">$PARAMETER_VALUE</' + dsml_token + 'parameter>\n...\n</' + dsml_token + 'invoke>\n<' + dsml_token + 'invoke name="$TOOL_NAME2">\n...\n</' + dsml_token + 'invoke>\n</' + dsml_token + 'tool_calls>\n\nString parameters should be specified as is and set `string="true"`. For all other types (numbers, booleans, arrays, objects), pass the value in JSON format and set `string="false"`.\n\nIf thinking_mode is enabled (triggered by ' + thinking_start_token + '), you MUST output your complete reasoning inside ' + thinking_start_token + '...' + thinking_end_token + ' BEFORE any tool calls or final response.\n\nOtherwise, output directly after ' + thinking_end_token + ' with tool calls or final response.\n\n### Available Tool Schemas\n\n' -%}
+{%- set tools_footer = '\nYou MUST strictly follow the above defined tool name and parameter schemas to invoke tool calls.\n' -%}
+{%- set ns = namespace(system_prompt='', is_first_sp=true, has_tool_calls=false) -%}
+{%- for message in messages -%}
+  {%- if message['role'] == 'system' -%}
+    {%- if ns.is_first_sp -%}
+      {%- set ns.system_prompt = ns.system_prompt + (message['content'] or '') -%}
+      {%- set ns.is_first_sp = false -%}
+    {%- else -%}
+      {%- set ns.system_prompt = ns.system_prompt + '\n\n' + (message['content'] or '') -%}
+    {%- endif -%}
+  {%- endif -%}
+{%- endfor -%}
+{%- if tools is defined and tools -%}
+  {%- set has_tools = true -%}
+  {%- set ts = namespace(schemas='') -%}
+  {%- for tool in tools -%}
+    {%- if tool['type'] == 'function' -%}
+      {%- set ts.schemas = ts.schemas + (tool['function'] | tojson) + '\n' -%}
+    {%- endif -%}
+  {%- endfor -%}
+  {%- if ns.system_prompt -%}
+    {%- set ns.system_prompt = ns.system_prompt + '\n\n' + tools_header + ts.schemas + tools_footer -%}
+  {%- else -%}
+    {%- set ns.system_prompt = tools_header + ts.schemas + tools_footer -%}
+  {%- endif -%}
+{%- endif -%}
+{%- if response_format is defined -%}
+  {%- if ns.system_prompt -%}
+    {%- set ns.system_prompt = ns.system_prompt + '\n\n' -%}
+  {%- endif -%}
+  {%- set ns.system_prompt = ns.system_prompt + response_format_template + (response_format | tojson) -%}
+{%- endif -%}
+{{- bos_token -}}
+{%- if messages and thinking and reasoning_effort is defined and reasoning_effort == 'high' -%}
+  {{- reasoning_effort_high -}}
+{%- elif messages and thinking and reasoning_effort is defined and reasoning_effort == 'max' -%}
+  {{- reasoning_effort_max -}}
+{%- endif -%}
+{{- ns.system_prompt -}}
+{%- set last_user_idx = namespace(value=-1) -%}
+{%- for message in messages -%}
+  {%- if message['role'] == 'user' or message['role'] == 'developer' or message['role'] == 'tool' -%}
+    {%- set last_user_idx.value = loop.index0 -%}
+  {%- endif -%}
+{%- endfor -%}
+{%- set state = namespace(in_user=false) -%}
+{%- for message in messages -%}
+  {%- if message['role'] == 'tool' -%}
+    {%- set ns.has_tool_calls = true -%}
+  {%- endif -%}
+{%- endfor -%}
+{%- for message in messages -%}
+  {%- if message['role'] == 'user' or message['role'] == 'developer' -%}
+    {%- if state.in_user -%}
+      {{- '\n\n' -}}
+    {%- else -%}
+      {{- '<｜User｜>' -}}
+      {%- set state.in_user = true -%}
+    {%- endif -%}
+    {{- message['content'] or '' -}}
+  {%- elif message['role'] == 'tool' -%}
+    {%- if state.in_user -%}
+      {{- '\n\n' -}}
+    {%- else -%}
+      {{- '<｜User｜>' -}}
+      {%- set state.in_user = true -%}
+    {%- endif -%}
+    {{- '<tool_result>' + (message['content'] or '') + '</tool_result>' -}}
+  {%- elif message['role'] == 'assistant' -%}
+    {%- set state.in_user = false -%}
+    {{- '<｜Assistant｜>' -}}
+    {%- set is_after_last_user = loop.index0 > last_user_idx.value -%}
+    {%- set keep_reasoning = thinking and ((not drop_thinking) or has_tools or is_after_last_user or ns.has_tool_calls) -%}
+    {%- if keep_reasoning -%}
+      {{- thinking_start_token -}}
+      {%- if message['reasoning_content'] is defined and message['reasoning_content'] -%}
+        {{- message['reasoning_content'] -}}
+      {%- endif -%}
+      {{- thinking_end_token -}}
+    {%- else -%}
+      {{- thinking_end_token -}}
+    {%- endif -%}
+    {%- if message['content'] is defined and message['content'] -%}
+      {{- message['content'] -}}
+    {%- endif -%}
+    {%- if message['tool_calls'] -%}
+      {{- '\n\n<' + dsml_token + 'tool_calls>\n' -}}
+      {%- for tool in message['tool_calls'] -%}
+        {%- set func = tool['function'] -%}
+        {{- '<' + dsml_token + 'invoke name="' + func['name'] + '">\n' -}}
+        {%- set args = func['arguments'] -%}
+        {%- if args is string -%}
+          {%- set args = args | from_json -%}
+        {%- endif -%}
+        {%- for key, val in args.items() -%}
+          {%- if val is string -%}
+            {{- '<' + dsml_token + 'parameter name="' + key + '" string="true">' + val + '</' + dsml_token + 'parameter>\n' -}}
+          {%- else -%}
+            {{- '<' + dsml_token + 'parameter name="' + key + '" string="false">' + (val | tojson) + '</' + dsml_token + 'parameter>\n' -}}
+          {%- endif -%}
+        {%- endfor -%}
+        {%- if not args -%}
+          {{- '\n' -}}
+        {%- endif -%}
+        {{- '</' + dsml_token + 'invoke>\n' -}}
+      {%- endfor -%}
+      {{- '</' + dsml_token + 'tool_calls>' -}}
+    {%- endif -%}
+    {{- '<｜end▁of▁sentence｜>' -}}
+  {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+  {{- '<｜Assistant｜>' -}}
+  {%- if thinking -%}
+    {{- thinking_start_token -}}
+  {%- else -%}
+    {{- thinking_end_token -}}
+  {%- endif -%}
+{%- endif -%}

models/templates/deepseek-ai-DeepSeek-V4.jinja

@@ -9,11 +9,14 @@
   {%- endif -%}
 {%- endif -%}
 {%- if not drop_thinking is defined -%}
-  {%- set drop_thinking = false -%}
+  {%- set drop_thinking = true -%}
 {%- endif -%}
 {%- set dsml_token = '｜DSML｜' -%}
 {%- set thinking_start_token = '<think>' -%}
 {%- set thinking_end_token = '</think>' -%}
+{%- set reasoning_effort_max = 'Reasoning Effort: Absolute maximum with no shortcuts permitted.\nYou MUST be very thorough in your thinking and comprehensively decompose the problem to resolve the root cause, rigorously stress-testing your logic against all potential paths, edge cases, and adversarial scenarios.\nExplicitly write out your entire deliberation process, documenting every intermediate step, considered alternative, and rejected hypothesis to ensure absolutely no assumption is left unchecked.\n\n' -%}
+{%- set response_format_template = '## Response Format:\n\nYou MUST strictly adhere to the following schema to reply:\n' -%}
+{%- set has_tools = false -%}
 {%- set tools_header = '## Tools\n\nYou have access to a set of tools to help answer the user\'s question. You can invoke tools by writing a "<' + dsml_token + 'tool_calls>" block like the following:\n\n<' + dsml_token + 'tool_calls>\n<' + dsml_token + 'invoke name="$TOOL_NAME">\n<' + dsml_token + 'parameter name="$PARAMETER_NAME" string="true|false">$PARAMETER_VALUE</' + dsml_token + 'parameter>\n...\n</' + dsml_token + 'invoke>\n<' + dsml_token + 'invoke name="$TOOL_NAME2">\n...\n</' + dsml_token + 'invoke>\n</' + dsml_token + 'tool_calls>\n\nString parameters should be specified as is and set `string="true"`. For all other types (numbers, booleans, arrays, objects), pass the value in JSON format and set `string="false"`.\n\nIf thinking_mode is enabled (triggered by ' + thinking_start_token + '), you MUST output your complete reasoning inside ' + thinking_start_token + '...' + thinking_end_token + ' BEFORE any tool calls or final response.\n\nOtherwise, output directly after ' + thinking_end_token + ' with tool calls or final response.\n\n### Available Tool Schemas\n\n' -%}
 {%- set tools_footer = '\nYou MUST strictly follow the above defined tool name and parameter schemas to invoke tool calls.\n' -%}
 {%- set ns = namespace(system_prompt='', is_first_sp=true, has_tool_calls=false) -%}
@@ -28,6 +31,7 @@
   {%- endif -%}
 {%- endfor -%}
 {%- if tools is defined and tools -%}
+  {%- set has_tools = true -%}
   {%- set ts = namespace(schemas='') -%}
   {%- for tool in tools -%}
     {%- if tool['type'] == 'function' -%}
@@ -40,7 +44,16 @@
     {%- set ns.system_prompt = tools_header + ts.schemas + tools_footer -%}
   {%- endif -%}
 {%- endif -%}
+{%- if response_format is defined -%}
+  {%- if ns.system_prompt -%}
+    {%- set ns.system_prompt = ns.system_prompt + '\n\n' -%}
+  {%- endif -%}
+  {%- set ns.system_prompt = ns.system_prompt + response_format_template + (response_format | tojson) -%}
+{%- endif -%}
 {{- bos_token -}}
+{%- if messages and thinking and reasoning_effort is defined and reasoning_effort == 'max' -%}
+  {{- reasoning_effort_max -}}
+{%- endif -%}
 {{- ns.system_prompt -}}
 {%- set last_user_idx = namespace(value=-1) -%}
 {%- for message in messages -%}
@@ -75,8 +88,8 @@
     {%- set state.in_user = false -%}
     {{- '<｜Assistant｜>' -}}
     {%- set is_after_last_user = loop.index0 > last_user_idx.value -%}
-    {%- set retain_reasoning = (not drop_thinking) or (is_after_last_user or ns.has_tool_calls) -%}
-    {%- if retain_reasoning and thinking -%}
+    {%- set keep_reasoning = thinking and ((not drop_thinking) or has_tools or is_after_last_user or ns.has_tool_calls) -%}
+    {%- if keep_reasoning -%}
       {{- thinking_start_token -}}
       {%- if message['reasoning_content'] is defined and message['reasoning_content'] -%}
         {{- message['reasoning_content'] -}}
@@ -104,6 +117,9 @@
             {{- '<' + dsml_token + 'parameter name="' + key + '" string="false">' + (val | tojson) + '</' + dsml_token + 'parameter>\n' -}}
           {%- endif -%}
         {%- endfor -%}
+        {%- if not args -%}
+          {{- '\n' -}}
+        {%- endif -%}
         {{- '</' + dsml_token + 'invoke>\n' -}}
       {%- endfor -%}
       {{- '</' + dsml_token + 'tool_calls>' -}}
@@ -118,4 +134,4 @@
   {%- else -%}
     {{- thinking_end_token -}}
   {%- endif -%}
-{%- endif -%}
+{%- endif -%}

scripts/sync-ggml.last

@@ -1 +1 @@
-06ca97616793248fadb410ea8d69c7511b2005e4
+90951f99af1fbebef3fbdd58ff5b8715b0bb9c43

scripts/sync_vendor.py

@@ -5,7 +5,7 @@ import os
 import sys
 import subprocess
 
-HTTPLIB_VERSION = "refs/tags/v0.51.0"
+HTTPLIB_VERSION = "refs/tags/v0.52.0"
 
 vendor = {
     "https://github.com/nlohmann/json/releases/latest/download/json.hpp":     "vendor/nlohmann/json.hpp",

skills/code-review/SKILL.md

@@ -119,6 +119,7 @@ Public API changes carry a higher bar than internal ones (`CONTRIBUTING.md`). Re
 - In most cases, `build_vit` should be enough to build the transformer graph for vision models. Do not add a loop to build the transformer graph manually, unless you have a very good reason to do so. If you do, please explain why in the PR description.
 - If you need a dedicated preprocessor, there is a high chance that it can be a derived class from one of the existing preprocessors. Check carefully before adding a new preprocessor class.
 - If the model need a new public API in `mtmd.h`, open a discussion first.
+- For audio generation models, see `tools/mtmd/README-dev.md`
 
 ## General (always)
 

src/llama-arch.cpp

@@ -144,6 +144,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
     { LLM_ARCH_TALKIE,           "talkie"           },
     { LLM_ARCH_MELLUM,           "mellum"           },
     { LLM_ARCH_NANBEIGE,         "nanbeige"         },
+    { LLM_ARCH_QWEN3TTS,         "qwen3tts"         },
     { LLM_ARCH_UNKNOWN,          "(unknown)"        },
 };
 
@@ -1026,6 +1027,7 @@ bool llm_arch_supports_sm_tensor(const llm_arch & arch) {
         case LLM_ARCH_MINIMAX_M3:
         case LLM_ARCH_MISTRAL4:
         case LLM_ARCH_KIMI_LINEAR:
+        case LLM_ARCH_QWEN3TTS:
             return false;
         default:
             return true;

src/llama-arch.h

@@ -149,6 +149,7 @@ enum llm_arch {
     LLM_ARCH_MINIMAX_M3,
     LLM_ARCH_DFLASH,
     LLM_ARCH_NANBEIGE,
+    LLM_ARCH_QWEN3TTS,
     LLM_ARCH_UNKNOWN,
 };
 

src/llama-ext.h

@@ -124,3 +124,9 @@ LLAMA_API llama_context * llama_get_ctx_other(struct llama_context * ctx);
 LLAMA_API const int32_t * llama_model_target_layer_ids  (const struct llama_model * model);
 // returns the number of extracted layers from target model
 LLAMA_API uint32_t        llama_model_target_layer_ids_n(const struct llama_model * model);
+
+// retrieves the whole token embedding matrix in F32 format (n_embd * n_vocab)
+// returns total number of elements or 0 on error
+// if out is nullptr, returns the number of tokens without writing to out
+// caller must allocate enough memory for out before calling
+LLAMA_API uint32_t llama_model_get_tok_embd(const struct llama_model * model, float * out);

src/llama-graph.cpp

@@ -3683,7 +3683,6 @@ void llm_graph_context::build_sampling() const {
             /*.probs       =*/ nullptr,
             /*.sampled     =*/ nullptr,
             /*.candidates  =*/ nullptr,
-            /*.n_vocab     =*/ logits_seq->ne[0],
         };
 
         assert(sampler->iface->backend_apply);

src/llama-model-loader.cpp

@@ -857,7 +857,11 @@ struct ggml_tensor * llama_model_loader::require_tensor_meta(const std::string &
     return tensor;
 }
 
-const struct ggml_tensor * llama_model_loader::check_tensor_dims(const std::string & name, const std::vector<int64_t> & ne, bool required) const {
+const struct ggml_tensor * llama_model_loader::check_tensor_dims(
+        const std::string & name,
+        const std::vector<int64_t> & ne,
+        bool required,
+        bool allow_reshape) const {
     const struct ggml_tensor * cur = get_tensor_meta(name.c_str());
 
     if (cur == NULL) {
@@ -867,21 +871,33 @@ const struct ggml_tensor * llama_model_loader::check_tensor_dims(const std::stri
         throw std::runtime_error(format("%s: tensor '%s' not found", __func__, name.c_str()));
     }
 
-    {
-        bool is_ok = true;
+    bool is_ok = true;
+
+    if (allow_reshape) {
+        // check total number of elements only
+        const int64_t ncur = ggml_nelements(cur);
+        int64_t nexp = 1;
+        for (size_t i = 0; i < ne.size(); ++i) {
+            nexp *= ne[i];
+        }
+        if (ncur != nexp) {
+            is_ok = false;
+        }
+    } else {
         for (size_t i = 0; i < GGML_MAX_DIMS; ++i) {
             if ((i < ne.size() && ne[i] != cur->ne[i]) || (i >= ne.size() && cur->ne[i] != 1)) {
                 is_ok = false;
                 break;
             }
         }
-        if (!is_ok) {
-            throw std::runtime_error(
-                    format("%s: tensor '%s' has wrong shape; expected %s, got %s",
-                        __func__, name.c_str(),
-                        llama_format_tensor_shape(ne).c_str(),
-                        llama_format_tensor_shape(cur).c_str()));
-        }
+    }
+
+    if (!is_ok) {
+        throw std::runtime_error(
+                format("%s: tensor '%s' has wrong shape; expected %s, got %s",
+                    __func__, name.c_str(),
+                    llama_format_tensor_shape(ne).c_str(),
+                    llama_format_tensor_shape(cur).c_str()));
     }
 
     return cur;
@@ -1246,11 +1262,25 @@ struct ggml_tensor * llama_model_loader::create_tensor(
         return ret;
     }
 
-    ggml_tensor * t_meta = get_tensor_meta(tn.str().c_str());
-    ggml_backend_buffer_type_t buft = buft_for_tensor(t_meta);
-    if (buft == nullptr) {
-        return nullptr; // return type is ggml_tensor *
+    LLAMA_LOG_DEBUG("%s: loading tensor %s\n", __func__, tn.str().c_str());
+    const struct ggml_tensor * cur = check_tensor_dims(tn.str(), ne, !(flags & TENSOR_NOT_REQUIRED), flags & TENSOR_ALLOW_RESHAPE);
+    if (cur == NULL) {
+        return NULL;
     }
+
+    ggml_tensor t_meta = *cur;
+    if (flags & TENSOR_ALLOW_RESHAPE) {
+        for (size_t dim = 0; dim < GGML_MAX_DIMS; dim++) {
+            t_meta.ne[dim] = dim < ne.size() ? ne.begin()[dim] : 1;
+            t_meta.nb[dim] = dim == 0 ? ggml_type_size(t_meta.type) : t_meta.ne[dim-1]*t_meta.nb[dim-1];
+        }
+    }
+
+    ggml_backend_buffer_type_t buft = buft_for_tensor(&t_meta);
+    if (buft == nullptr) {
+        return nullptr;
+    }
+
     ggml_context * ctx = ctx_for_buft(buft);
 
     // if duplicated, check if the original tensor was allocated in the same buffer type context and avoid creating a new one
@@ -1261,20 +1291,13 @@ struct ggml_tensor * llama_model_loader::create_tensor(
         }
     }
 
-    LLAMA_LOG_DEBUG("%s: loading tensor %s\n", __func__, tn.str().c_str());
-    const struct ggml_tensor * cur = check_tensor_dims(tn.str(), ne, !(flags & TENSOR_NOT_REQUIRED));
-
-    if (cur == NULL) {
-        return NULL;
-    }
-
     const bool duplicated = flags & TENSOR_DUPLICATED;
 
-    struct ggml_tensor * tensor = ggml_dup_tensor(ctx, cur);
-    ggml_set_name(tensor, ggml_get_name(cur));
+    struct ggml_tensor * tensor = ggml_dup_tensor(ctx, &t_meta);
+    ggml_set_name(tensor, ggml_get_name(&t_meta));
 
     if (duplicated) {
-        size_data += ggml_nbytes(cur);
+        size_data += ggml_nbytes(&t_meta);
     } else {
         n_created++;
     }
@@ -1282,34 +1305,6 @@ struct ggml_tensor * llama_model_loader::create_tensor(
     return tensor;
 }
 
-struct ggml_tensor * llama_model_loader::create_tensor_as_view(struct ggml_context * ctx, struct ggml_tensor * base, const std::string & name, const std::initializer_list<int64_t> & ne, size_t offset, bool required) {
-    const struct ggml_tensor * cur = check_tensor_dims(name, ne, required);
-
-    if (cur == NULL) {
-        return NULL;
-    }
-
-    if (cur->type != base->type) {
-        throw std::runtime_error(format("%s: tensor '%s' has wrong type; expected %s, got %s", __func__, name.c_str(), ggml_type_name(base->type), ggml_type_name(cur->type)));
-    }
-
-    std::array<int64_t, GGML_MAX_DIMS> dims;
-    for (size_t i = 0; i < GGML_MAX_DIMS; ++i) {
-        dims[i] = i < ne.size() ? ne.begin()[i] : 1;
-    }
-
-    struct ggml_tensor * tensor = ggml_view_4d(ctx, base,
-                                    dims[0], dims[1], dims[2], dims[3],
-                                    cur->nb[1], cur->nb[2], cur->nb[3],
-                                    offset);
-
-    ggml_set_name(tensor, name.c_str());
-
-    n_created++;
-
-    return tensor;
-}
-
 void llama_model_loader::done_getting_tensors(bool partial) const {
     if (n_created > n_tensors) {
         throw std::runtime_error(format("%s: too many tensors created; expected %d, got %d", __func__, n_tensors, n_created));

src/llama-model-loader.h

@@ -67,6 +67,7 @@ struct llama_model_loader {
     static const int TENSOR_DUPLICATED      = 1 << 1;
     static const int TENSOR_SKIP            = 1 << 2;
     static const int TENSOR_SKIP_IF_VIRTUAL = 1 << 3;
+    static const int TENSOR_ALLOW_RESHAPE   = 1 << 4;
 
     int n_kv      = 0;
     int n_tensors = 0;
@@ -177,14 +178,16 @@ struct llama_model_loader {
 
     struct ggml_tensor * require_tensor_meta(const std::string & name) const;
 
-    const struct ggml_tensor * check_tensor_dims(const std::string & name, const std::vector<int64_t> & ne, bool required) const;
+    const struct ggml_tensor * check_tensor_dims(
+            const std::string & name,
+            const std::vector<int64_t> & ne,
+            bool required,
+            bool allow_reshape) const;
 
     struct ggml_tensor * create_tensor(
         const llama_hparams & hparams, const buft_list_t * buft_list_cpu, const buft_list_t * buft_list_input, const buft_list_t * buft_list_output,
         const buft_list_t * buft_list_layer, const LLM_TN_IMPL & tn, const std::initializer_list<int64_t> & ne, int flags);
 
-    struct ggml_tensor * create_tensor_as_view(struct ggml_context * ctx, struct ggml_tensor * base, const std::string & name, const std::initializer_list<int64_t> & ne, size_t offset, bool required = true);
-
     void done_getting_tensors(bool partial = false) const;
 
     void init_mappings(bool prefetch = true, llama_mlocks * mlock_mmaps = nullptr);

src/llama-model.cpp

@@ -112,6 +112,8 @@ static llama_model * llama_model_mapping(llm_arch arch, const llama_model_params
             return new llama_model_qwen3vl(params);
         case LLM_ARCH_QWEN3VLMOE:
             return new llama_model_qwen3vlmoe(params);
+        case LLM_ARCH_QWEN3TTS:
+            return new llama_model_qwen3tts(params);
         case LLM_ARCH_PHI2:
             return new llama_model_phi2(params);
         case LLM_ARCH_PHI3:
@@ -2693,6 +2695,7 @@ llama_rope_type llama_model_rope_type(const llama_model * model) {
         case LLM_ARCH_QWEN3VLMOE:
         case LLM_ARCH_QWEN35:
         case LLM_ARCH_QWEN35MOE:
+        case LLM_ARCH_QWEN3TTS:
             return LLAMA_ROPE_TYPE_IMROPE;
 
         case LLM_ARCH_GLM4:
@@ -2867,7 +2870,8 @@ llama_model_base::llama_model_base(const struct llama_model_params & params) : l
     TENSOR_DUPLICATED     (llama_model_loader::TENSOR_DUPLICATED),
     TENSOR_NOT_REQUIRED   (llama_model_loader::TENSOR_NOT_REQUIRED),
     TENSOR_SKIP           (llama_model_loader::TENSOR_SKIP),
-    TENSOR_SKIP_IF_VIRTUAL(llama_model_loader::TENSOR_SKIP_IF_VIRTUAL) {}
+    TENSOR_SKIP_IF_VIRTUAL(llama_model_loader::TENSOR_SKIP_IF_VIRTUAL),
+    TENSOR_ALLOW_RESHAPE  (llama_model_loader::TENSOR_ALLOW_RESHAPE) {}
 
 ggml_tensor * llama_model_base::create_tensor(const LLM_TN_IMPL & tn, const std::initializer_list<int64_t> & ne, int flags) {
     GGML_ASSERT(ml != nullptr);
@@ -2907,3 +2911,38 @@ const int32_t * llama_model_target_layer_ids(const struct llama_model * model) {
 uint32_t llama_model_target_layer_ids_n(const struct llama_model * model) {
     return (uint32_t) model->target_layer_ids.size();
 }
+
+uint32_t llama_model_get_tok_embd(const struct llama_model * model, float * out) {
+    if (model->vocab.n_tokens() == 0 || model->tok_embd == nullptr) {
+        return 0;
+    }
+
+    const ggml_tensor * tensor = model->tok_embd;
+    const size_t nelements = ggml_nelements(tensor);
+    GGML_ASSERT(nelements <= UINT32_MAX); // for the return type
+
+    if (out == nullptr) {
+        return (uint32_t) nelements;
+    }
+
+    if (tensor->type == GGML_TYPE_F32) {
+        ggml_backend_tensor_get(tensor, out, 0, nelements * sizeof(float));
+        return (uint32_t) nelements;
+    }
+
+    std::vector<uint8_t> buf(ggml_nbytes(tensor));
+    ggml_backend_tensor_get(tensor, buf.data(), 0, buf.size());
+
+    const ggml_type_traits * traits = ggml_get_type_traits(tensor->type);
+    if (tensor->type == GGML_TYPE_F16) {
+        ggml_fp16_to_fp32_row((const ggml_fp16_t *) buf.data(), out, nelements);
+    } else if (tensor->type == GGML_TYPE_BF16) {
+        ggml_bf16_to_fp32_row((const ggml_bf16_t *) buf.data(), out, nelements);
+    } else if (ggml_is_quantized(tensor->type) && traits->to_float != nullptr) {
+        traits->to_float(buf.data(), out, nelements);
+    } else {
+        GGML_ABORT("unsupported tensor type for dequantization: %s", ggml_type_name(tensor->type));
+    }
+
+    return (uint32_t) nelements;
+}

src/llama-model.h

@@ -719,6 +719,7 @@ struct llama_model_base : public llama_model {
     const int TENSOR_NOT_REQUIRED;
     const int TENSOR_SKIP;
     const int TENSOR_SKIP_IF_VIRTUAL;
+    const int TENSOR_ALLOW_RESHAPE;
 
     explicit llama_model_base(const llama_model_params & params);
     virtual ~llama_model_base() = default;

src/llama-sampler.cpp

@@ -589,7 +589,6 @@ static bool llama_sampler_backend_support(
         /*.probs      = */ nullptr,
         /*.sampled    = */ nullptr,
         /*.candidates = */ ggml_new_tensor_1d(ctx, GGML_TYPE_I32, n),
-        /*.n_vocab    = */ n,
     };
 
     ggml_cgraph * gf = ggml_new_graph(ctx);
@@ -2640,6 +2639,7 @@ struct llama_sampler * llama_sampler_init_grammar_lazy_patterns(
 // penalties
 
 struct llama_sampler_penalties : public llama_sampler_backend {
+    const int32_t n_vocab;
     const int32_t penalty_last_n;
     const float   penalty_repeat;
     const float   penalty_freq;
@@ -2655,7 +2655,6 @@ struct llama_sampler_penalties : public llama_sampler_backend {
     ggml_tensor * inp_counts    = nullptr;
 
     // backend helpers
-    int32_t n_vocab = 0;
     int32_t n_max   = 0;
     bool has_candidates = false;
 
@@ -2676,11 +2675,13 @@ struct llama_sampler_penalties : public llama_sampler_backend {
     }
 
     llama_sampler_penalties(
+            int32_t n_vocab,
             int32_t penalty_last_n,
             float   penalty_repeat,
             float   penalty_freq,
             float   penalty_present)
         : llama_sampler_backend("penalties")
+        , n_vocab         (n_vocab)
         , penalty_last_n  (penalty_last_n)
         , penalty_repeat  (penalty_repeat)
         , penalty_freq    (penalty_freq)
@@ -2766,6 +2767,7 @@ static void llama_sampler_penalties_reset(struct llama_sampler * smpl) {
 static struct llama_sampler * llama_sampler_penalties_clone(const struct llama_sampler * smpl) {
     const auto * ctx = (const llama_sampler_penalties *) smpl->ctx;
     auto * result = llama_sampler_init_penalties(
+            ctx->n_vocab,
             ctx->penalty_last_n,
             ctx->penalty_repeat,
             ctx->penalty_freq,
@@ -2811,10 +2813,9 @@ static void llama_sampler_penalties_backend_apply(
         return;
     }
 
-    GGML_ASSERT(data->n_vocab > 0 && data->n_vocab <= INT32_MAX);
+    GGML_ASSERT(sctx->n_vocab > 0);
 
     sctx->has_candidates = data->candidates != nullptr;
-    sctx->n_vocab = (int32_t) data->n_vocab;
     sctx->n_max   = std::min(sctx->penalty_last_n, sctx->n_vocab);
 
     sctx->inp_token_ids = ggml_new_tensor_1d(ctx, GGML_TYPE_I32, sctx->n_max);
@@ -2965,6 +2966,7 @@ static struct llama_sampler_i llama_sampler_penalties_i = {
 };
 
 struct llama_sampler * llama_sampler_init_penalties(
+        int32_t n_vocab,
         int32_t penalty_last_n,
         float penalty_repeat,
         float penalty_freq,
@@ -2979,6 +2981,7 @@ struct llama_sampler * llama_sampler_init_penalties(
     return llama_sampler_init(
         /* .iface = */ &llama_sampler_penalties_i,
         /* .ctx   = */ new llama_sampler_penalties(
+            n_vocab,
             penalty_last_n,
             penalty_repeat,
             penalty_freq,

src/llama-vocab.cpp

@@ -1373,8 +1373,10 @@ struct llm_tokenizer_plamo2 : llm_tokenizer {
             if (vocab.is_byte(token_id)) {
                 if (entry.text.length() == 6 && entry.text.substr(0, 3) == "<0x" && entry.text.back() == '>') {
                     std::string hex_str = entry.text.substr(3, 2);
-                    int byte_val = std::stoi(hex_str, nullptr, 16);
-                    bytes_[byte_val] = static_cast<llama_token>(token_id);
+                    if (std::isxdigit(static_cast<unsigned char>(hex_str[0])) && std::isxdigit(static_cast<unsigned char>(hex_str[1]))) {
+                        int byte_val = std::stoi(hex_str, nullptr, 16);
+                        bytes_[byte_val] = static_cast<llama_token>(token_id);
+                    }
                 }
                 continue;
             }
@@ -3625,12 +3627,15 @@ int32_t llama_vocab::impl::token_to_piece(llama_token token, char * buf, int32_t
                 if (vocab.is_byte(token)) {
                     // Handle byte tokens like <0xXX>
                     if (token_text.length() == 6 && token_text.substr(0, 3) == "<0x" && token_text.back() == '>') {
-                        int hex_val = std::stoi(token_text.substr(3, 2), nullptr, 16);
-                        if (length < 1) {
-                            return -1;
+                        std::string hex_str = token_text.substr(3, 2);
+                        if (std::isxdigit(static_cast<unsigned char>(hex_str[0])) && std::isxdigit(static_cast<unsigned char>(hex_str[1]))) {
+                            int hex_val = std::stoi(hex_str, nullptr, 16);
+                            if (length < 1) {
+                                return -1;
+                            }
+                            buf[0] = static_cast<char>(hex_val);
+                            return 1;
                         }
-                        buf[0] = static_cast<char>(hex_val);
-                        return 1;
                     }
                 }
 

src/models/deepseek2.cpp

@@ -37,6 +37,11 @@ void llama_model_deepseek2::load_arch_hparams(llama_model_loader & ml) {
         hparams.rope_yarn_log_mul /= 0.1f;
     }
 
+    // NextN/MTP
+    ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false);
+    GGML_ASSERT(hparams.n_layer_nextn == 0 ||
+        hparams.n_layer() + hparams.n_layer_nextn == hparams.n_layer_all);
+
     // (optional) temperature tuning - used by mistral-large
     ml.get_key(LLM_KV_ATTENTION_TEMPERATURE_SCALE,  hparams.f_attn_temp_scale,       false);
     ml.get_key(LLM_KV_ATTENTION_TEMPERATURE_LENGTH, hparams.n_attn_temp_floor_scale, false); // FIXME why not use temperature_length?
@@ -52,10 +57,20 @@ void llama_model_deepseek2::load_arch_hparams(llama_model_loader & ml) {
     }
 }
 
-void llama_model_deepseek2::load_arch_tensors(llama_model_loader &) {
+void llama_model_deepseek2::load_arch_tensors(llama_model_loader & ml) {
     LLAMA_LOAD_LOCALS;
     const int64_t n_expert_shared = hparams.n_expert_shared;
 
+    const bool mtp_only = (hparams.n_layer_nextn > 0) && (ml.get_weight("blk.0.attn_norm.weight") == nullptr);
+    const std::string mtp_probe = "blk." + std::to_string(n_layer) + ".nextn.eh_proj.weight";
+    const bool trunk_only = (hparams.n_layer_nextn > 0) && (ml.get_weight(mtp_probe.c_str()) == nullptr);
+    const int trunk_flags = mtp_only  ? TENSOR_NOT_REQUIRED : 0;
+    int       mtp_flags   = trunk_only ? TENSOR_NOT_REQUIRED : 0;
+
+    if (!ml.load_mtp) {
+        mtp_flags |= TENSOR_SKIP;
+    }
+
     const bool is_mla = hparams.is_mla();
 
     // note: these are the actual head sizes you get when treating as MHA or after "decompression" using wv_b for MLA
@@ -81,44 +96,45 @@ void llama_model_deepseek2::load_arch_tensors(llama_model_loader &) {
         output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
     }
 
-    for (int i = 0; i < n_layer; ++i) {
+    for (int i = 0; i < n_layer_all; ++i) {
         auto & layer = layers[i];
+        const int flags = i < n_layer ? trunk_flags : mtp_flags;
 
-        layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, 0);
+        layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, flags);
         if (q_lora_rank > 0) {
-            layer.attn_q_a_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_A_NORM, "weight", i), {q_lora_rank}, 0);
+            layer.attn_q_a_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_A_NORM, "weight", i), {q_lora_rank}, flags);
         }
 
-        layer.attn_kv_a_norm = create_tensor(tn(LLM_TENSOR_ATTN_KV_A_NORM, "weight", i), {kv_lora_rank}, 0);
+        layer.attn_kv_a_norm = create_tensor(tn(LLM_TENSOR_ATTN_KV_A_NORM, "weight", i), {kv_lora_rank}, flags);
 
         if (q_lora_rank > 0) {
-            layer.wq_a = create_tensor(tn(LLM_TENSOR_ATTN_Q_A, "weight", i), {n_embd, q_lora_rank}, 0);
-            layer.wq_b = create_tensor(tn(LLM_TENSOR_ATTN_Q_B, "weight", i), {q_lora_rank, n_head * n_embd_head_k_mla}, 0);
+            layer.wq_a = create_tensor(tn(LLM_TENSOR_ATTN_Q_A, "weight", i), {n_embd, q_lora_rank}, flags);
+            layer.wq_b = create_tensor(tn(LLM_TENSOR_ATTN_Q_B, "weight", i), {q_lora_rank, n_head * n_embd_head_k_mla}, flags);
         } else {
-            layer.wq = create_tensor(tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_head * n_embd_head_k_mla}, 0);
+            layer.wq = create_tensor(tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_head * n_embd_head_k_mla}, flags);
         }
 
-        layer.wkv_a_mqa = create_tensor(tn(LLM_TENSOR_ATTN_KV_A_MQA, "weight", i), {n_embd, kv_lora_rank + n_embd_head_qk_rope}, 0);
+        layer.wkv_a_mqa = create_tensor(tn(LLM_TENSOR_ATTN_KV_A_MQA, "weight", i), {n_embd, kv_lora_rank + n_embd_head_qk_rope}, flags);
 
         // note: only old legacy GGUF files will have the unsplit wkv_b tensor in
         if (is_mla) {
-            layer.wk_b = create_tensor(tn(LLM_TENSOR_ATTN_K_B, "weight", i), {n_embd_head_qk_nope, kv_lora_rank, n_head}, 0);
-            layer.wv_b = create_tensor(tn(LLM_TENSOR_ATTN_V_B, "weight", i), {kv_lora_rank, n_embd_head_v_mla, n_head}, 0);
+            layer.wk_b = create_tensor(tn(LLM_TENSOR_ATTN_K_B, "weight", i), {n_embd_head_qk_nope, kv_lora_rank, n_head}, flags);
+            layer.wv_b = create_tensor(tn(LLM_TENSOR_ATTN_V_B, "weight", i), {kv_lora_rank, n_embd_head_v_mla, n_head}, flags);
         } else {
-            layer.wkv_b = create_tensor(tn(LLM_TENSOR_ATTN_KV_B, "weight", i), {kv_lora_rank, n_head * (n_embd_head_qk_nope + n_embd_head_v_mla)}, 0);
+            layer.wkv_b = create_tensor(tn(LLM_TENSOR_ATTN_KV_B, "weight", i), {kv_lora_rank, n_head * (n_embd_head_qk_nope + n_embd_head_v_mla)}, flags);
         }
 
-        layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_head * n_embd_head_v_mla, n_embd}, 0);
+        layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_head * n_embd_head_v_mla, n_embd}, flags);
 
-        layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0);
+        layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, flags);
 
         if (i < (int) hparams.n_layer_dense_lead) {
-            layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd,   n_ff}, 0);
-            layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), {  n_ff, n_embd}, 0);
-            layer.ffn_up   = create_tensor(tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd,   n_ff}, 0);
+            layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd,   n_ff}, flags);
+            layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), {  n_ff, n_embd}, flags);
+            layer.ffn_up   = create_tensor(tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd,   n_ff}, flags);
         } else {
-            layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert}, 0);
-            layer.ffn_exp_probs_b = create_tensor(tn(LLM_TENSOR_FFN_EXP_PROBS_B, "bias", i), {n_expert}, TENSOR_NOT_REQUIRED);
+            layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert}, flags);
+            layer.ffn_exp_probs_b = create_tensor(tn(LLM_TENSOR_FFN_EXP_PROBS_B, "bias", i), {n_expert}, TENSOR_NOT_REQUIRED | flags);
 
             if (n_expert == 0) {
                 throw std::runtime_error("n_expert must be > 0");
@@ -128,21 +144,281 @@ void llama_model_deepseek2::load_arch_tensors(llama_model_loader &) {
             }
 
             // MoE branch
-            layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), {n_ff_exp,   n_embd, n_expert}, 0);
-            create_tensor_gate_up_exps(layer, i, n_embd, n_ff_exp, n_expert, 0);
+            layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), {n_ff_exp,   n_embd, n_expert}, flags);
+            create_tensor_gate_up_exps(layer, i, n_embd, n_ff_exp, n_expert, flags);
 
             // Shared expert branch
-            layer.ffn_gate_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_SHEXP, "weight", i), {n_embd, n_ff_exp * n_expert_shared}, 0);
-            layer.ffn_down_shexp = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "weight", i), {        n_ff_exp * n_expert_shared, n_embd}, 0);
-            layer.ffn_up_shexp   = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP,   "weight", i), {n_embd, n_ff_exp * n_expert_shared}, 0);
+            layer.ffn_gate_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_SHEXP, "weight", i), {n_embd, n_ff_exp * n_expert_shared}, flags);
+            layer.ffn_down_shexp = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "weight", i), {        n_ff_exp * n_expert_shared, n_embd}, flags);
+            layer.ffn_up_shexp   = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP,   "weight", i), {n_embd, n_ff_exp * n_expert_shared}, flags);
+        }
+
+        // NextN/MTP tensors
+        if (i >= n_layer) {
+            layer.nextn.eh_proj          = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ, "weight", i), { 2 * n_embd, n_embd }, mtp_flags);
+            layer.nextn.enorm            = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM, "weight", i), { n_embd }, mtp_flags);
+            layer.nextn.hnorm            = create_tensor(tn(LLM_TENSOR_NEXTN_HNORM, "weight", i), { n_embd }, mtp_flags);
+            layer.nextn.embed_tokens     = create_tensor(tn(LLM_TENSOR_NEXTN_EMBED_TOKENS, "weight", i), { n_embd, n_vocab }, TENSOR_NOT_REQUIRED | flags);
+            layer.nextn.shared_head_head = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_HEAD, "weight", i), { n_embd, n_vocab }, TENSOR_NOT_REQUIRED | flags);
+            layer.nextn.shared_head_norm = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_NORM, "weight", i), { n_embd }, TENSOR_NOT_REQUIRED | flags);
         }
     }
 }
 
 std::unique_ptr<llm_graph_context> llama_model_deepseek2::build_arch_graph(const llm_graph_params & params) const {
+    if (params.gtype == LLM_GRAPH_TYPE_DECODER_MTP) {
+        return std::make_unique<graph_mtp>(*this, params);
+    }
     return std::make_unique<graph>(*this, params);
 }
 
+llama_model_deepseek2::graph_mtp::graph_mtp(const llama_model & model, const llm_graph_params & params) :
+    llm_graph_context(params) {
+    GGML_ASSERT(hparams.n_layer_nextn > 0 && "GLM4 MTP requires n_layer_nextn > 0");
+    GGML_ASSERT(hparams.n_layer_nextn == 1 && "GLM4 MTP currently only supports a single MTP block");
+    GGML_ASSERT(hparams.is_mla() && "GLM4 MTP requires MLA");
+    GGML_ASSERT(hparams.f_attn_temp_scale == 0.0f && "GLM4 MTP does not support attention temperature scaling");
+
+    // The appended MTP block is stored immediately after the main decoder layers.
+    const int il = hparams.n_layer();
+    const auto & layer = model.layers[il];
+
+    GGML_ASSERT(layer.nextn.eh_proj && "MTP block missing nextn.eh_proj");
+    GGML_ASSERT(layer.nextn.enorm   && "MTP block missing nextn.enorm");
+    GGML_ASSERT(layer.nextn.hnorm   && "MTP block missing nextn.hnorm");
+
+    GGML_ASSERT((uint32_t) il >= hparams.n_layer_dense_lead && "GLM4 MTP block expected to use MoE FFN");
+
+    const int64_t n_embd_head_k_mla   = hparams.n_embd_head_k_mla();
+    const int64_t n_embd_head_qk_rope = hparams.n_rot();
+    const int64_t n_embd_head_qk_nope = n_embd_head_k_mla - n_embd_head_qk_rope;
+    const int64_t kv_lora_rank        = hparams.n_lora_kv;
+
+    GGML_ASSERT(n_embd_head_qk_nope >= 1);
+    GGML_ASSERT(hparams.n_lora_q > 0);
+    GGML_ASSERT(layer.wq_a);
+    GGML_ASSERT(layer.attn_q_a_norm);
+    GGML_ASSERT(layer.wq_b);
+    GGML_ASSERT(layer.wkv_a_mqa);
+    GGML_ASSERT(layer.attn_kv_a_norm);
+    GGML_ASSERT(layer.wk_b);
+
+    const bool has_split_exps =
+            layer.ffn_up_exps   != nullptr &&
+            layer.ffn_gate_exps != nullptr;
+
+    const bool has_fused_exps = layer.ffn_gate_up_exps != nullptr;
+
+    GGML_ASSERT(has_split_exps || has_fused_exps);
+    GGML_ASSERT(layer.ffn_norm);
+    GGML_ASSERT(layer.ffn_gate_inp);
+    GGML_ASSERT(layer.ffn_down_exps);
+    GGML_ASSERT(layer.ffn_gate_shexp);
+    GGML_ASSERT(layer.ffn_down_shexp);
+    GGML_ASSERT(layer.ffn_up_shexp);
+
+    auto inp = std::make_unique<llm_graph_input_embd_h>(hparams.n_embd);
+
+    inp->tokens = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_tokens);
+    ggml_set_input(inp->tokens);
+
+    inp->embd = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, hparams.n_embd_inp(), n_tokens);
+    ggml_set_input(inp->embd);
+
+    ggml_tensor * tok_embd;
+    if (ubatch.token) {
+        ggml_tensor * tok_embd_w = layer.nextn.embed_tokens
+                ? layer.nextn.embed_tokens
+                : model.tok_embd;
+
+        tok_embd = ggml_get_rows(ctx0, tok_embd_w, inp->tokens);
+    } else {
+        tok_embd = inp->embd;
+    }
+    cb(tok_embd, "mtp_tok_embd", il);
+
+    inp->h = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, hparams.n_embd, n_tokens);
+    ggml_set_input(inp->h);
+    ggml_set_name(inp->h, "mtp_h_input");
+
+    ggml_tensor * h_embd = inp->h;
+
+    res->add_input(std::move(inp));
+
+    ggml_tensor * inp_pos     = build_inp_pos();
+    ggml_tensor * inp_out_ids = build_inp_out_ids();
+
+    auto * inp_attn_k = build_attn_inp_k();
+
+    ggml_tensor * h_norm = build_norm(h_embd, layer.nextn.hnorm, nullptr, LLM_NORM_RMS, il);
+    cb(h_norm, "mtp_hnorm", il);
+
+    ggml_tensor * e_norm = build_norm(tok_embd, layer.nextn.enorm, nullptr, LLM_NORM_RMS, il);
+    cb(e_norm, "mtp_enorm", il);
+
+    ggml_tensor * concat = ggml_concat(ctx0, e_norm, h_norm, 0);
+    cb(concat, "mtp_concat", il);
+
+    ggml_tensor * cur = build_lora_mm(layer.nextn.eh_proj, concat, layer.nextn.eh_proj_s);
+    cb(cur, "mtp_eh_proj", il);
+
+    ggml_tensor * inpSA = cur;
+
+    cur = build_norm(cur, layer.attn_norm, nullptr, LLM_NORM_RMS, il);
+    cb(cur, "mtp_attn_norm", il);
+
+    ggml_tensor * q = ggml_mul_mat(ctx0, layer.wq_a, cur);
+    cb(q, "mtp_q_a", il);
+
+    q = build_norm(q, layer.attn_q_a_norm, nullptr, LLM_NORM_RMS, il);
+    cb(q, "mtp_q_a_norm", il);
+
+    q = ggml_mul_mat(ctx0, layer.wq_b, q);
+    cb(q, "mtp_q_b", il);
+
+    ggml_tensor * q_nope =
+        ggml_view_3d(ctx0, q, n_embd_head_qk_nope, n_head, n_tokens,
+                ggml_row_size(q->type, n_embd_head_k_mla),
+                ggml_row_size(q->type, n_embd_head_k_mla) * n_head, 0);
+    cb(q_nope, "mtp_q_nope", il);
+
+    ggml_tensor * q_pe =
+        ggml_view_3d(ctx0, q, n_embd_head_qk_rope, n_head, n_tokens,
+                ggml_row_size(q->type, n_embd_head_k_mla),
+                ggml_row_size(q->type, n_embd_head_k_mla) * n_head,
+                ggml_row_size(q->type, n_embd_head_qk_nope));
+    cb(q_pe, "mtp_q_pe", il);
+
+    ggml_tensor * kv_cmpr_pe = ggml_mul_mat(ctx0, layer.wkv_a_mqa, cur);
+    cb(kv_cmpr_pe, "mtp_kv_cmpr_pe", il);
+
+    ggml_tensor * kv_cmpr =
+        ggml_view_2d(ctx0, kv_cmpr_pe, kv_lora_rank, n_tokens,
+                ggml_row_size(kv_cmpr_pe->type, kv_lora_rank + n_embd_head_qk_rope), 0);
+    cb(kv_cmpr, "mtp_kv_cmpr", il);
+
+    ggml_tensor * k_pe =
+        ggml_view_3d(ctx0, kv_cmpr_pe, n_embd_head_qk_rope, 1, n_tokens,
+                ggml_row_size(kv_cmpr_pe->type, kv_lora_rank + n_embd_head_qk_rope),
+                ggml_row_size(kv_cmpr_pe->type, kv_lora_rank + n_embd_head_qk_rope),
+                ggml_row_size(kv_cmpr_pe->type, kv_lora_rank));
+    cb(k_pe, "mtp_k_pe", il);
+
+    kv_cmpr = build_norm(kv_cmpr, layer.attn_kv_a_norm, nullptr, LLM_NORM_RMS, il);
+    cb(kv_cmpr, "mtp_kv_cmpr_norm", il);
+
+    GGML_ASSERT(ext_factor >= 0.0f);
+
+    const float attn_factor_org =
+            attn_factor * (1.0f + 0.1f * logf(1.0f / freq_scale));
+
+    const float mscale =
+            attn_factor_org * (1.0f + 0.1f * hparams.rope_yarn_log_mul * logf(1.0f / freq_scale));
+
+    const float kq_scale =
+            1.0f * mscale * mscale / sqrtf(float(n_embd_head_k_mla));
+
+    q_pe = ggml_rope_ext(ctx0, q_pe, inp_pos, nullptr,
+            n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
+            ext_factor, attn_factor, beta_fast, beta_slow);
+    cb(q_pe, "mtp_q_pe_rope", il);
+
+    k_pe = ggml_rope_ext(ctx0, k_pe, inp_pos, nullptr,
+            n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
+            ext_factor, attn_factor, beta_fast, beta_slow);
+    cb(k_pe, "mtp_k_pe_rope", il);
+
+    q_nope = ggml_permute(ctx0, q_nope, 0, 2, 1, 3);
+    cb(q_nope, "mtp_q_nope_perm", il);
+
+    ggml_tensor * q_nope_absorbed = ggml_mul_mat(ctx0, layer.wk_b, q_nope);
+    cb(q_nope_absorbed, "mtp_q_nope_absorbed", il);
+
+    q_nope_absorbed = ggml_permute(ctx0, q_nope_absorbed, 0, 2, 1, 3);
+    cb(q_nope_absorbed, "mtp_q_nope_absorbed_perm", il);
+
+    ggml_tensor * Qcur = ggml_concat(ctx0, q_nope_absorbed, q_pe, 0);
+    cb(Qcur, "mtp_Qcur", il);
+
+    kv_cmpr = ggml_reshape_3d(ctx0, kv_cmpr, hparams.n_lora_kv, 1, n_tokens);
+    cb(kv_cmpr, "mtp_kv_cmpr_reshape", il);
+
+    ggml_tensor * Kcur = ggml_concat(ctx0, kv_cmpr, k_pe, 0);
+    cb(Kcur, "mtp_Kcur", il);
+
+    ggml_tensor * Vcur = kv_cmpr;
+    cb(Vcur, "mtp_Vcur", il);
+
+    cur = build_attn(inp_attn_k,
+            layer.wo, nullptr, layer.wo_s,
+            Qcur, Kcur, Vcur, nullptr, nullptr, layer.wv_b, kq_scale, il);
+    cb(cur, "mtp_attn_out", il);
+
+    ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);
+    cb(ffn_inp, "mtp_ffn_inp", il);
+
+    cur = build_norm(ffn_inp, layer.ffn_norm, nullptr, LLM_NORM_RMS, il);
+    cb(cur, "mtp_ffn_norm", il);
+
+    ggml_tensor * moe_out = build_moe_ffn(cur,
+            layer.ffn_gate_inp,
+            layer.ffn_up_exps,
+            layer.ffn_gate_exps,
+            layer.ffn_down_exps,
+            layer.ffn_exp_probs_b,
+            n_expert, n_expert_used,
+            LLM_FFN_SILU, hparams.expert_weights_norm,
+            hparams.expert_weights_scale,
+            (llama_expert_gating_func_type) hparams.expert_gating_func,
+            il,
+            nullptr,
+            layer.ffn_gate_up_exps);
+    cb(moe_out, "mtp_ffn_moe_out", il);
+
+    ggml_tensor * ffn_shexp = build_ffn(cur,
+            layer.ffn_up_shexp, nullptr, nullptr,
+            layer.ffn_gate_shexp, nullptr, nullptr,
+            layer.ffn_down_shexp, nullptr, nullptr,
+            nullptr, LLM_FFN_SILU, LLM_FFN_PAR, il);
+    cb(ffn_shexp, "mtp_ffn_shexp", il);
+
+    cur = ggml_add(ctx0, moe_out, ffn_shexp);
+    cb(cur, "mtp_ffn_out", il);
+
+    cur = ggml_add(ctx0, cur, ffn_inp);
+    cb(cur, "mtp_post_ffn", il);
+
+    ggml_tensor * head_norm_w = layer.nextn.shared_head_norm
+            ? layer.nextn.shared_head_norm
+            : model.output_norm;
+    GGML_ASSERT(head_norm_w && "GLM4 MTP: missing both nextn.shared_head_norm and output_norm");
+
+    cur = build_norm(cur, head_norm_w, nullptr, LLM_NORM_RMS, -1);
+    cb(cur, "h_nextn", -1);
+    res->t_h_nextn = cur;
+
+    if (inp_out_ids) {
+        cur = ggml_get_rows(ctx0, cur, inp_out_ids);
+    }
+    cb(cur, "mtp_shared_head_norm", -1);
+
+    ggml_tensor * head_w = layer.nextn.shared_head_head
+            ? layer.nextn.shared_head_head
+            : model.output;
+
+    ggml_tensor * head_s = layer.nextn.shared_head_head
+            ? layer.nextn.shared_head_head_s
+            : model.output_s;
+
+    GGML_ASSERT(head_w && "GLM4 MTP: missing LM head (nextn.shared_head_head or model.output)");
+
+    cur = build_lora_mm(head_w, cur, head_s);
+    cb(cur, "result_output", -1);
+
+    res->t_logits = cur;
+    ggml_build_forward_expand(gf, cur);
+}
+
 llama_model_deepseek2::graph::graph(const llama_model & model, const llm_graph_params & params) :
     llm_graph_context(params) {
     // lite variants include DeepSeek-V2-Lite, GigaChat3-10B-A1.8B
@@ -365,7 +641,7 @@ llama_model_deepseek2::graph::graph(const llama_model & model, const llm_graph_p
                             Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale, il);
             }
         }
-        if (il == n_layer - 1 && inp_out_ids) {
+        if (il == n_layer - 1 && inp_out_ids && (!cparams.embeddings_nextn || cparams.embeddings_nextn_masked)) {
             cur   = ggml_get_rows(ctx0, cur, inp_out_ids);
             inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids);
         }
@@ -425,6 +701,13 @@ llama_model_deepseek2::graph::graph(const llama_model & model, const llm_graph_p
 
     cur = build_norm(cur, model.output_norm, NULL, LLM_NORM_RMS, -1);
 
+    cb(cur, "h_nextn", -1);
+    res->t_h_nextn = cur;
+
+    if (cparams.embeddings_nextn && !cparams.embeddings_nextn_masked && inp_out_ids) {
+        cur = ggml_get_rows(ctx0, cur, inp_out_ids);
+    }
+
     cb(cur, "result_norm", -1);
     res->t_embd = cur;
 

src/models/deepseek4.cpp

@@ -114,7 +114,9 @@ void llama_model_deepseek4::load_arch_tensors(llama_model_loader & ml) {
         layer.wq_b          = create_tensor(tn(LLM_TENSOR_ATTN_Q_B,      "weight", i), {q_lora_rank, n_head * n_embd_head}, flags);
         layer.wkv           = create_tensor(tn(LLM_TENSOR_ATTN_KV,       "weight", i), {n_embd, n_embd_head}, flags);
         layer.attn_kv_norm  = create_tensor(tn(LLM_TENSOR_ATTN_KV_NORM,  "weight", i), {n_embd_head}, flags);
-        layer.wo_a          = create_tensor(tn(LLM_TENSOR_ATTN_OUT_A,    "weight", i), {n_head * n_embd_head / o_groups, o_lora_rank * o_groups}, flags);
+        // for wo_a, the shape in the file is (n_head * n_embd_head / o_groups, o_lora_rank*o_groups)
+        // so we reshape here, to avoid reshaping the tensor in the graph
+        layer.wo_a          = create_tensor(tn(LLM_TENSOR_ATTN_OUT_A,    "weight", i), {n_head * n_embd_head / o_groups, o_lora_rank, o_groups}, flags | TENSOR_ALLOW_RESHAPE);
         layer.wo_b          = create_tensor(tn(LLM_TENSOR_ATTN_OUT_B,    "weight", i), {o_groups * o_lora_rank, n_embd}, flags);
 
         layer.hc_attn_fn    = create_tensor(tn(LLM_TENSOR_HC_ATTN_FN,    "weight", i), {hc_dim, hc_mix_dim}, flags);
@@ -1258,7 +1260,7 @@ ggml_tensor * llama_model_deepseek4::graph::build_attention_impl(
 
     out = ggml_reshape_3d(ctx0, out, o_group_dim, n_groups, nt);
     out = ggml_permute(ctx0, out, 0, 2, 1, 3);
-    ggml_tensor * oa = ggml_mul_mat(ctx0, ggml_reshape_3d(ctx0, layer.wo_a, layer.wo_a->ne[0], o_lora_rank, n_groups), out);
+    ggml_tensor * oa = ggml_mul_mat(ctx0, layer.wo_a, out);
     cb(oa, "attn_wo_a", il);
     oa = ggml_permute(ctx0, oa, 0, 2, 1, 3);
     oa = ggml_cont_2d(ctx0, oa, o_lora_rank*n_groups, nt);

src/models/dflash.cpp

@@ -125,7 +125,7 @@ void llama_model_dflash::load_arch_tensors(llama_model_loader &) {
             layer.wq_b          = create_tensor(tn(LLM_TENSOR_ATTN_Q_B,      "weight", i), {q_lora_rank, n_head * n_embd_head}, 0);
             layer.wkv           = create_tensor(tn(LLM_TENSOR_ATTN_KV,       "weight", i), {n_embd, n_embd_head}, 0);
             layer.attn_kv_norm  = create_tensor(tn(LLM_TENSOR_ATTN_KV_NORM,  "weight", i), {n_embd_head}, 0);
-            layer.wo_a          = create_tensor(tn(LLM_TENSOR_ATTN_OUT_A,    "weight", i), {n_head * n_embd_head / o_groups, o_lora_rank * o_groups}, 0);
+            layer.wo_a          = create_tensor(tn(LLM_TENSOR_ATTN_OUT_A,    "weight", i), {n_head * n_embd_head / o_groups, o_lora_rank, o_groups}, TENSOR_ALLOW_RESHAPE);
             layer.wo_b          = create_tensor(tn(LLM_TENSOR_ATTN_OUT_B,    "weight", i), {o_groups * o_lora_rank, n_embd}, 0);
 
             layer.hc_attn_fn    = create_tensor(tn(LLM_TENSOR_HC_ATTN_FN,    "weight", i), {hc_dim, hc_mix_dim}, 0);

src/models/models.h

@@ -596,6 +596,11 @@ struct llama_model_qwen3vlmoe : public llama_model_base {
 };
 
 
+struct llama_model_qwen3tts : public llama_model_qwen3vl {
+    llama_model_qwen3tts(const struct llama_model_params & params) : llama_model_qwen3vl(params) {}
+};
+
+
 struct llama_model_phi2 : public llama_model_base {
     llama_model_phi2(const struct llama_model_params & params) : llama_model_base(params) {}
     void load_arch_hparams(llama_model_loader & ml) override;
@@ -1084,6 +1089,10 @@ struct llama_model_deepseek2 : public llama_model_base {
         graph(const llama_model & model, const llm_graph_params & params);
     };
 
+    struct graph_mtp : public llm_graph_context {
+        graph_mtp(const llama_model & model, const llm_graph_params & params);
+    };
+
     std::unique_ptr<llm_graph_context> build_arch_graph(const llm_graph_params & params) const override;
 };
 

src/models/qwen3tts.cpp

@@ -0,0 +1,3 @@
+#include "models.h"
+
+// llama_model_qwen3tts reuses llama_model_qwen3vl's hparams/tensors/graph logic

src/models/qwen3vl.cpp

@@ -16,11 +16,16 @@ void llama_model_qwen3vl::load_arch_hparams(llama_model_loader & ml) {
 void llama_model_qwen3vl::load_arch_tensors(llama_model_loader &) {
     LLAMA_LOAD_LOCALS;
 
+    int64_t n_vocab_out = n_vocab;
+    if (arch == LLM_ARCH_QWEN3TTS) {
+        n_vocab_out = 3072;
+    }
+
     tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
 
     // output
     output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
-    output      = create_tensor(tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED);
+    output      = create_tensor(tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab_out}, TENSOR_NOT_REQUIRED);
     // if output is NULL, init from the input tok embed
     if (output == NULL) {
         output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
@@ -166,6 +171,24 @@ llama_model_qwen3vl::graph::graph(const llama_model & model, const llm_graph_par
     // lm_head
     cur = build_lora_mm(model.output, cur, model.output_s);
 
+    int64_t n_vocab_in  = model.tok_embd->ne[1];
+    int64_t n_vocab_out = model.output->ne[1];
+    if (n_vocab_in > n_vocab_out) {
+        // case: Qwen3TTS model with codec_head as output
+        GGML_ASSERT(model.output_norm);
+        int64_t pad = n_vocab_in - n_vocab_out;
+
+        // using this trick to get a scalar -inf tensor to pad the output
+        ggml_tensor * neg_inf = ggml_scale_bias(ctx0,
+                ggml_view_1d(ctx0, model.output_norm, 1, 0),
+                0.0f, -INFINITY);
+        neg_inf = ggml_repeat_4d(ctx0, neg_inf, pad, cur->ne[1], 1, 1);
+        cur = ggml_concat(ctx0, neg_inf, cur, 0); // [padded .. n_vocab_out, n_stream]
+
+    } else if (n_vocab_in < n_vocab_out) {
+        GGML_ABORT("invalid case");
+    }
+
     cb(cur, "result_output", -1);
     res->t_logits = cur;
 

tests/CMakeLists.txt

@@ -258,6 +258,9 @@ llama_build_and_test(test-thread-safety.cpp ARGS -m "${MODEL_DEST}" -ngl 99 -p "
 set_tests_properties(test-thread-safety PROPERTIES FIXTURES_REQUIRED test-download-model)
 
 llama_build_and_test(test-arg-parser.cpp)
+llama_build_and_test(test-model-resolution.cpp)
+# the test serves its repos from an httplib server, and the library links it privately
+target_link_libraries(test-model-resolution PRIVATE cpp-httplib)
 
 if (NOT LLAMA_SANITIZE_ADDRESS AND NOT GGML_SCHED_NO_REALLOC)
   # TODO: repair known memory leaks

tests/test-backend-sampler.cpp

@@ -823,6 +823,7 @@ enum class penalties_position {
 static void add_filter_and_penalties(
         llama_sampler * chain,
         const sampler_init_fn & init_filter,
+        int32_t n_vocab,
         int32_t penalty_last_n,
         float penalty_repeat,
         float penalty_freq,
@@ -830,7 +831,7 @@ static void add_filter_and_penalties(
         penalties_position position) {
     const auto add_penalties = [&]() {
         llama_sampler_chain_add(chain, llama_sampler_init_penalties(
-                    penalty_last_n, penalty_repeat, penalty_freq, penalty_present));
+                    n_vocab, penalty_last_n, penalty_repeat, penalty_freq, penalty_present));
     };
 
     if (position == penalties_position::before_filter) {
@@ -1006,7 +1007,7 @@ static sampler_comparison_output run_penalties_comparison(
     const std::vector<float> raw_logits = decode_raw_logits(params, prompt);
     const auto add_samplers = [&](llama_sampler * chain) {
         llama_sampler_chain_add(chain, llama_sampler_init_penalties(
-                    penalty_last_n, penalty_repeat, penalty_freq, penalty_present));
+                    llama_vocab_n_tokens(vocab), penalty_last_n, penalty_repeat, penalty_freq, penalty_present));
     };
     const auto accept_history = [&](llama_sampler * chain) {
         accept_prompt(chain, vocab, prompt);
@@ -1105,7 +1106,7 @@ static void compare_top_k_penalties_logits(
     GGML_ASSERT(excluded_history_token != LLAMA_TOKEN_NULL);
 
     const auto add_samplers = [&](llama_sampler * chain) {
-        add_filter_and_penalties(chain, init_top_k,
+        add_filter_and_penalties(chain, init_top_k, n_vocab,
                 penalty_last_n, penalty_repeat, penalty_freq, penalty_present, position);
     };
 
@@ -1190,7 +1191,7 @@ static void compare_masking_penalties_logits(
     GGML_ASSERT(masked_token != LLAMA_TOKEN_NULL);
 
     const auto add_samplers = [&](llama_sampler * chain) {
-        add_filter_and_penalties(chain, init_filter,
+        add_filter_and_penalties(chain, init_filter, n_vocab,
                 penalty_last_n, penalty_repeat, penalty_freq, penalty_present, position);
     };
     auto accept_history = [&](llama_sampler * smpl) {
@@ -1218,7 +1219,7 @@ static void compare_masking_penalties_logits(
             GGML_ASSERT(fabsf(expected_logits.at(penalized_token) - raw_logits[penalized_token]) > 1e-6f);
         } else {
             llama_sampler_ptr penalties(llama_sampler_init_penalties(
-                        penalty_last_n, penalty_repeat, penalty_freq, penalty_present));
+                        n_vocab, penalty_last_n, penalty_repeat, penalty_freq, penalty_present));
             accept_history(penalties.get());
             const std::unordered_map<llama_token, float> penalized_logits =
                 map_logits(apply_cpu_sampler(raw_logits, penalties.get()));

tests/test-chat.cpp

@@ -3987,6 +3987,7 @@ static void test_template_output_peg_parsers(bool detailed_debug) {
             .expect_tool_calls({
                 { "special_function", R"({"arg1": 1})", {} },
             })
+            .expect_reconstruction()
             .run();
 
         // Tool call with negative number
@@ -4212,6 +4213,7 @@ static void test_template_output_peg_parsers(bool detailed_debug) {
             .expect_tool_calls({
                 { "special_function", R"({"arg1": 1})", {} },
             })
+            .expect_reconstruction()
             .run();
 
         // Tool call with multiple params (mixed types)
@@ -4268,6 +4270,24 @@ static void test_template_output_peg_parsers(bool detailed_debug) {
             .run();
     }
 
+    {
+        // The DSML separator belongs to the tool call block, not assistant content.
+        auto tst = peg_tester("models/templates/deepseek-ai-DeepSeek-V4-Flash-0731.jinja", detailed_debug);
+        tst.test(
+               "\n\n"
+               "<｜DSML｜tool_calls>\n"
+               "<｜DSML｜invoke name=\"special_function\">\n"
+               "<｜DSML｜parameter name=\"arg1\" string=\"false\">1</｜DSML｜parameter>\n"
+               "</｜DSML｜invoke>\n"
+               "</｜DSML｜tool_calls>")
+            .enable_thinking(false)
+            .reasoning_format(COMMON_REASONING_FORMAT_DEEPSEEK)
+            .tools({ special_function_tool })
+            .expect(message_assist_call)
+            .expect_reconstruction()
+            .run();
+    }
+
     // GLM-4.6 tests - format: <tool_call>function_name\n<arg_key>...</arg_key>\n<arg_value>...</arg_value>\n</tool_call>
     {
         auto tst = peg_tester("models/templates/GLM-4.6.jinja", detailed_debug);
@@ -6359,6 +6379,7 @@ static void test_template_generation_prompt() {
         std::vector<common_chat_msg> messages;
         bool                         add_generation_prompt  = true;
         common_chat_continuation     continue_final_message = COMMON_CHAT_CONTINUATION_NONE;
+        bool                         enable_thinking        = true;
     };
 
     auto basic = [&]() {
@@ -6390,6 +6411,7 @@ static void test_template_generation_prompt() {
         inputs.messages               = opts.messages;
         inputs.add_generation_prompt  = opts.add_generation_prompt;
         inputs.continue_final_message = opts.continue_final_message;
+        inputs.enable_thinking        = opts.enable_thinking;
 
         auto params = common_chat_templates_apply(tmpls.get(), inputs);
 
@@ -6488,6 +6510,156 @@ static void test_template_generation_prompt() {
         check(tmpls, continuation_reasoning(), "<｜Assistant｜><think>I'm");
     }
 
+    const std::string deepseek_v4_reasoning_effort_max = "Reasoning Effort: Absolute maximum";
+    const std::string deepseek_v4_flash_0731_reasoning_effort_max = "Reasoning Effort: Beyond maximum";
+
+    {
+        auto tmpls = read_templates("models/templates/deepseek-ai-DeepSeek-V4.jinja");
+        check(tmpls, basic(),                  "<｜Assistant｜><think>");
+        check(tmpls, continuation_content(),   "<｜Assistant｜><think>I'm thinking</think>Hello, ");
+        check(tmpls, continuation_reasoning(), "<｜Assistant｜><think>I'm");
+
+        auto continuation_content_no_thinking = continuation_content();
+        continuation_content_no_thinking.messages = { system_msg, message_user, simple_assist_msg("Hello, ") };
+        continuation_content_no_thinking.enable_thinking = false;
+        check(tmpls, continuation_content_no_thinking, "<｜Assistant｜></think>Hello, ");
+
+        common_chat_templates_inputs max_inputs;
+        max_inputs.messages = { system_msg, message_user };
+        max_inputs.chat_template_kwargs["reasoning_effort"] = R"("max")";
+        auto max_params = common_chat_templates_apply(tmpls.get(), max_inputs);
+        assert_contains(max_params.prompt, deepseek_v4_reasoning_effort_max);
+
+        auto high_inputs = max_inputs;
+        high_inputs.chat_template_kwargs["reasoning_effort"] = R"("high")";
+        auto high_params = common_chat_templates_apply(tmpls.get(), high_inputs);
+        assert_not_contains(high_params.prompt, deepseek_v4_reasoning_effort_max);
+
+        auto low_inputs = max_inputs;
+        low_inputs.chat_template_kwargs["reasoning_effort"] = R"("low")";
+        auto low_params = common_chat_templates_apply(tmpls.get(), low_inputs);
+        assert_not_contains(low_params.prompt, deepseek_v4_reasoning_effort_max);
+
+        common_chat_templates_inputs default_effort_inputs;
+        default_effort_inputs.messages = { system_msg, message_user };
+        auto default_effort_params = common_chat_templates_apply(tmpls.get(), default_effort_inputs);
+        assert_not_contains(default_effort_params.prompt, deepseek_v4_reasoning_effort_max);
+
+        auto non_thinking_max_inputs = max_inputs;
+        non_thinking_max_inputs.enable_thinking = false;
+        auto non_thinking_max_params = common_chat_templates_apply(tmpls.get(), non_thinking_max_inputs);
+        assert_not_contains(non_thinking_max_params.prompt, deepseek_v4_reasoning_effort_max);
+
+        common_chat_templates_inputs response_format_inputs;
+        response_format_inputs.messages = { system_msg, message_user };
+        response_format_inputs.tools = { get_time_tool };
+        response_format_inputs.json_schema =
+            R"({"type":"object","properties":{"answer":{"type":"string"}}})";
+        auto response_format_params = common_chat_templates_apply(tmpls.get(), response_format_inputs);
+        const auto tools_pos = response_format_params.prompt.find("## Tools");
+        const auto response_format_pos = response_format_params.prompt.find(
+            "## Response Format:\n\nYou MUST strictly adhere to the following schema to reply:\n");
+        if (tools_pos == std::string::npos || response_format_pos == std::string::npos || tools_pos > response_format_pos) {
+            LOG_ERR("Expected response format after tools\nActual: %s\n", response_format_params.prompt.c_str());
+            common_log_flush(common_log_main());
+            throw std::runtime_error("Test failed");
+        }
+        assert_contains(response_format_params.prompt, R"("answer": {"type": "string"})");
+
+        response_format_inputs.json_schema = "{}";
+        auto json_object_params = common_chat_templates_apply(tmpls.get(), response_format_inputs);
+        assert_contains(json_object_params.prompt,
+                        "## Response Format:\n\nYou MUST strictly adhere to the following schema to reply:\n{}");
+
+        common_chat_msg assistant_history;
+        assistant_history.role              = "assistant";
+        assistant_history.content           = "Previous answer";
+        assistant_history.reasoning_content = "Previous reasoning";
+
+        common_chat_msg user_followup;
+        user_followup.role    = "user";
+        user_followup.content = "Follow up";
+
+        common_chat_templates_inputs default_history_inputs;
+        default_history_inputs.messages = { message_user, assistant_history, user_followup };
+        auto default_history_params = common_chat_templates_apply(tmpls.get(), default_history_inputs);
+        assert_contains(default_history_params.prompt, "<｜Assistant｜></think>Previous answer");
+
+        auto drop_thinking_inputs = default_history_inputs;
+        drop_thinking_inputs.chat_template_kwargs["drop_thinking"] = "false";
+        auto drop_thinking_params = common_chat_templates_apply(tmpls.get(), drop_thinking_inputs);
+        assert_contains(drop_thinking_params.prompt, "<｜Assistant｜><think>Previous reasoning</think>Previous answer");
+
+        auto preserve_reasoning_inputs = default_history_inputs;
+        preserve_reasoning_inputs.chat_template_kwargs["preserve_reasoning"] = "true";
+        auto preserve_reasoning_params = common_chat_templates_apply(tmpls.get(), preserve_reasoning_inputs);
+        assert_contains(preserve_reasoning_params.prompt, "<｜Assistant｜><think>Previous reasoning</think>Previous answer");
+        assert_equals(true, common_chat_templates_get_caps(tmpls.get()).at("supports_preserve_reasoning"));
+
+        auto no_preserve_reasoning_inputs = default_history_inputs;
+        no_preserve_reasoning_inputs.chat_template_kwargs["preserve_reasoning"] = "false";
+        auto no_preserve_reasoning_params = common_chat_templates_apply(tmpls.get(), no_preserve_reasoning_inputs);
+        assert_contains(no_preserve_reasoning_params.prompt, "<｜Assistant｜></think>Previous answer");
+
+        common_chat_msg empty_tool_call = simple_assist_msg("", "", "empty_args", "{}");
+        common_chat_templates_inputs empty_tool_inputs;
+        empty_tool_inputs.messages = { message_user, empty_tool_call };
+        empty_tool_inputs.tools    = { empty_args_tool };
+        auto empty_tool_params = common_chat_templates_apply(tmpls.get(), empty_tool_inputs);
+        assert_contains(empty_tool_params.prompt,
+                        "<｜DSML｜invoke name=\"empty_args\">\n\n</｜DSML｜invoke>");
+    }
+
+    {
+        auto tmpls = read_templates("models/templates/deepseek-ai-DeepSeek-V4-Flash-0731.jinja");
+        check(tmpls, basic(),                  "<｜Assistant｜><think>");
+        check(tmpls, continuation_content(),   "<｜Assistant｜><think>I'm thinking</think>Hello, ");
+        check(tmpls, continuation_reasoning(), "<｜Assistant｜><think>I'm");
+
+        auto continuation_content_no_thinking = continuation_content();
+        continuation_content_no_thinking.messages = { system_msg, message_user, simple_assist_msg("Hello, ") };
+        continuation_content_no_thinking.enable_thinking = false;
+        check(tmpls, continuation_content_no_thinking, "<｜Assistant｜></think>Hello, ");
+
+        common_chat_templates_inputs high_inputs;
+        high_inputs.messages = { system_msg, message_user };
+        high_inputs.chat_template_kwargs["reasoning_effort"] = R"("high")";
+        auto high_params = common_chat_templates_apply(tmpls.get(), high_inputs);
+        assert_contains(high_params.prompt, deepseek_v4_reasoning_effort_max);
+
+        auto max_inputs = high_inputs;
+        max_inputs.chat_template_kwargs["reasoning_effort"] = R"("max")";
+        auto max_params = common_chat_templates_apply(tmpls.get(), max_inputs);
+        assert_contains(max_params.prompt, deepseek_v4_flash_0731_reasoning_effort_max);
+
+        auto low_inputs = high_inputs;
+        low_inputs.chat_template_kwargs["reasoning_effort"] = R"("low")";
+        auto low_params = common_chat_templates_apply(tmpls.get(), low_inputs);
+        assert_not_contains(low_params.prompt, deepseek_v4_reasoning_effort_max);
+        assert_not_contains(low_params.prompt, deepseek_v4_flash_0731_reasoning_effort_max);
+
+        common_chat_templates_inputs default_effort_inputs;
+        default_effort_inputs.messages = { system_msg, message_user };
+        auto default_effort_params = common_chat_templates_apply(tmpls.get(), default_effort_inputs);
+        assert_not_contains(default_effort_params.prompt, deepseek_v4_reasoning_effort_max);
+        assert_not_contains(default_effort_params.prompt, deepseek_v4_flash_0731_reasoning_effort_max);
+
+        auto non_thinking_max_inputs = max_inputs;
+        non_thinking_max_inputs.enable_thinking = false;
+        auto non_thinking_max_params = common_chat_templates_apply(tmpls.get(), non_thinking_max_inputs);
+        assert_not_contains(non_thinking_max_params.prompt, deepseek_v4_flash_0731_reasoning_effort_max);
+
+        common_chat_templates_inputs response_format_inputs;
+        response_format_inputs.messages = { system_msg, message_user };
+        response_format_inputs.tools = { get_time_tool };
+        response_format_inputs.json_schema =
+            R"({"type":"object","properties":{"answer":{"type":"string"}}})";
+        auto response_format_params = common_chat_templates_apply(tmpls.get(), response_format_inputs);
+        assert_contains(response_format_params.prompt,
+                        "## Response Format:\n\nYou MUST strictly adhere to the following schema to reply:\n");
+        assert_contains(response_format_params.prompt, R"("answer": {"type": "string"})");
+    }
+
     {
         auto tmpls = read_templates("models/templates/openbmb-MiniCPM5-1B.jinja");
         check(tmpls, basic(),                  "<|im_start|>assistant\n<think>\n");

tests/test-llama-archs.cpp

@@ -113,6 +113,8 @@ static gguf_context_ptr get_gguf_ctx(const llm_arch arch, const bool moe) {
         n_layer = 3;
     } else if (arch == LLM_ARCH_CHAMELEON) {
         n_vocab = 10240;
+    } else if (arch == LLM_ARCH_QWEN3TTS) {
+        n_vocab = 4096; // must be >= the hard-coded codec head size (3072)
     }
 
     const uint32_t n_embd_head = n_embd / n_head;

tests/test-model-resolution.cpp

@@ -0,0 +1,506 @@
+// tests the HF model resolution and the model handler assembly end-to-end on
+// synthetic repo listings: a local httplib server bound to the loopback
+// serves hardcoded HF API responses, so the real client, hf_cache, resolution
+// and CLI parsing run against them without external network access
+
+#include "arg.h"
+#include "common.h"
+#include "download.h"
+#include "http.h"
+#include "log.h"
+
+#include <nlohmann/json.hpp>
+
+#include <algorithm>
+#include <cstdio>
+#include <cstdlib>
+#include <filesystem>
+#include <map>
+#include <thread>
+#include <string>
+#include <vector>
+
+// the case and reordering being checked, printed with every failure
+static std::string g_context;
+
+// independent of NDEBUG, so the checks stay alive in Release builds
+#define REQUIRE(x) do {                                                         \
+    if (!(x)) {                                                                 \
+        fprintf(stderr, "%s:%d: [%s] REQUIRE(%s) failed\n",                     \
+                __FILE__, __LINE__, g_context.c_str(), #x);                     \
+        std::abort();                                                           \
+    }                                                                           \
+} while (0)
+
+#define REQUIRE_EQ(actual, expected) do {                                       \
+    if (!((actual) == (expected))) {                                            \
+        fprintf(stderr, "%s:%d: [%s] REQUIRE_EQ(%s, %s) failed\n  actual:   '%s'\n  expected: '%s'\n", \
+                __FILE__, __LINE__, g_context.c_str(), #actual, #expected,      \
+                std::string(actual).c_str(), std::string(expected).c_str());    \
+        std::abort();                                                           \
+    }                                                                           \
+} while (0)
+
+//
+// synthetic repos keyed by repo id, served over the loopback by a real
+// httplib server, so the tested code runs its own client and transport
+//
+
+static std::map<std::string, std::vector<std::string>> g_repos;
+
+static const char * COMMIT = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa";
+
+// the server lives in main, so its destructor runs before the static teardown
+// tears down the winsock state httplib brings in
+static void serve_repos(httplib::Server & server) {
+    server.Get(R"(/api/models/(.+)/refs)", [](const httplib::Request & req, httplib::Response & res) {
+        if (g_repos.count(req.matches[1])) {
+            res.set_content(nlohmann::json{{"branches", {{{"name", "main"}, {"targetCommit", COMMIT}}}}}.dump(),
+                            "application/json");
+        } else {
+            res.status = 404;
+        }
+    });
+    server.Get(R"(/api/models/(.+)/tree/.+)", [](const httplib::Request & req, httplib::Response & res) {
+        if (!g_repos.count(req.matches[1])) {
+            res.status = 404;
+            return;
+        }
+        auto files = nlohmann::json::array();
+        size_t i = 0;
+        for (const auto & p : g_repos[req.matches[1]]) {
+            char oid[41];
+            snprintf(oid, sizeof(oid), "%040lx", (unsigned long) ++i);
+            files.push_back({{"type", "file"}, {"path", p}, {"size", 1}, {"oid", oid}});
+        }
+        res.set_content(files.dump(), "application/json");
+    });
+}
+
+static common_params_model model_ref(const std::string & hf_repo, const std::string & hf_file = "") {
+    common_params_model m;
+    m.hf_repo = hf_repo;
+    m.hf_file = hf_file;
+    return m;
+}
+
+// the model cache is isolated under a temporary directory named after the
+// loopback port, so concurrent runs on a shared machine keep their own, and
+// the local path the handler wires for a file is snapshots/<commit>/<path>
+static std::filesystem::path cache_dir;
+
+static std::string cached(std::string repo_id, const std::string & path) {
+    string_replace_all(repo_id, "/", "--");
+    return (cache_dir / ("models--" + repo_id) / "snapshots" / COMMIT / path).string();
+}
+
+//
+// fixtures mimicking real repo layouts
+//
+
+// flat layout in the style of ggml-org/gemma-4-31B-it-GGUF
+static const std::vector<std::string> flat = {
+    "README.md",
+    "model-BF16.gguf",
+    "model-Q4_K_M.gguf",
+    "model-Q8_0.gguf",
+    "mmproj-model-BF16.gguf",
+    "mmproj-model-Q8_0.gguf",
+    "mtp-model-BF16.gguf",
+    "mtp-model-Q4_0.gguf",
+    "mtp-model-Q8_0.gguf",
+    "dflash-model-BF16.gguf",
+    "dflash-model-Q8_0.gguf",
+};
+
+// quants in subdirectories with sharded files and root sidecars,
+// in the style of stepfun-ai/Step-3.7-Flash-GGUF
+static const std::vector<std::string> subdir = {
+    "mmproj-model-f16.gguf",
+    "model-mtp-BF16.gguf",
+    "model-mtp-Q8_0.gguf",
+    "Q3_K_M/model-Q3_K_M-00001-of-00003.gguf",
+    "Q3_K_M/model-Q3_K_M-00002-of-00003.gguf",
+    "Q3_K_M/model-Q3_K_M-00003-of-00003.gguf",
+    "Q8_0/model-Q8_0-00001-of-00002.gguf",
+    "Q8_0/model-Q8_0-00002-of-00002.gguf",
+};
+
+// sidecar quants exist where the full model quant does not,
+// in the style of ggml-org/Qwen3.6-27B-GGUF
+static const std::vector<std::string> hole = {
+    "model-BF16.gguf",
+    "model-Q4_K_M.gguf",
+    "model-Q8_0.gguf",
+    "mtp-model-BF16.gguf",
+    "mtp-model-Q4_0.gguf",
+    "mtp-model-Q8_0.gguf",
+    "dflash-model-BF16.gguf",
+    "dflash-model-Q8_0.gguf",
+};
+
+// unsloth-style naming with UD quants and a suffix MTP file
+static const std::vector<std::string> unsloth = {
+    "model-UD-Q8_K_XL.gguf",
+    "mmproj-BF16.gguf",
+    "model-MTP-BF16.gguf",
+};
+
+// bartowski-style vendor prefix and mradermacher-style dot quant
+static const std::vector<std::string> vendors = {
+    "TheDrummer_Model-24B-v4.1-Q8_0.gguf",
+    "BlackSheep-24B.Q8_0.gguf",
+};
+
+// every speculative sidecar type at the same quant
+static const std::vector<std::string> quad = {
+    "model-Q8_0.gguf",
+    "mtp-model-Q8_0.gguf",
+    "dflash-model-Q8_0.gguf",
+    "eagle3-model-Q8_0.gguf",
+    "dspark-model-Q8_0.gguf",
+};
+
+static const std::vector<std::string> dflash_only = {
+    "model-Q8_0.gguf",
+    "dflash-model-Q8_0.gguf",
+};
+
+static const std::vector<std::string> eagle3_only = {
+    "model-Q8_0.gguf",
+    "eagle3-model-Q8_0.gguf",
+};
+
+// a single full quant with dspark sidecars at other quants,
+// in the style of ggml-org/DeepSeek-V4-Flash-0731-GGUF
+static const std::vector<std::string> spark = {
+    "README.md",
+    "model-MXFP4.gguf",
+    "dspark-model-BF16.gguf",
+    "dspark-model-MXFP4.gguf",
+};
+
+// dspark outranks dflash in the type auto-selection
+static const std::vector<std::string> dspark_dflash = {
+    "model-Q8_0.gguf",
+    "dflash-model-Q8_0.gguf",
+    "dspark-model-Q8_0.gguf",
+};
+
+//
+// table-driven plan resolution through the real entry point,
+// each case replayed on multiple deterministic reorderings of the listing,
+// except the cases whose pick legitimately depends on the listing order
+//
+
+struct plan_case {
+    const char * name;
+    const std::vector<std::string> & files;
+    const char * hf_repo;
+    const char * hf_file;
+    bool sidecars;        // request mmproj + mtp + dflash + eagle3 + dspark
+    bool order_dependent; // the expected pick depends on the listing order
+    const char * primary;
+    std::vector<std::string> model_files;
+    const char * mmproj;
+    const char * mtp;
+    const char * dflash;
+    const char * eagle3;
+    const char * dspark;
+};
+
+static const plan_case plan_cases[] = {
+    // exact tag picks the matching primary, sidecars follow the tag
+    {"flat exact tag", flat, "test/repo:Q8_0", "", true, false,
+     "model-Q8_0.gguf", {"model-Q8_0.gguf"},
+     "mmproj-model-Q8_0.gguf", "mtp-model-Q8_0.gguf", "dflash-model-Q8_0.gguf", "", ""},
+
+    // no tag falls back to the default quant preference
+    {"flat default", flat, "test/repo", "", false, false,
+     "model-Q4_K_M.gguf", {"model-Q4_K_M.gguf"},
+     "", "", "", "", ""},
+
+    // no tag and no default match falls back to the first model in the listing
+    {"unsloth fallback", unsloth, "test/repo", "", true, true,
+     "model-UD-Q8_K_XL.gguf", {"model-UD-Q8_K_XL.gguf"},
+     "mmproj-BF16.gguf", "", "", "", ""},
+
+    // explicit hf_file picks that exact file
+    {"flat hf_file", flat, "test/repo", "model-BF16.gguf", false, false,
+     "model-BF16.gguf", {"model-BF16.gguf"},
+     "", "", "", "", ""},
+
+    // missing hf_file resolves nothing
+    {"flat missing hf_file", flat, "test/repo", "nope.gguf", false, false,
+     "", {},
+     "", "", "", "", ""},
+
+    // a sharded primary brings all its parts, a subdir primary finds the root sidecar
+    {"subdir shards", subdir, "test/repo:Q3_K_M", "", true, false,
+     "Q3_K_M/model-Q3_K_M-00001-of-00003.gguf",
+     {"Q3_K_M/model-Q3_K_M-00001-of-00003.gguf",
+      "Q3_K_M/model-Q3_K_M-00002-of-00003.gguf",
+      "Q3_K_M/model-Q3_K_M-00003-of-00003.gguf"},
+     "mmproj-model-f16.gguf", "model-mtp-Q8_0.gguf", "", "", ""},
+
+    // a tag with no matching full model still resolves the requested sidecars
+    {"hole tag sidecar", hole, "test/repo:Q4_0", "", true, false,
+     "", {},
+     "", "mtp-model-Q4_0.gguf", "dflash-model-Q8_0.gguf", "", ""},
+
+    // the same tag without a requested sidecar resolves nothing
+    {"hole tag alone", hole, "test/repo:Q4_0", "", false, false,
+     "", {},
+     "", "", "", "", ""},
+
+    // no tag anchors the sidecars on the primary quant
+    {"hole default anchor", hole, "test/repo", "", true, false,
+     "model-Q4_K_M.gguf", {"model-Q4_K_M.gguf"},
+     "", "mtp-model-Q4_0.gguf", "dflash-model-Q8_0.gguf", "", ""},
+
+    // the mtp- keyword is case sensitive, a suffix -MTP file is not discovered
+    {"unsloth suffix mtp", unsloth, "test/repo:Q8_K_XL", "", true, false,
+     "model-UD-Q8_K_XL.gguf", {"model-UD-Q8_K_XL.gguf"},
+     "mmproj-BF16.gguf", "", "", "", ""},
+
+    // vendor prefixes and the dot quant convention both match the tag,
+    // first match wins between two files at the same quant
+    {"vendor prefix", vendors, "test/repo:Q8_0", "", false, true,
+     "TheDrummer_Model-24B-v4.1-Q8_0.gguf", {"TheDrummer_Model-24B-v4.1-Q8_0.gguf"},
+     "", "", "", "", ""},
+
+    // every sidecar type resolves at the tag
+    {"quad exact tag", quad, "test/repo:Q8_0", "", true, false,
+     "model-Q8_0.gguf", {"model-Q8_0.gguf"},
+     "", "mtp-model-Q8_0.gguf", "dflash-model-Q8_0.gguf", "eagle3-model-Q8_0.gguf", "dspark-model-Q8_0.gguf"},
+
+    // no tag anchors the dspark sidecar on the only full quant
+    {"spark default anchor", spark, "test/repo", "", true, false,
+     "model-MXFP4.gguf", {"model-MXFP4.gguf"},
+     "", "", "", "", "dspark-model-MXFP4.gguf"},
+
+    // a tag with no matching full model still resolves the exact dspark sidecar
+    {"spark tag sidecar", spark, "test/repo:BF16", "", true, false,
+     "", {},
+     "", "", "", "", "dspark-model-BF16.gguf"},
+};
+
+static void check_plan(const plan_case & c) {
+    common_download_opts opts;
+    opts.download_mmproj = c.sidecars;
+    opts.download_mtp    = c.sidecars;
+    opts.download_dflash = c.sidecars;
+    opts.download_eagle3 = c.sidecars;
+    opts.download_dspark = c.sidecars;
+
+    auto plan = common_download_get_hf_plan(model_ref(c.hf_repo, c.hf_file), opts);
+
+    REQUIRE_EQ(plan.primary.path, c.primary);
+    REQUIRE_EQ(plan.mmproj.path,  c.mmproj);
+    REQUIRE_EQ(plan.mtp.path,     c.mtp);
+    REQUIRE_EQ(plan.dflash.path,  c.dflash);
+    REQUIRE_EQ(plan.eagle3.path,  c.eagle3);
+    REQUIRE_EQ(plan.dspark.path,  c.dspark);
+
+    // exact shard set, order insensitive; the primary must be the first split
+    std::vector<std::string> actual;
+    for (const auto & f : plan.model_files) {
+        actual.push_back(f.path);
+    }
+    std::sort(actual.begin(), actual.end());
+    auto expected = c.model_files;
+    std::sort(expected.begin(), expected.end());
+    REQUIRE(actual == expected);
+    if (!expected.empty()) {
+        REQUIRE(plan.primary.path == expected.front());
+    }
+}
+
+static void test_plan_resolution() {
+    printf("test-model-resolution: plan resolution on %zu cases\n", sizeof(plan_cases) / sizeof(plan_cases[0]));
+
+    for (const auto & c : plan_cases) {
+        printf("  %s\n", c.name);
+        // invariant: the resolution is insensitive to the listing order
+        for (size_t rot = 0; rot < c.files.size(); ++rot) {
+            if (c.order_dependent && rot > 0) {
+                continue;
+            }
+            g_context = std::string(c.name) + ", reordering " + std::to_string(rot);
+            auto files = c.files;
+            std::rotate(files.begin(), files.begin() + rot, files.end());
+            if (rot % 2 == 1) {
+                std::reverse(files.begin(), files.end());
+            }
+            g_repos["test/repo"] = files;
+            check_plan(c);
+        }
+    }
+    g_repos.clear();
+}
+
+//
+// end-to-end assembly: real CLI parsing, real handler init resolving over the
+// loopback, downloads skipped by flipping offline before apply
+//
+
+static void assemble(std::vector<std::string> argv, common_params & params) {
+    std::vector<char *> cargv;
+    g_context.clear();
+    for (auto & a : argv) {
+        g_context += g_context.empty() ? a : " " + a;
+        cargv.push_back(a.data());
+    }
+    bool ok = common_params_parse((int) cargv.size(), cargv.data(), params, LLAMA_EXAMPLE_SERVER);
+    REQUIRE(ok);
+
+    auto handler = common_models_handler_init(params, LLAMA_EXAMPLE_SERVER);
+
+    // skip the network execution, on_done still wires the params
+    params.offline = true;
+    common_models_handler_apply(handler, params);
+}
+
+static void test_task_assembly() {
+    printf("test-model-resolution: end-to-end assembly\n");
+
+    g_repos["test/main"]   = flat;
+    g_repos["test/hole"]   = hole;
+    g_repos["test/quad"]   = quad;
+    g_repos["test/dflash"] = dflash_only;
+    g_repos["test/eagle3"] = eagle3_only;
+    g_repos["test/spark"]  = spark;
+    g_repos["test/pair"]   = dspark_dflash;
+    g_repos["test/small"]  = {"draft-model-Q4_K_M.gguf"};
+    g_repos["test/preset"] = {"preset.ini", "model-Q8_0.gguf"};
+
+    {
+        // plain -hf wires the model and its mmproj, nothing speculative
+        common_params params;
+        assemble({"server", "-hf", "test/main:Q8_0"}, params);
+        REQUIRE_EQ(params.model.path,  cached("test/main", "model-Q8_0.gguf"));
+        REQUIRE_EQ(params.mmproj.path, cached("test/main", "mmproj-model-Q8_0.gguf"));
+        REQUIRE(params.speculative.draft.mparams.path.empty());
+    }
+    {
+        // --no-mmproj disables the mmproj discovery
+        common_params params;
+        assemble({"server", "-hf", "test/main:Q8_0", "--no-mmproj"}, params);
+        REQUIRE(params.mmproj.path.empty());
+    }
+    {
+        // an explicit --mmproj wins over the discovery
+        common_params params;
+        assemble({"server", "-hf", "test/main:Q8_0", "--mmproj", "/local/mmproj.gguf"}, params);
+        REQUIRE(params.mmproj.path == "/local/mmproj.gguf");
+    }
+    {
+        // -hf with a spec type wires the sidecar of the main repo as fallback draft
+        common_params params;
+        assemble({"server", "-hf", "test/main:Q8_0", "--spec-type", "draft-mtp"}, params);
+        REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/main", "mtp-model-Q8_0.gguf"));
+    }
+    {
+        // -hfd with a spec type wires the draft repo sidecar at its tag,
+        // not its full model, and suppresses the main repo fallback
+        common_params params;
+        assemble({"server", "-hf", "test/hole:Q8_0", "-hfd", "test/hole:Q4_0", "--spec-type", "draft-mtp"}, params);
+        REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/hole", "mtp-model-Q4_0.gguf"));
+    }
+    {
+        // an explicit -md file wins over the sidecar resolution
+        common_params params;
+        assemble({"server", "-hf", "test/main:Q8_0", "-hfd", "test/main", "-md", "mtp-model-BF16.gguf", "--spec-type", "draft-mtp"}, params);
+        REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/main", "mtp-model-BF16.gguf"));
+    }
+    {
+        // -hfd without a spec type auto-selects the type, mtp first when all ship
+        common_params params;
+        assemble({"server", "-hf", "test/main:Q8_0", "-hfd", "test/quad:Q8_0"}, params);
+        REQUIRE(params.speculative.types == std::vector<enum common_speculative_type>{COMMON_SPECULATIVE_TYPE_DRAFT_MTP});
+        REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/quad", "mtp-model-Q8_0.gguf"));
+    }
+    {
+        // auto-selection with only a dflash sidecar
+        common_params params;
+        assemble({"server", "-hf", "test/main:Q8_0", "-hfd", "test/dflash:Q8_0"}, params);
+        REQUIRE(params.speculative.types == std::vector<enum common_speculative_type>{COMMON_SPECULATIVE_TYPE_DRAFT_DFLASH});
+        REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/dflash", "dflash-model-Q8_0.gguf"));
+    }
+    {
+        // auto-selection with only an eagle3 sidecar
+        common_params params;
+        assemble({"server", "-hf", "test/main:Q8_0", "-hfd", "test/eagle3:Q8_0"}, params);
+        REQUIRE(params.speculative.types == std::vector<enum common_speculative_type>{COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3});
+        REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/eagle3", "eagle3-model-Q8_0.gguf"));
+    }
+    {
+        // auto-selection prefers dspark over dflash when both ship
+        common_params params;
+        assemble({"server", "-hf", "test/main:Q8_0", "-hfd", "test/pair:Q8_0"}, params);
+        REQUIRE(params.speculative.types == std::vector<enum common_speculative_type>{COMMON_SPECULATIVE_TYPE_DRAFT_DSPARK});
+        REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/pair", "dspark-model-Q8_0.gguf"));
+    }
+    {
+        // -hf with the dspark spec type wires the sidecar of the main repo,
+        // anchored on the only full quant
+        common_params params;
+        assemble({"server", "-hf", "test/spark", "--spec-type", "draft-dspark"}, params);
+        REQUIRE_EQ(params.model.path, cached("test/spark", "model-MXFP4.gguf"));
+        REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/spark", "dspark-model-MXFP4.gguf"));
+    }
+    {
+        // -hfd on a repo without sidecars keeps resolving a full model as draft
+        common_params params;
+        assemble({"server", "-hf", "test/main:Q8_0", "-hfd", "test/small"}, params);
+        REQUIRE(params.speculative.types == std::vector<enum common_speculative_type>{COMMON_SPECULATIVE_TYPE_NONE});
+        REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/small", "draft-model-Q4_K_M.gguf"));
+    }
+    {
+        // a preset repo wires the preset and clears the model for router mode
+        common_params params;
+        assemble({"server", "-hf", "test/preset"}, params);
+        REQUIRE_EQ(params.models_preset, cached("test/preset", "preset.ini"));
+        REQUIRE(params.model.path.empty());
+        REQUIRE(params.model.hf_repo.empty());
+    }
+
+    g_repos.clear();
+}
+
+int main(void) {
+    // unbuffered, so a crash cannot swallow the reports already printed
+    setvbuf(stdout, nullptr, _IONBF, 0);
+    setvbuf(stderr, nullptr, _IONBF, 0);
+
+    // the negative cases legitimately log errors on every reordering,
+    // keep the output down to the reports
+    common_log_pause(common_log_main());
+
+    // the loopback endpoint also keeps the client init from rejecting
+    // https on the builds without TLS support
+    httplib::Server server;
+    serve_repos(server);
+    int port = server.bind_to_any_port("127.0.0.1");
+
+    // isolate the cache, its location is read once so it is set
+    // before anything else
+    cache_dir = std::filesystem::temp_directory_path() /
+                ("test-model-resolution-cache-" + std::to_string(port));
+    std::filesystem::remove_all(cache_dir);
+    common_set_env("LLAMA_CACHE", cache_dir.string());
+
+    std::thread server_thread([&server] { server.listen_after_bind(); });
+    server.wait_until_ready();
+    common_set_env("MODEL_ENDPOINT", "http://127.0.0.1:" + std::to_string(port) + "/");
+
+    test_plan_resolution();
+    test_task_assembly();
+
+    server.stop();
+    server_thread.join();
+
+    std::filesystem::remove_all(cache_dir);
+    printf("test-model-resolution: all tests OK\n");
+    return 0;
+}

tests/test-sampling.cpp

@@ -144,7 +144,7 @@ static void test_penalties(
 
     sampler_tester tester(probs, probs_expected);
 
-    auto * sampler = llama_sampler_init_penalties(last_tokens.size(), repeat_penalty, alpha_frequency, alpha_presence);
+    auto * sampler = llama_sampler_init_penalties((int32_t) probs.size(), (int32_t) last_tokens.size(), repeat_penalty, alpha_frequency, alpha_presence);
 
     for (size_t i = 0; i < last_tokens.size(); i++) {
         llama_sampler_accept(sampler, last_tokens[i]);

tools/cli/README.md

@@ -54,6 +54,7 @@
 | `-ctv, --cache-type-v TYPE` | KV cache data type for V<br/>allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1<br/>(default: f16)<br/>(env: LLAMA_ARG_CACHE_TYPE_V) |
 | `-dt, --defrag-thold N` | KV cache defragmentation threshold (DEPRECATED)<br/>(env: LLAMA_ARG_DEFRAG_THOLD) |
 | `-np, --parallel N` | number of parallel sequences to decode (default: 1)<br/>(env: LLAMA_ARG_N_PARALLEL) |
+| `--rpc SERVERS` | comma-separated list of RPC servers (host:port)<br/>(env: LLAMA_ARG_RPC) |
 | `--mlock` | DEPRECATED in favor of `--load-mode`: force system to keep model in RAM rather than swapping or compressing<br/>(env: LLAMA_ARG_MLOCK) |
 | `--mmap, --no-mmap` | DEPRECATED in favor of `--load-mode`: whether to memory-map model. (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>(env: LLAMA_ARG_MMAP) |
 | `-dio, --direct-io, -ndio, --no-direct-io` | DEPRECATED in favor of `--load-mode`: use DirectIO if available<br/>(env: LLAMA_ARG_DIO) |

tools/completion/README.md

@@ -137,6 +137,7 @@ llama-completion.exe -m models\gemma-1.1-7b-it.Q4_K_M.gguf --ignore-eos -n -1
 | `-ctv, --cache-type-v TYPE` | KV cache data type for V<br/>allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1<br/>(default: f16)<br/>(env: LLAMA_ARG_CACHE_TYPE_V) |
 | `-dt, --defrag-thold N` | KV cache defragmentation threshold (DEPRECATED)<br/>(env: LLAMA_ARG_DEFRAG_THOLD) |
 | `-np, --parallel N` | number of parallel sequences to decode (default: 1)<br/>(env: LLAMA_ARG_N_PARALLEL) |
+| `--rpc SERVERS` | comma-separated list of RPC servers (host:port)<br/>(env: LLAMA_ARG_RPC) |
 | `--mlock` | DEPRECATED in favor of `--load-mode`: force system to keep model in RAM rather than swapping or compressing<br/>(env: LLAMA_ARG_MLOCK) |
 | `--mmap, --no-mmap` | DEPRECATED in favor of `--load-mode`: whether to memory-map model. (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>(env: LLAMA_ARG_MMAP) |
 | `-dio, --direct-io, -ndio, --no-direct-io` | DEPRECATED in favor of `--load-mode`: use DirectIO if available<br/>(env: LLAMA_ARG_DIO) |

tools/mtmd/CMakeLists.txt

@@ -18,6 +18,8 @@ add_library(mtmd
             mtmd-image.cpp
             mtmd.h
             mtmd-helper.cpp
+            mtmd-helper-gen.cpp
+            mtmd-helper-common.h
             mtmd-helper.h
             clip.cpp
             clip.h
@@ -52,6 +54,8 @@ add_library(mtmd
             models/mimovl.cpp
             models/qwen3a.cpp
             models/mimo-audio.cpp
+            models/qwen3tts-spkenc.cpp
+            models/qwen3tts-gen.cpp
             models/step3vl.cpp
             models/siglip.cpp
             models/whisper-enc.cpp

tools/mtmd/README-dev.md

@@ -33,3 +33,52 @@ A typical pipeline of the core libmtmd is as follows:
 We provide a set of helper functions via `mtmd_helper` to make using libmtmd easier. The helper provides:
 - Image, audio and video file decoding (for example, decode raw JPEG into RGB bitmap)
 - Manage `llama_batch` and calls to `llama_decode`
+
+## Audio generation support
+
+Audio generation is added to mtmd in PR [#26254](https://github.com/ggml-org/llama.cpp/pull/26254)
+
+Currently, we support the 3-stage pipeline below which should cover most TTS models:
+- Stage 1: Backbone / Semantic Stage: Backbone model accepts text prompt and reference voice as input
+- Stage 2: Acoustic Detail Generator: A model takes the hidden state from backbone and generate audio details (usually as audio codes or mel-spectrogram)
+- Stage 3: Waveform Reconstruction: Convert the semantic and acoustic data from previous stages to the final waveform
+
+For example, Qwen3-TTS:
+- Reference voice is encoded using ECAPA-TDNN speaker encoder (`speaker_encoder`)
+- Text prompt and reference voice are processed via a backbone (`talker.model`)
+- A model converts sampled semantic token and hidden state from stage 2 into a list of 15 acoustic codes (`talker.code_predictor`)
+- 16 generated codes are converted into waveform (`code2wav`)
+
+### API design constraints
+
+Due to wide variety of audio generation pipelines, the `mtmd_gen_audio` system is designed to be flexible and reusable by new models.
+
+`mtmd_gen_audio` is split into 2 main API:
+- Core API `mtmd.h`: handles main inference. Important: the API surface must be stateless; caller must handle state management and audio frame accumulation.
+- Helper API `mtmd-helper.h`: provides a model-agnostic stateful API. Usage example can be found in the `tools/tts` directory.
+
+### Checklist for porting new audio generation models to mtmd
+
+1. Establish a list of reusable and missing components from the current mtmd implementation.
+2. For GGUF conversion:
+    - Backbone model should be converted to a normal text model (loadable via `libllama`)
+        - If model used hard-coded embedding row ID, append them to token embeddings and assign token name for them (see `qwen3tts.py`)
+        - If model have a specific output logits head for audio codes (usually semantic code), keep the head as-is and pad the logits at inference time (see `src/models/qwen3vl.cpp`)
+    - Sidecar models (code2wav, bigvgan, etc) must live inside the mmproj GGUF (but can be in different `clip_context` if necessary)
+        - Note: it should use `ggml_build_forward_select` to select graphs if multiple graphs living in the same context
+    - Reuse existing GGUF metadata key name and tensor name whenever possible; think twice before adding extensive changes to GGUF writer. For example, Qwen3-TTS hard-code part of the hparams to `clip.cpp` as they won't likely to change.
+    - For tensor naming:
+        - Prefixed with `a.*` for tensors used by speaker encoder pipeline
+        - Prefixed with `a.gen.*` for generation stages (code / mel-spectrogram / PCM generation)
+3. Make sure most of the changes happen inside `mtmd-helper-gen.cpp`. A good PR looks like this:
+    - 10-20% changes is to add new backbone (text) model and conversion
+    - 60% changes inside `mtmd-helper-gen.cpp`
+    - 10% changes inside `libmtmd` and `clip.cpp` systems
+    - The rest downstream code (CLI, server) should have no changes at all
+4. Update usage documentation in `tools/tts/README.md`
+
+IMPORTANT: If your model needs changes that don't fit the existing infrastructure, **open an issue first for discussion**.
+
+No-go checklist (these will get the PR rejected and require discussion before proceeding):
+- Violating the API design constraints stated above
+- Adding a new model-specific binary: the API and binary surface must stay model-agnostic

tools/mtmd/clip-graph.h

@@ -54,6 +54,9 @@ struct clip_graph {
 
     clip_graph(clip_ctx * ctx, const clip_image_f32 & img);
 
+    // build sub-graph, reuse buf from parent
+    clip_graph(const clip_graph & parent);
+
     virtual ~clip_graph() = default;
     virtual ggml_cgraph * build() = 0;
 

tools/mtmd/clip-impl.h

@@ -32,6 +32,7 @@
 #define KEY_PROJ_TYPE           "clip.projector_type"
 #define KEY_HAS_AUDIO_ENC       "clip.has_audio_encoder"
 #define KEY_HAS_VISION_ENC      "clip.has_vision_encoder"
+#define KEY_HAS_GEN_AUDIO_ENC   "clip.has_gen_audio_encoder"
 #define KEY_USE_GELU            "clip.use_gelu"
 #define KEY_USE_SILU            "clip.use_silu"
 
@@ -89,6 +90,8 @@
 #define KEY_A_ATTN_WINDOW_SIZE     "clip.audio.window_size"          // mimo-audio-tokenizer: sliding-window radius
 #define KEY_A_LOCAL_BLOCK_COUNT    "clip.audio.local_block_count"    // mimo-v2.5: input_local_transformer layer count
 #define KEY_A_LOCAL_GROUP_SIZE     "clip.audio.local_group_size"     // mimo-v2.5: input_local_transformer grouping size
+// audio generation (gen-audio)-specific
+#define KEY_GEN_AUDIO_PROJ_TYPE    "clip.gen.audio.projector_type" // for models with mixed modalities
 #define KEY_AUDIO_SUBSAMPLING_FACTOR "clip.audio.subsampling_factor"
 
 //
@@ -201,6 +204,48 @@
 #define TN_MM_A_LOCAL_LN2      "mm.a.local_blk.%d.ln2.%s"
 #define TN_MM_A_LOCAL_NORM     "mm.a.local_norm.%s"
 
+// qwen3tts speaker encoder (ECAPA-TDNN)
+#define TN_A_SE_CONV1  "a.blk.%d.se_conv1.%s"
+#define TN_A_SE_CONV2  "a.blk.%d.se_conv2.%s"
+#define TN_A_CONV_RES2 "a.blk.%d.res2.%d.%s"
+#define TN_A_ASP_ATTN  "a.asp_attn.%s"
+#define TN_A_ASP_TDNN  "a.asp_tdnn.%s"
+
+// qwen3tts code_predictor
+#define TN_A_GEN_CODE_PROJ_IN  "a.gen.code.proj_in.%s"
+#define TN_A_GEN_CODE_EMBD     "a.gen.code.embd.%s"
+#define TN_A_GEN_CODE_HEAD     "a.gen.code.head.%s"
+#define TN_A_GEN_CODE_OUT_EMBD "a.gen.code.out_embd.%s"
+#define TN_A_GEN_CODE_NORM     "a.gen.code.output_norm.%s"
+
+// qwen3tts code2wav (RVQ codes -> raw PCM)
+// pre_transformer layers use the generic TN_ATTN_*/TN_FFN_*/TN_LN_*/TN_LS_* macros, prefix "a.gen.wav.tfm"
+#define TN_A_GEN_WAV_QUANT_FIRST_IN  "a.gen.wav.quant.first.in_proj.%s"
+#define TN_A_GEN_WAV_QUANT_FIRST_OUT "a.gen.wav.quant.first.out_proj.%s"
+#define TN_A_GEN_WAV_QUANT_FIRST_CB  "a.gen.wav.quant.first.codebook.%s"
+#define TN_A_GEN_WAV_QUANT_REST_IN   "a.gen.wav.quant.rest.in_proj.%s"
+#define TN_A_GEN_WAV_QUANT_REST_OUT  "a.gen.wav.quant.rest.out_proj.%s"
+#define TN_A_GEN_WAV_QUANT_REST_CB   "a.gen.wav.quant.rest.codebook.%s"
+#define TN_A_GEN_WAV_PRE_CONV        "a.gen.wav.pre_conv.%s"
+#define TN_A_GEN_WAV_TFM_IN_PROJ     "a.gen.wav.tfm.in_proj.%s"
+#define TN_A_GEN_WAV_TFM_OUT_PROJ    "a.gen.wav.tfm.out_proj.%s"
+#define TN_A_GEN_WAV_TFM_OUT_NORM    "a.gen.wav.tfm.output_norm.%s"
+#define TN_A_GEN_WAV_UP_CONV         "a.gen.wav.up.blk.%d.conv.%s"
+#define TN_A_GEN_WAV_UP_DWCONV       "a.gen.wav.up.blk.%d.dwconv.%s"
+#define TN_A_GEN_WAV_UP_NORM         "a.gen.wav.up.blk.%d.norm.%s"
+#define TN_A_GEN_WAV_UP_PW1          "a.gen.wav.up.blk.%d.pw1.%s"
+#define TN_A_GEN_WAV_UP_PW2          "a.gen.wav.up.blk.%d.pw2.%s"
+#define TN_A_GEN_WAV_UP_GAMMA        "a.gen.wav.up.blk.%d.gamma"
+#define TN_A_GEN_WAV_DAC_ENTRY       "a.gen.wav.dac.entry.%s"
+#define TN_A_GEN_WAV_DAC_SNAKE       "a.gen.wav.dac.blk.%d.snake.%s"
+#define TN_A_GEN_WAV_DAC_CONV        "a.gen.wav.dac.blk.%d.conv.%s"
+#define TN_A_GEN_WAV_DAC_RES_ACT1    "a.gen.wav.dac.blk.%d.res.%d.act1.%s"
+#define TN_A_GEN_WAV_DAC_RES_CONV1   "a.gen.wav.dac.blk.%d.res.%d.conv1.%s"
+#define TN_A_GEN_WAV_DAC_RES_ACT2    "a.gen.wav.dac.blk.%d.res.%d.act2.%s"
+#define TN_A_GEN_WAV_DAC_RES_CONV2   "a.gen.wav.dac.blk.%d.res.%d.conv2.%s"
+#define TN_A_GEN_WAV_DAC_POST_SNAKE  "a.gen.wav.dac.post_snake.%s"
+#define TN_A_GEN_WAV_DAC_POST_CONV   "a.gen.wav.dac.post_conv.%s"
+
 // cogvlm
 #define TN_MM_POST_FC_NORM "mm.post_fc_norm.%s"
 #define TN_MM_H_TO_4H      "mm.up.%s"
@@ -408,6 +453,8 @@ enum projector_type {
     PROJECTOR_TYPE_MINIMAX_M3,
     PROJECTOR_TYPE_GRANITE4_VISION,
     PROJECTOR_TYPE_MIMO_AUDIO,
+    PROJECTOR_TYPE_QWEN3TTS_SPKENC,
+    PROJECTOR_TYPE_QWEN3TTS_GEN,
     PROJECTOR_TYPE_UNKNOWN,
 };
 
@@ -465,6 +512,8 @@ static std::map<projector_type, std::string> PROJECTOR_TYPE_NAMES = {
     { PROJECTOR_TYPE_GRANITE4_VISION,   "granite4_vision"},
     { PROJECTOR_TYPE_MIMO_AUDIO,        "mimo_audio"},
     { PROJECTOR_TYPE_PARAKEET,          "parakeet"},
+    { PROJECTOR_TYPE_QWEN3TTS_SPKENC,   "qwen3tts_spkenc"},
+    { PROJECTOR_TYPE_QWEN3TTS_GEN,      "qwen3tts_gen"},
 };
 
 static projector_type clip_projector_type_from_string(const std::string & str) {

tools/mtmd/clip-model.h

@@ -136,6 +136,19 @@ struct clip_hparams {
     int32_t rvq_num_quantizers = 0;
     std::vector<int32_t> rvq_codebook_size; // per-quantizer bin count (ragged, e.g. 1024/1024/256/128x17)
 
+    // qwen3tts code2wav
+    int32_t wav_tfm_n_layer      = 0;
+    int32_t wav_tfm_n_embd       = 0;
+    int32_t wav_tfm_n_ff         = 0;
+    int32_t wav_tfm_n_head       = 0;
+    int32_t wav_tfm_n_head_kv    = 0;
+    float   wav_tfm_eps          = 1e-5f;
+    float   wav_tfm_rope_theta   = 10000.0f;
+    int32_t wav_upsample_n_block = 0;
+    int32_t wav_dac_n_block      = 0;
+    int32_t wav_dac_n_res        = 0;
+    int32_t wav_tfm_swa          = 0; // pre_transformer's KV cache size, in frames
+
     // mimo-v2.5: LLM-side connector (input_local_transformer)
     int32_t audio_local_n_layer = 0;
     int32_t audio_local_group_size = 0;
@@ -286,6 +299,14 @@ struct clip_layer {
     ggml_tensor * cross_attn_norm_w = nullptr;
     ggml_tensor * cross_attn_norm_b = nullptr;
 
+    // qwen3tts speaker encoder: SE-Res2Net block, tdnn1/tdnn2 reuse conv_pw1_w/b and conv_pw2_w/b above
+    ggml_tensor * se_conv1_w = nullptr;
+    ggml_tensor * se_conv1_b = nullptr;
+    ggml_tensor * se_conv2_w = nullptr;
+    ggml_tensor * se_conv2_b = nullptr;
+    std::vector<ggml_tensor *> res2_conv_w; // Res2Net hierarchical branches
+    std::vector<ggml_tensor *> res2_conv_b;
+
     bool has_deepstack() const {
         return deepstack_fc1_w != nullptr;
     }
@@ -365,6 +386,73 @@ struct qf_block {
     std::vector<clip_layer> qf_proj_layers;
 };
 
+// qwen3tts code2wav: RVQ codes -> raw PCM
+struct clip_code2wav {
+    // "upsample" stage: one ConvNeXt block plus the causal ConvTranspose1d before it
+    struct upsample_block {
+        ggml_tensor * conv_w   = nullptr; // causal ConvTranspose1d, 2x
+        ggml_tensor * conv_b   = nullptr;
+        ggml_tensor * dwconv_w = nullptr; // depthwise causal conv, k=7
+        ggml_tensor * dwconv_b = nullptr;
+        ggml_tensor * norm_w   = nullptr; // LayerNorm
+        ggml_tensor * norm_b   = nullptr;
+        ggml_tensor * pw1_w    = nullptr; // pointwise expand
+        ggml_tensor * pw1_b    = nullptr;
+        ggml_tensor * pw2_w    = nullptr; // pointwise project
+        ggml_tensor * pw2_b    = nullptr;
+        ggml_tensor * gamma    = nullptr; // layer scale
+    };
+
+    // one DAC residual unit: SnakeBeta -> dilated causal conv -> SnakeBeta -> pointwise causal conv
+    struct dac_res {
+        ggml_tensor * act1_alpha = nullptr;
+        ggml_tensor * act1_beta  = nullptr;
+        ggml_tensor * conv1_w    = nullptr;
+        ggml_tensor * conv1_b    = nullptr;
+        ggml_tensor * act2_alpha = nullptr;
+        ggml_tensor * act2_beta  = nullptr;
+        ggml_tensor * conv2_w    = nullptr;
+        ggml_tensor * conv2_b    = nullptr;
+    };
+
+    // one DAC upsample block (SnakeBeta -> causal ConvTranspose1d -> 3 residual units)
+    struct dac_block {
+        ggml_tensor * snake_alpha = nullptr;
+        ggml_tensor * snake_beta  = nullptr;
+        ggml_tensor * conv_w      = nullptr; // causal ConvTranspose1d
+        ggml_tensor * conv_b      = nullptr;
+        std::vector<dac_res> res;
+    };
+
+    // quantizer: RVQ codebook decode
+    ggml_tensor * quant_first_in_w  = nullptr; // semantic RVQ, in_proj (1x1 conv, loaded as 2D)
+    ggml_tensor * quant_first_out_w = nullptr;
+    ggml_tensor * quant_first_cb_w  = nullptr; // codebook (1 layer)
+    ggml_tensor * quant_rest_in_w   = nullptr; // acoustic RVQ
+    ggml_tensor * quant_rest_out_w  = nullptr;
+    ggml_tensor * quant_rest_cb_w   = nullptr; // codebooks, merged 3D [15, vocab, dim]
+
+    ggml_tensor * pre_conv_w = nullptr;
+    ggml_tensor * pre_conv_b = nullptr;
+
+    ggml_tensor * tfm_in_proj_w     = nullptr;
+    ggml_tensor * tfm_in_proj_b     = nullptr;
+    ggml_tensor * tfm_out_proj_w    = nullptr;
+    ggml_tensor * tfm_out_proj_b    = nullptr;
+    ggml_tensor * tfm_output_norm_w = nullptr;
+    std::vector<clip_layer> tfm_layers; // reuses the generic block fields (ln_1/attn/ln_2/ffn/ls_1/ls_2)
+
+    std::vector<upsample_block> upsample;
+
+    ggml_tensor * dac_entry_w = nullptr;
+    ggml_tensor * dac_entry_b = nullptr;
+    std::vector<dac_block> dac;
+    ggml_tensor * dac_post_snake_alpha = nullptr;
+    ggml_tensor * dac_post_snake_beta  = nullptr;
+    ggml_tensor * dac_post_conv_w      = nullptr;
+    ggml_tensor * dac_post_conv_b      = nullptr;
+};
+
 struct clip_model {
     clip_modality modality = CLIP_MODALITY_VISION;
     projector_type proj_type = PROJECTOR_TYPE_MLP;
@@ -577,6 +665,24 @@ struct clip_model {
     ggml_tensor * conv2d_3_w = nullptr;
     ggml_tensor * conv2d_3_b = nullptr;
 
+    // qwen3tts speaker encoder (ECAPA-TDNN)
+    // reused tensors: stem conv is conv1d_1_w/b, feature aggregation is conv_out_w/b, output proj is mm_fc_w/b
+    ggml_tensor * spk_asp_attn_w = nullptr;
+    ggml_tensor * spk_asp_attn_b = nullptr;
+    ggml_tensor * spk_asp_tdnn_w = nullptr;
+    ggml_tensor * spk_asp_tdnn_b = nullptr;
+
+    // qwen3tts code_predictor
+    ggml_tensor * gen_code_proj_in_w  = nullptr; // small_to_mtp_projection
+    ggml_tensor * gen_code_proj_in_b  = nullptr;
+    ggml_tensor * gen_code_embd_w     = nullptr; // per-codebook embedding, merged 3D
+    ggml_tensor * gen_code_head_w     = nullptr; // per-codebook output head, merged 3D
+    ggml_tensor * gen_code_out_embd_w = nullptr; // codebook-0 embedding, fed back into the talker
+    ggml_tensor * gen_code_norm_w     = nullptr; // final norm
+
+    // qwen3tts code2wav: RVQ codes -> raw PCM
+    clip_code2wav c2w;
+
     // cogvlm
     ggml_tensor * mm_post_fc_norm_w = nullptr;
     ggml_tensor * mm_post_fc_norm_b = nullptr;

tools/mtmd/clip.cpp

@@ -17,6 +17,7 @@
 #include <cstring>
 #include <fstream>
 #include <map>
+#include <random>
 #include <stdexcept>
 #include <unordered_set>
 #include <vector>
@@ -269,6 +270,29 @@ clip_graph::clip_graph(clip_ctx * ctx, const clip_image_f32 & img) :
     gf = ggml_new_graph_custom(ctx0, ctx->max_nodes, false);
 }
 
+clip_graph::clip_graph(const clip_graph & parent) :
+        model(parent.model),
+        hparams(parent.hparams),
+        proj_type(parent.proj_type),
+        img(parent.img),
+        patch_size(parent.patch_size),
+        n_patches_x(parent.n_patches_x),
+        n_patches_y(parent.n_patches_y),
+        n_patches(parent.n_patches),
+        n_embd(parent.n_embd),
+        n_head(parent.n_head),
+        n_head_kv(parent.n_head_kv),
+        d_head(parent.d_head),
+        n_layer(parent.n_layer),
+        n_mmproj_embd(parent.n_mmproj_embd),
+        eps(parent.eps),
+        kq_scale(parent.kq_scale),
+        flash_attn_type(parent.flash_attn_type) {
+    // reuse from parent
+    ctx0 = parent.ctx0;
+    gf   = parent.gf;
+}
+
 ggml_tensor * clip_graph::build_mm(ggml_tensor * w, ggml_tensor * x) const {
     return ggml_mul_mat(ctx0, w, x);
 }
@@ -873,7 +897,8 @@ ggml_tensor * clip_graph::build_patch_merge_permute(ggml_tensor * cur, int scale
     return cur;
 }
 
-static std::unique_ptr<clip_graph> clip_get_graph_builder(clip_ctx * ctx, const clip_image_f32_batch & imgs) {
+static std::unique_ptr<clip_graph> clip_get_graph_builder(clip_ctx * ctx, const clip_image_f32_batch & imgs,
+                                                            const clip_encode_params * params = nullptr) {
     const clip_image_f32 & img = imgs.entries[0];
     std::unique_ptr<clip_graph> builder;
 
@@ -1025,6 +1050,17 @@ static std::unique_ptr<clip_graph> clip_get_graph_builder(clip_ctx * ctx, const
             {
                 builder = std::make_unique<clip_graph_mimo_audio>(ctx, img);
             } break;
+        case PROJECTOR_TYPE_QWEN3TTS_SPKENC:
+            {
+                builder = std::make_unique<clip_graph_qwen3tts_spkenc>(ctx, img);
+            } break;
+        case PROJECTOR_TYPE_QWEN3TTS_GEN:
+            {
+                const auto  gen_process = params ? params->gen_process : CLIP_GEN_PROCESS_GEN_CODE;
+                const int   top_k = params ? params->top_k : 50;
+                const float top_p = params ? params->top_p : 1.0f;
+                builder = std::make_unique<clip_graph_qwen3tts_gen>(ctx, img, gen_process, top_k, top_p);
+            } break;
         case PROJECTOR_TYPE_YOUTUVL:
             {
                 builder = std::make_unique<clip_graph_youtuvl>(ctx, img);
@@ -1065,8 +1101,9 @@ struct clip_model_loader {
 
     size_t model_size = 0; // in bytes
 
-    bool has_vision = false;
-    bool has_audio  = false;
+    bool has_vision    = false;
+    bool has_audio     = false;
+    bool has_gen_audio = false;
 
     mtmd_progress_callback progress_callback = nullptr;
     void * progress_callback_user_data = nullptr;
@@ -1112,8 +1149,9 @@ struct clip_model_loader {
 
         // modalities
         {
-            get_bool(KEY_HAS_VISION_ENC, has_vision, false);
-            get_bool(KEY_HAS_AUDIO_ENC,  has_audio,  false);
+            get_bool(KEY_HAS_VISION_ENC,    has_vision,    false);
+            get_bool(KEY_HAS_AUDIO_ENC,     has_audio,     false);
+            get_bool(KEY_HAS_GEN_AUDIO_ENC, has_gen_audio, false);
 
             if (has_vision) {
                 LOG_INF("%s: has vision encoder\n", __func__);
@@ -1121,6 +1159,9 @@ struct clip_model_loader {
             if (has_audio) {
                 LOG_INF("%s: has audio encoder\n", __func__);
             }
+            if (has_gen_audio) {
+                LOG_INF("%s: has audio generation (gen) encoder\n", __func__);
+            }
         }
 
         // tensors
@@ -1147,6 +1188,8 @@ struct clip_model_loader {
             GGML_ASSERT(has_vision);
         } else if (modality == CLIP_MODALITY_AUDIO) {
             GGML_ASSERT(has_audio);
+        } else if (modality == CLIP_MODALITY_GEN_AUDIO) {
+            GGML_ASSERT(has_gen_audio);
         }
         model.modality = modality;
 
@@ -1163,6 +1206,8 @@ struct clip_model_loader {
                     get_string(KEY_VISION_PROJ_TYPE, proj_type, false);
                 } else if (modality == CLIP_MODALITY_AUDIO) {
                     get_string(KEY_AUDIO_PROJ_TYPE, proj_type, false);
+                } else if (modality == CLIP_MODALITY_GEN_AUDIO) {
+                    get_string(KEY_GEN_AUDIO_PROJ_TYPE, proj_type, false);
                 } else {
                     GGML_ABORT("unknown modality");
                 }
@@ -1182,12 +1227,13 @@ struct clip_model_loader {
             }
         }
 
-        const bool is_vision = model.modality == CLIP_MODALITY_VISION;
-        const bool is_audio  = model.modality == CLIP_MODALITY_AUDIO;
+        const bool is_vision    = model.modality == CLIP_MODALITY_VISION;
+        const bool is_audio     = model.modality == CLIP_MODALITY_AUDIO;
+        const bool is_gen_audio = model.modality == CLIP_MODALITY_GEN_AUDIO;
 
         // other hparams
         {
-            const char * prefix = is_vision ? "vision" : "audio";
+            const char * prefix = is_vision ? "vision" : (is_audio ? "audio" : "gen.audio");
             get_u32(string_format(KEY_N_EMBD,         prefix), hparams.n_embd);
             get_u32(string_format(KEY_N_HEAD,         prefix), hparams.n_head);
             get_u32(string_format(KEY_N_EMBD_HEAD,    prefix), hparams.n_embd_head, false);
@@ -1198,6 +1244,7 @@ struct clip_model_loader {
 
             // n_head_kv is optional (for GQA), default to n_head
             hparams.n_head_kv = hparams.n_head;
+            get_u32(string_format(KEY_N_HEAD_KV, prefix), hparams.n_head_kv, false);
 
             if (is_vision) {
                 get_u32(KEY_IMAGE_SIZE, hparams.image_size);
@@ -1226,6 +1273,11 @@ struct clip_model_loader {
                 hparams.image_size = 0;
                 hparams.patch_size = 1;
 
+            } else if (is_gen_audio) {
+                // these are unused, but still need to be set to avoid issues
+                hparams.image_size = 0;
+                hparams.patch_size = 1;
+
             } else {
                 GGML_ASSERT(false && "unknown modality");
             }
@@ -1647,6 +1699,33 @@ struct clip_model_loader {
                                 "%s: mimo_audio: %s must be > 0\n", __func__, KEY_A_LOCAL_GROUP_SIZE));
                         }
                     } break;
+                case PROJECTOR_TYPE_QWEN3TTS_SPKENC:
+                    {
+                        // ECAPA-TDNN speaker encoder, mel front-end uses the Slaney default (fmin=0, fmax=sr/2)
+                        hparams.audio_sample_rate = 24000;
+                        hparams.audio_n_fft       = 1024;
+                        hparams.audio_window_len  = 1024;
+                        hparams.audio_hop_len     = 256;
+                    } break;
+                case PROJECTOR_TYPE_QWEN3TTS_GEN:
+                    {
+                        // TODO: hardcoded for now, read from code_predictor_config instead
+                        hparams.rope_theta = 1000000.0f;
+
+                        // code2wav params
+                        hparams.wav_tfm_n_layer      = 8;
+                        hparams.wav_tfm_n_embd       = 512;
+                        hparams.wav_tfm_n_ff         = 1024;
+                        hparams.wav_tfm_n_head       = 16;
+                        hparams.wav_tfm_n_head_kv    = 16;
+                        hparams.wav_tfm_eps          = 1e-5f;
+                        hparams.wav_tfm_rope_theta   = 10000.0f;
+                        hparams.wav_upsample_n_block = 2;
+                        hparams.wav_dac_n_block      = 4;
+                        hparams.wav_dac_n_res        = 3;
+                        // matches the reference decoder's sliding_window (speech_tokenizer/config.json)
+                        hparams.wav_tfm_swa = 72;
+                    } break;
                 case PROJECTOR_TYPE_PADDLEOCR:
                     {
                         hparams.n_merge = 2;
@@ -1871,7 +1950,9 @@ struct clip_model_loader {
         }
 
         // TODO @ngxson : support both audio and video in the future
-        const char * prefix = model.modality == CLIP_MODALITY_AUDIO ? "a" : "v";
+        const char * prefix = model.modality == CLIP_MODALITY_AUDIO ? "a"
+                             : model.modality == CLIP_MODALITY_GEN_AUDIO ? "a.gen.code"
+                             : "v";
 
         // get offsets
         for (int64_t i = 0; i < gguf_get_n_tensors(ctx_gguf.get()); ++i) {
@@ -1973,7 +2054,8 @@ struct clip_model_loader {
         model.position_embeddings = get_tensor(string_format(TN_POS_EMBD, prefix), false);
 
         const bool has_standard_layers = (
-            model.proj_type != PROJECTOR_TYPE_GEMMA3NV);
+            model.proj_type != PROJECTOR_TYPE_GEMMA3NV &&
+            model.proj_type != PROJECTOR_TYPE_QWEN3TTS_SPKENC);
 
         // layers
         const int n_layers_to_load = has_standard_layers ? hparams.n_layer : 0;
@@ -2599,6 +2681,144 @@ struct clip_model_loader {
                     model.mm_1_w = get_tensor(string_format(TN_MM_AUDIO_MLP, 1, "weight"));
                     model.mm_2_w = get_tensor(string_format(TN_MM_AUDIO_MLP, 2, "weight"));
                 } break;
+            case PROJECTOR_TYPE_QWEN3TTS_SPKENC:
+                {
+                    // stem TDNN (block 0)
+                    model.conv1d_1_w = get_tensor(string_format(TN_CONV1D, 0, "weight"));
+                    model.conv1d_1_b = get_tensor(string_format(TN_CONV1D, 0, "bias"));
+
+                    // SE-Res2Net blocks (GGUF bid 1..3, one per hparams.n_layer)
+                    model.layers.resize(hparams.n_layer);
+                    for (int il = 0; il < hparams.n_layer; il++) {
+                        auto & layer = model.layers[il];
+                        int bid = il + 1;
+                        layer.conv_pw1_w = get_tensor(string_format(TN_CONV_PW1, prefix, bid, "weight"));
+                        layer.conv_pw1_b = get_tensor(string_format(TN_CONV_PW1, prefix, bid, "bias"));
+                        layer.conv_pw2_w = get_tensor(string_format(TN_CONV_PW2, prefix, bid, "weight"));
+                        layer.conv_pw2_b = get_tensor(string_format(TN_CONV_PW2, prefix, bid, "bias"));
+                        layer.se_conv1_w = get_tensor(string_format(TN_A_SE_CONV1, bid, "weight"));
+                        layer.se_conv1_b = get_tensor(string_format(TN_A_SE_CONV1, bid, "bias"));
+                        layer.se_conv2_w = get_tensor(string_format(TN_A_SE_CONV2, bid, "weight"));
+                        layer.se_conv2_b = get_tensor(string_format(TN_A_SE_CONV2, bid, "bias"));
+                        layer.res2_conv_w.resize(7);
+                        layer.res2_conv_b.resize(7);
+                        for (int xid = 0; xid < 7; xid++) {
+                            layer.res2_conv_w[xid] = get_tensor(string_format(TN_A_CONV_RES2, bid, xid, "weight"));
+                            layer.res2_conv_b[xid] = get_tensor(string_format(TN_A_CONV_RES2, bid, xid, "bias"));
+                        }
+                    }
+
+                    // multi-layer feature aggregation
+                    model.conv_out_w = get_tensor(string_format(TN_CONV_OUT, "weight"));
+                    model.conv_out_b = get_tensor(string_format(TN_CONV_OUT, "bias"));
+
+                    // attentive statistics pooling
+                    model.spk_asp_attn_w = get_tensor(string_format(TN_A_ASP_ATTN, "weight"));
+                    model.spk_asp_attn_b = get_tensor(string_format(TN_A_ASP_ATTN, "bias"));
+                    model.spk_asp_tdnn_w = get_tensor(string_format(TN_A_ASP_TDNN, "weight"));
+                    model.spk_asp_tdnn_b = get_tensor(string_format(TN_A_ASP_TDNN, "bias"));
+
+                    // final speaker embedding projection
+                    model.mm_fc_w = get_tensor(string_format(TN_MM_AUDIO_FC, "weight"));
+                    model.mm_fc_b = get_tensor(string_format(TN_MM_AUDIO_FC, "bias"));
+                } break;
+            case PROJECTOR_TYPE_QWEN3TTS_GEN:
+                {
+                    // code_predictor
+                    model.gen_code_proj_in_w = get_tensor(string_format(TN_A_GEN_CODE_PROJ_IN, "weight"));
+                    model.gen_code_proj_in_b = get_tensor(string_format(TN_A_GEN_CODE_PROJ_IN, "bias"));
+                    model.gen_code_embd_w     = get_tensor(string_format(TN_A_GEN_CODE_EMBD,     "weight"));
+                    model.gen_code_head_w     = get_tensor(string_format(TN_A_GEN_CODE_HEAD,     "weight"));
+                    model.gen_code_out_embd_w = get_tensor(string_format(TN_A_GEN_CODE_OUT_EMBD, "weight"));
+                    model.gen_code_norm_w     = get_tensor(string_format(TN_A_GEN_CODE_NORM,     "weight"));
+
+                    // code2wav: RVQ codes -> raw PCM, lives in the same ctx as code_predictor
+                    {
+                        auto & c2w = model.c2w;
+
+                        c2w.quant_first_in_w  = get_tensor(string_format(TN_A_GEN_WAV_QUANT_FIRST_IN,  "weight"));
+                        c2w.quant_first_out_w = get_tensor(string_format(TN_A_GEN_WAV_QUANT_FIRST_OUT, "weight"));
+                        c2w.quant_first_cb_w  = get_tensor(string_format(TN_A_GEN_WAV_QUANT_FIRST_CB,  "weight"));
+                        c2w.quant_rest_in_w   = get_tensor(string_format(TN_A_GEN_WAV_QUANT_REST_IN,   "weight"));
+                        c2w.quant_rest_out_w  = get_tensor(string_format(TN_A_GEN_WAV_QUANT_REST_OUT,  "weight"));
+                        c2w.quant_rest_cb_w   = get_tensor(string_format(TN_A_GEN_WAV_QUANT_REST_CB,   "weight"));
+
+                        c2w.pre_conv_w = get_tensor(string_format(TN_A_GEN_WAV_PRE_CONV, "weight"));
+                        c2w.pre_conv_b = get_tensor(string_format(TN_A_GEN_WAV_PRE_CONV, "bias"));
+
+                        c2w.tfm_in_proj_w     = get_tensor(string_format(TN_A_GEN_WAV_TFM_IN_PROJ,  "weight"));
+                        c2w.tfm_in_proj_b     = get_tensor(string_format(TN_A_GEN_WAV_TFM_IN_PROJ,  "bias"));
+                        c2w.tfm_out_proj_w    = get_tensor(string_format(TN_A_GEN_WAV_TFM_OUT_PROJ, "weight"));
+                        c2w.tfm_out_proj_b    = get_tensor(string_format(TN_A_GEN_WAV_TFM_OUT_PROJ, "bias"));
+                        c2w.tfm_output_norm_w = get_tensor(string_format(TN_A_GEN_WAV_TFM_OUT_NORM, "weight"));
+
+                        // loaded manually, the generic model.layers loop is taken by code_predictor
+                        c2w.tfm_layers.resize(hparams.wav_tfm_n_layer);
+                        for (int il = 0; il < hparams.wav_tfm_n_layer; il++) {
+                            auto & layer = c2w.tfm_layers[il];
+                            const char * p = "a.gen.wav.tfm";
+                            layer.q_w      = get_tensor(string_format(TN_ATTN_Q,      p, il, "weight"));
+                            layer.k_w      = get_tensor(string_format(TN_ATTN_K,      p, il, "weight"));
+                            layer.v_w      = get_tensor(string_format(TN_ATTN_V,      p, il, "weight"));
+                            layer.o_w      = get_tensor(string_format(TN_ATTN_OUTPUT, p, il, "weight"));
+                            layer.ln_1_w   = get_tensor(string_format(TN_LN_1,        p, il, "weight"));
+                            layer.ln_2_w   = get_tensor(string_format(TN_LN_2,        p, il, "weight"));
+                            layer.ls_1_w   = get_tensor(string_format(TN_LS_1,        p, il, "weight"));
+                            layer.ls_2_w   = get_tensor(string_format(TN_LS_2,        p, il, "weight"));
+                            layer.ff_gate_w = get_tensor(string_format(TN_FFN_GATE,   p, il, "weight"));
+                            layer.ff_up_w   = get_tensor(string_format(TN_FFN_UP,     p, il, "weight"));
+                            layer.ff_down_w = get_tensor(string_format(TN_FFN_DOWN,   p, il, "weight"));
+                        }
+
+                        // upsample: 2x (causal ConvTranspose1d + ConvNeXt block)
+                        c2w.upsample.resize(hparams.wav_upsample_n_block);
+                        for (int il = 0; il < hparams.wav_upsample_n_block; il++) {
+                            auto & up = c2w.upsample[il];
+                            up.conv_w   = get_tensor(string_format(TN_A_GEN_WAV_UP_CONV,   il, "weight"));
+                            up.conv_b   = get_tensor(string_format(TN_A_GEN_WAV_UP_CONV,   il, "bias"));
+                            up.dwconv_w = get_tensor(string_format(TN_A_GEN_WAV_UP_DWCONV, il, "weight"));
+                            up.dwconv_b = get_tensor(string_format(TN_A_GEN_WAV_UP_DWCONV, il, "bias"));
+                            up.norm_w   = get_tensor(string_format(TN_A_GEN_WAV_UP_NORM,   il, "weight"));
+                            up.norm_b   = get_tensor(string_format(TN_A_GEN_WAV_UP_NORM,   il, "bias"));
+                            up.pw1_w    = get_tensor(string_format(TN_A_GEN_WAV_UP_PW1,    il, "weight"));
+                            up.pw1_b    = get_tensor(string_format(TN_A_GEN_WAV_UP_PW1,    il, "bias"));
+                            up.pw2_w    = get_tensor(string_format(TN_A_GEN_WAV_UP_PW2,    il, "weight"));
+                            up.pw2_b    = get_tensor(string_format(TN_A_GEN_WAV_UP_PW2,    il, "bias"));
+                            up.gamma    = get_tensor(string_format(TN_A_GEN_WAV_UP_GAMMA,  il));
+                        }
+
+                        // DAC decoder: conv_pre + n upsample blocks (each with n_res residual units) + conv_post
+                        c2w.dac_entry_w = get_tensor(string_format(TN_A_GEN_WAV_DAC_ENTRY, "weight"));
+                        c2w.dac_entry_b = get_tensor(string_format(TN_A_GEN_WAV_DAC_ENTRY, "bias"));
+
+                        c2w.dac.resize(hparams.wav_dac_n_block);
+                        for (int il = 0; il < hparams.wav_dac_n_block; il++) {
+                            auto & blk = c2w.dac[il];
+                            blk.snake_alpha = get_tensor(string_format(TN_A_GEN_WAV_DAC_SNAKE, il, "alpha"));
+                            blk.snake_beta  = get_tensor(string_format(TN_A_GEN_WAV_DAC_SNAKE, il, "beta"));
+                            blk.conv_w      = get_tensor(string_format(TN_A_GEN_WAV_DAC_CONV,  il, "weight"));
+                            blk.conv_b      = get_tensor(string_format(TN_A_GEN_WAV_DAC_CONV,  il, "bias"));
+
+                            blk.res.resize(hparams.wav_dac_n_res);
+                            for (int ir = 0; ir < hparams.wav_dac_n_res; ir++) {
+                                auto & res = blk.res[ir];
+                                res.act1_alpha = get_tensor(string_format(TN_A_GEN_WAV_DAC_RES_ACT1,  il, ir, "alpha"));
+                                res.act1_beta  = get_tensor(string_format(TN_A_GEN_WAV_DAC_RES_ACT1,  il, ir, "beta"));
+                                res.conv1_w    = get_tensor(string_format(TN_A_GEN_WAV_DAC_RES_CONV1, il, ir, "weight"));
+                                res.conv1_b    = get_tensor(string_format(TN_A_GEN_WAV_DAC_RES_CONV1, il, ir, "bias"));
+                                res.act2_alpha = get_tensor(string_format(TN_A_GEN_WAV_DAC_RES_ACT2,  il, ir, "alpha"));
+                                res.act2_beta  = get_tensor(string_format(TN_A_GEN_WAV_DAC_RES_ACT2,  il, ir, "beta"));
+                                res.conv2_w    = get_tensor(string_format(TN_A_GEN_WAV_DAC_RES_CONV2, il, ir, "weight"));
+                                res.conv2_b    = get_tensor(string_format(TN_A_GEN_WAV_DAC_RES_CONV2, il, ir, "bias"));
+                            }
+                        }
+
+                        c2w.dac_post_snake_alpha = get_tensor(string_format(TN_A_GEN_WAV_DAC_POST_SNAKE, "alpha"));
+                        c2w.dac_post_snake_beta  = get_tensor(string_format(TN_A_GEN_WAV_DAC_POST_SNAKE, "beta"));
+                        c2w.dac_post_conv_w      = get_tensor(string_format(TN_A_GEN_WAV_DAC_POST_CONV,  "weight"));
+                        c2w.dac_post_conv_b      = get_tensor(string_format(TN_A_GEN_WAV_DAC_POST_CONV,  "bias"));
+                    }
+                } break;
             case PROJECTOR_TYPE_VOXTRAL:
                 {
                     model.conv1d_1_w = get_tensor(string_format(TN_CONV1D, 1, "weight"));
@@ -3427,6 +3647,7 @@ struct clip_model_loader {
 struct clip_init_result clip_init(const char * fname, struct clip_context_params ctx_params) {
     clip_ctx * ctx_vision = nullptr;
     clip_ctx * ctx_audio = nullptr;
+    clip_ctx * ctx_gen_audio = nullptr;
 
     try {
         clip_model_loader loader(fname,
@@ -3459,16 +3680,25 @@ struct clip_init_result clip_init(const char * fname, struct clip_context_params
             }
         }
 
+        if (loader.has_gen_audio) {
+            ctx_gen_audio = new clip_ctx(ctx_params);
+            loader.load_hparams(ctx_gen_audio->model, CLIP_MODALITY_GEN_AUDIO);
+            loader.load_tensors(*ctx_gen_audio);
+            // TODO: fix warmup
+            ctx_gen_audio->buf_compute_meta.resize(ctx_gen_audio->max_nodes * ggml_tensor_overhead() + ggml_graph_overhead());
+        }
+
     } catch (const std::exception & e) {
         LOG_ERR("%s: failed to load model '%s': %s\n", __func__, fname, e.what());
 
         delete ctx_vision;
         delete ctx_audio;
+        delete ctx_gen_audio;
 
-        return {nullptr, nullptr};
+        return {nullptr, nullptr, nullptr};
     }
 
-    return {ctx_vision, ctx_audio};
+    return {ctx_vision, ctx_audio, ctx_gen_audio};
 }
 
 struct clip_cap clip_get_cap(const char * fname) {
@@ -3784,6 +4014,16 @@ int clip_n_output_tokens(const clip_ctx * ctx, const clip_image_f32 * img) {
                 const int ds = ctx->model.hparams.audio_proj_downsample_rate;
                 n_patches = ((img->nx() + ws - 1) / ws) * (ws / ds);
             } break;
+        case PROJECTOR_TYPE_QWEN3TTS_SPKENC:
+            {
+                // pooling gives one speaker embedding, whatever the clip length is
+                n_patches = 1;
+            } break;
+        case PROJECTOR_TYPE_QWEN3TTS_GEN:
+            {
+                // one hidden-state vector fed back to the talker per call
+                n_patches = 1;
+            } break;
         case PROJECTOR_TYPE_GRANITE4_VISION:
             {
                 // Per-tile output token count: each projector block outputs
@@ -3817,7 +4057,16 @@ bool clip_image_encode(struct clip_ctx * ctx, int n_threads, const clip_image_f3
 }
 
 bool clip_image_batch_encode(clip_ctx * ctx, int n_threads, const clip_image_f32_batch * imgs_c_ptr, std::vector<float> & out_batch_embd) {
-    const clip_image_f32_batch & imgs = *imgs_c_ptr;
+    clip_encode_params params;
+    params.imgs = imgs_c_ptr;
+    params.n_threads = n_threads;
+    params.out_embd = &out_batch_embd;
+
+    return clip_encode(ctx, &params);
+}
+
+bool clip_encode(struct clip_ctx * ctx, struct clip_encode_params * params) {
+    const clip_image_f32_batch & imgs = *params->imgs;
     int n_batch_cur = imgs.entries.size();
 
     // [QWEN_VIDEO] for video models, the batch dimension is used as temporal dimension for merged frames
@@ -3828,12 +4077,12 @@ bool clip_image_batch_encode(clip_ctx * ctx, int n_threads, const clip_image_f32
 
     // if buffers are not allocated, we need to do a warmup run to allocate them
     if (!ctx->is_allocated) {
-        clip_model_loader::warmup(*ctx, *imgs_c_ptr);
+        clip_model_loader::warmup(*ctx, *params->imgs);
     }
 
     // build the inference graph
     ggml_backend_sched_reset(ctx->sched.get());
-    ggml_cgraph * gf = clip_get_graph_builder(ctx, imgs)->build();
+    ggml_cgraph * gf = clip_get_graph_builder(ctx, imgs, params)->build();
     ggml_backend_sched_alloc_graph(ctx->sched.get(), gf);
 
     // set inputs
@@ -3918,8 +4167,8 @@ bool clip_image_batch_encode(clip_ctx * ctx, int n_threads, const clip_image_f32
         }
         set_input_f32("inp_raw", inp_raw);
 
-    } else {
-        // audio input
+    } else if (!(ctx->proj_type() == PROJECTOR_TYPE_QWEN3TTS_GEN && params->gen_process == CLIP_GEN_PROCESS_GEN_WAV)) {
+        // audio input, code2wav is not here: its only input is "inp_codes", set in the switch below
         GGML_ASSERT(imgs.entries.size() == 1);
 
         const auto & mel_inp = imgs.entries[0];
@@ -4475,9 +4724,77 @@ bool clip_image_batch_encode(clip_ctx * ctx, int n_threads, const clip_image_f32
         case PROJECTOR_TYPE_COGVLM:
         case PROJECTOR_TYPE_YASA2:
         case PROJECTOR_TYPE_GEMMA4UA:
+        case PROJECTOR_TYPE_QWEN3TTS_SPKENC:
             {
                 // do nothing
             } break;
+        case PROJECTOR_TYPE_QWEN3TTS_GEN:
+            {
+                if (params->gen_process == CLIP_GEN_PROCESS_GEN_WAV) {
+                    GGML_ASSERT(params->codes != nullptr);
+
+                    // frame-major input to group-major, rear-padded with code 0 up to one window
+                    const int64_t n_codes  = model.gen_code_head_w->ne[2] + 1;
+                    const int64_t n_frames_w = hparams.wav_tfm_swa;
+                    const int64_t n_frames   = (int64_t) params->codes->size() / n_codes;
+                    GGML_ASSERT(n_frames > 0 && n_frames <= n_frames_w);
+
+                    // codes are used as ggml_get_rows indices, so check them against the codebook vocab
+                    const int64_t vocab_first = model.c2w.quant_first_cb_w->ne[1];
+                    const int64_t vocab_rest  = model.c2w.quant_rest_cb_w->ne[1];
+                    for (int64_t f = 0; f < n_frames; f++) {
+                        for (int64_t g = 0; g < n_codes; g++) {
+                            const int32_t c = (*params->codes)[f * n_codes + g];
+                            const int64_t vocab = (g == 0) ? vocab_first : vocab_rest;
+                            if (c < 0 || (int64_t) c >= vocab) {
+                                LOG_ERR("%s: code out of range (frame %lld, group %lld, code %d, vocab %lld)\n",
+                                        __func__, (long long) f, (long long) g, c, (long long) vocab);
+                                return false;
+                            }
+                        }
+                    }
+
+                    std::vector<int32_t> codes(n_frames_w * n_codes, 0);
+                    for (int64_t f = 0; f < n_frames; f++) {
+                        for (int64_t g = 0; g < n_codes; g++) {
+                            codes[g * n_frames_w + f] = (*params->codes)[f * n_codes + g];
+                        }
+                    }
+                    set_input_i32("inp_codes", codes);
+
+                    // upload the state from the previous call, or zero-fill on a cold start
+                    size_t offset = 0;
+                    for (const auto & slot : list_c2w_state_slots(hparams, model)) {
+                        ggml_tensor * t = get_inp_tensor(("state_in_" + slot.name).c_str());
+                        const size_t nb = ggml_nbytes(t);
+                        if (params->state_in && params->state_in->size() >= offset + nb) {
+                            ggml_backend_tensor_set(t, params->state_in->data() + offset, 0, nb);
+                        } else {
+                            std::vector<uint8_t> zeros(nb, 0);
+                            ggml_backend_tensor_set(t, zeros.data(), 0, nb);
+                        }
+                        offset += nb;
+                    }
+                } else {
+                    // code0 indexes gen_code_out_embd_w via ggml_get_rows; bound it
+                    const int64_t vocab0 = model.gen_code_out_embd_w->ne[1];
+                    if (params->code0 < 0 || (int64_t) params->code0 >= vocab0) {
+                        LOG_ERR("%s: code0 out of range (%d, vocab %lld)\n", __func__, params->code0, (long long) vocab0);
+                        return false;
+                    }
+                    std::vector<int32_t> code0 = { params->code0 };
+                    set_input_i32("inp_code0", code0);
+
+                    // one uniform(0,1) draw per codebook, used by do_sampling()
+                    static std::mt19937 rng{ std::random_device{}() };
+                    std::uniform_real_distribution<float> dist(0.0f, 1.0f);
+                    const int64_t n_acoustic = model.gen_code_head_w->ne[2];
+                    for (int64_t g = 0; g < n_acoustic; g++) {
+                        std::vector<float> r = { dist(rng) };
+                        set_input_f32(("inp_rand_" + std::to_string(g)).c_str(), r);
+                    }
+                }
+            } break;
         case PROJECTOR_TYPE_HUNYUANVL:
             {
                 // Compute the HunyuanVL 2D position embedding on CPU (with the
@@ -4883,7 +5200,7 @@ bool clip_image_batch_encode(clip_ctx * ctx, int n_threads, const clip_image_f32
     if (reg) {
         auto ggml_backend_set_n_threads_fn = (ggml_backend_set_n_threads_t) ggml_backend_reg_get_proc_address(reg, "ggml_backend_set_n_threads");
         if (ggml_backend_set_n_threads_fn) {
-            ggml_backend_set_n_threads_fn(ctx->backend_cpu, n_threads);
+            ggml_backend_set_n_threads_fn(ctx->backend_cpu, params->n_threads);
         }
     }
 
@@ -4893,34 +5210,90 @@ bool clip_image_batch_encode(clip_ctx * ctx, int n_threads, const clip_image_f32
         return false;
     }
 
-    // the last node is the embedding tensor
-    ggml_tensor * embeddings = ggml_graph_node(gf, -1);
+    // the last node is the embedding tensor, code2wav has no out_embd
+    ggml_tensor * embeddings = params->out_embd ? ggml_graph_node(gf, -1) : nullptr;
 
-    // sanity check (assuming that all images in batch have the same number of tokens, so we only check the first one)
-    const int n_tokens_out = embeddings->ne[1];
-    const int expected_n_tokens_out = clip_n_output_tokens(ctx, &imgs.entries[0]);
-    if (n_tokens_out != expected_n_tokens_out) {
-        LOG_ERR("%s: expected output %d tokens, got %d\n", __func__, expected_n_tokens_out, n_tokens_out);
-        GGML_ABORT("Invalid number of output tokens");
-    }
+    if (embeddings != nullptr) {
+        // sanity check (assuming that all images in batch have the same number of tokens, so we only check the first one)
+        const int n_tokens_out = embeddings->ne[1];
+        const int expected_n_tokens_out = clip_n_output_tokens(ctx, &imgs.entries[0]);
+        if (n_tokens_out != expected_n_tokens_out) {
+            LOG_ERR("%s: expected output %d tokens, got %d\n", __func__, expected_n_tokens_out, n_tokens_out);
+            GGML_ABORT("Invalid number of output tokens");
+        }
 
-    LOG_DBG("%s: output embedding shape [%d, %d, %d]\n", __func__,
-        (int)embeddings->ne[0], (int)embeddings->ne[1], (int)embeddings->ne[2]);
+        LOG_DBG("%s: output embedding shape [%d, %d, %d]\n", __func__,
+            (int)embeddings->ne[0], (int)embeddings->ne[1], (int)embeddings->ne[2]);
 
-    // copy output to user buffer if provided
-    // if output is empty, skip the copy
-    if (!out_batch_embd.empty()) {
-        if (out_batch_embd.size() != (size_t)ggml_nelements(embeddings)) {
-            LOG_ERR("%s: output buffer has %zu elements but expected %zu\n", __func__, out_batch_embd.size(), (size_t)ggml_nelements(embeddings));
-            GGML_ABORT("Output buffer size mismatch");
+        // copy output to user buffer if provided
+        // if output is empty, skip the copy
+        auto & out_batch_embd = *params->out_embd;
+        if (!out_batch_embd.empty()) {
+            if (out_batch_embd.size() != (size_t)ggml_nelements(embeddings)) {
+                LOG_ERR("%s: output buffer has %zu elements but expected %zu\n", __func__, out_batch_embd.size(), (size_t)ggml_nelements(embeddings));
+                GGML_ABORT("Output buffer size mismatch");
+            }
+            ggml_backend_tensor_get(embeddings, out_batch_embd.data(), 0, ggml_nbytes(embeddings));
+        } else {
+            LOG_WRN("%s: output buffer is empty, skipping copy\n", __func__);
         }
-        ggml_backend_tensor_get(embeddings, out_batch_embd.data(), 0, ggml_nbytes(embeddings));
-    } else {
-        LOG_WRN("%s: output buffer is empty, skipping copy\n", __func__);
     }
 
+    //
+    // for audio gen models
+    //
+
+    if (params->out_codes != nullptr) {
+        ggml_tensor * codes = ggml_graph_get_tensor(gf, "out_codes");
+        if (codes == nullptr) {
+            GGML_ABORT("out_codes requested but graph has no \"out_codes\" tensor");
+        }
+        auto & out_codes = *params->out_codes;
+        out_codes.resize(ggml_nelements(codes));
+        ggml_backend_tensor_get(codes, out_codes.data(), 0, ggml_nbytes(codes));
+    }
+    if (params->out_audio != nullptr) {
+        ggml_tensor * audio = ggml_graph_get_tensor(gf, "out_audio");
+        if (audio == nullptr) {
+            GGML_ABORT("out_audio requested but graph has no \"out_audio\" tensor");
+        }
+        auto & out_audio = *params->out_audio;
+        out_audio.resize(ggml_nelements(audio));
+        ggml_backend_tensor_get(audio, out_audio.data(), 0, ggml_nbytes(audio));
+
+        // drop the tail audio that comes from the code-0 rear padding
+        const int64_t n_codes    = model.gen_code_head_w->ne[2] + 1;
+        const int64_t n_frames_w = hparams.wav_tfm_swa;
+        const int64_t n_frames   = (int64_t) params->codes->size() / n_codes;
+        if (n_frames < n_frames_w) {
+            const size_t hop = out_audio.size() / n_frames_w;
+            out_audio.resize((size_t) n_frames * hop);
+        }
+    }
+    if (params->state_out != nullptr) {
+        auto & state_out = *params->state_out;
+        size_t total = 0;
+        for (const auto & slot : list_c2w_state_slots(hparams, model)) {
+            total += (size_t) (slot.ne0 * slot.ne1) * sizeof(float);
+        }
+        state_out.resize(total);
+        size_t offset = 0;
+        for (const auto & slot : list_c2w_state_slots(hparams, model)) {
+            ggml_tensor * t = ggml_graph_get_tensor(gf, ("state_out_" + slot.name).c_str());
+            if (t == nullptr) {
+                GGML_ABORT("state_out requested but graph has no \"state_out_%s\" tensor", slot.name.c_str());
+            }
+            const size_t nb = ggml_nbytes(t);
+            ggml_backend_tensor_get(t, state_out.data() + offset, 0, nb);
+            offset += nb;
+        }
+    }
+
+    //
     // Debug: dump final embeddings if MTMD_DEBUG_EMBEDDINGS is set
-    if (ctx->debug_output_embeddings) {
+    //
+
+    if (ctx->debug_output_embeddings && embeddings != nullptr) {
         const int64_t n_embd = embeddings->ne[0];
         const int64_t n_tokens = embeddings->ne[1];
         std::vector<float> emb_data(ggml_nelements(embeddings));
@@ -5047,6 +5420,10 @@ int clip_n_mmproj_embd(const struct clip_ctx * ctx) {
             return ctx->model.mm_ffn_down_w->ne[1];
         case PROJECTOR_TYPE_MIMO_AUDIO:
             return ctx->model.mm_2_w->ne[1];
+        case PROJECTOR_TYPE_QWEN3TTS_SPKENC:
+            return ctx->model.mm_fc_w->ne[2];
+        case PROJECTOR_TYPE_QWEN3TTS_GEN:
+            return ctx->model.gen_code_out_embd_w->ne[0];
         case PROJECTOR_TYPE_PARAKEET:
             return ctx->model.mm_1_w->ne[1];
         default:

tools/mtmd/clip.h

@@ -37,6 +37,7 @@ struct clip_image_f32_batch;
 enum clip_modality {
     CLIP_MODALITY_VISION,
     CLIP_MODALITY_AUDIO,
+    CLIP_MODALITY_GEN_AUDIO,
 };
 
 enum clip_flash_attn_type {
@@ -61,6 +62,7 @@ struct clip_context_params {
 struct clip_init_result {
     struct clip_ctx * ctx_v; // vision context
     struct clip_ctx * ctx_a; // audio context
+    struct clip_ctx * ctx_gen_a; // audio generation context
 };
 
 struct clip_init_result clip_init(const char * fname, struct clip_context_params ctx_params);
@@ -84,6 +86,33 @@ int clip_n_mmproj_embd(const struct clip_ctx * ctx);
 bool clip_image_encode      (struct clip_ctx * ctx, int n_threads, const clip_image_f32 * img, std::vector<float> & out_vec);
 bool clip_image_batch_encode(struct clip_ctx * ctx, int n_threads, const struct clip_image_f32_batch * imgs, std::vector<float> & out_batch_embd);
 
+enum clip_gen_process_type {
+    CLIP_GEN_PROCESS_GEN_UNKNOWN,
+    CLIP_GEN_PROCESS_GEN_CODE, // h_state to codes
+    CLIP_GEN_PROCESS_GEN_WAV,  // codes to raw PCM audio
+};
+struct clip_encode_params {
+    int n_threads = 1;
+    const clip_image_f32_batch * imgs = nullptr;
+    std::vector<float> * out_embd = nullptr;
+
+    // for audio gen, imgs has exactly one entry: hidden state from backbone (GEN_CODE) or unused (GEN_WAV)
+    clip_gen_process_type gen_process = CLIP_GEN_PROCESS_GEN_UNKNOWN;
+
+    // GEN_CODE: out_embd receives the embd to feed back to the backbone
+    int32_t code0 = 0; // semantic code sampled by the backbone
+    int32_t top_k = 50;
+    float   top_p = 1.0f;
+    std::vector<int32_t> * out_codes = nullptr; // this frame's 16 sampled codes
+
+    // GEN_WAV
+    const std::vector<int32_t> * codes = nullptr;     // this frame's 16 RVQ codes
+    std::vector<float> * out_audio = nullptr;         // decoded PCM samples, F32
+    const std::vector<uint8_t> * state_in  = nullptr; // state from previous call, null or wrong size means cold start
+    std::vector<uint8_t> *       state_out = nullptr; // state for the next call
+};
+bool clip_encode(struct clip_ctx * ctx, struct clip_encode_params * params);
+
 bool clip_is_llava(const struct clip_ctx * ctx);
 // note for contributor: this clip_is_(model) pattern is deprecated
 //                       do NOT add new functions like this

tools/mtmd/models/models.h

@@ -2,6 +2,11 @@
 
 #include "../clip-graph.h"
 
+#include <map>
+#include <string>
+#include <utility>
+#include <vector>
+
 /*
  * IMPORTANT: The mtmd module does NOT accept pull requests that are fully or predominantly AI-generated.
  * We encourage human contributors to ensure the quality and reliability of the codebase.
@@ -215,6 +220,111 @@ struct clip_graph_mimo_audio : clip_graph {
     ggml_cgraph * build() override;
 };
 
+struct clip_graph_qwen3tts_spkenc : clip_graph {
+    clip_graph_qwen3tts_spkenc(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
+    ggml_cgraph * build() override;
+
+    ggml_tensor * conv1d_same(ggml_tensor * x, ggml_tensor * w, ggml_tensor * b, int dilation) const;
+    ggml_tensor * res2net(ggml_tensor * x, const clip_layer & layer, int dilation, int scale) const;
+    ggml_tensor * se_block(ggml_tensor * x, const clip_layer & layer) const;
+    ggml_tensor * se_res2net_block(ggml_tensor * x, const clip_layer & layer, int dilation, int scale) const;
+    ggml_tensor * attentive_stats_pool(ggml_tensor * x) const;
+};
+
+struct clip_graph_qwen3tts_gen : clip_graph {
+    clip_graph_qwen3tts_gen(clip_ctx * ctx, const clip_image_f32 & img, clip_gen_process_type gen_process, int top_k, float top_p)
+        : clip_graph(ctx, img), gen_process(gen_process), top_k(top_k), top_p(top_p) {}
+    ggml_cgraph * build() override;
+
+    // which sub-graph build() constructs, fixed at graph-build time
+    clip_gen_process_type gen_process;
+
+    // sampling params, fixed at graph-build time (GEN_CODE only)
+    int   top_k;
+    float top_p;
+
+    //
+    // code_gen: backbone hidden state + sampled code0 -> 16 RVQ codes
+    // MTP-style code predictor, one token per codebook
+    //
+    struct code_gen : clip_graph {
+        code_gen(const clip_graph & parent, int top_k, float top_p)
+            : clip_graph(parent), top_k(top_k), top_p(top_p) {}
+        ggml_cgraph * build() override { GGML_ABORT("call prefill()/step() instead"); }
+
+        int   top_k;
+        float top_p;
+
+        ggml_tensor * cache_set(ggml_tensor * cache, int row_idx, ggml_tensor * value) const;
+        ggml_tensor * do_sampling(ggml_tensor * logits, ggml_tensor * inp_rand) const;
+
+        ggml_tensor * const_i32(ggml_tensor * anchor, float value) const;
+        ggml_tensor * causal_mask_row(int64_t n_kv_pad, int pos) const;
+        ggml_tensor * project_in(ggml_tensor * cur) const;
+
+        ggml_tensor * layer_forward(
+                ggml_tensor * cur,
+                const clip_layer & layer,
+                ggml_tensor * inp_pos,
+                ggml_tensor * kq_mask,
+                ggml_tensor *& k_cache_layer,
+                ggml_tensor *& v_cache_layer,
+                int64_t n_kv_pad,
+                int pos,
+                int il) const;
+
+        void prefill(
+                std::vector<ggml_tensor *> & k_cache,
+                std::vector<ggml_tensor *> & v_cache,
+                ggml_tensor *& out_code_cache,
+                ggml_tensor * h_state,
+                ggml_tensor * code0_embd,
+                ggml_tensor * inp_rand) const;
+
+        ggml_tensor * step(
+                std::vector<ggml_tensor *> & k_cache,
+                std::vector<ggml_tensor *> & v_cache,
+                ggml_tensor * out_code_cache,
+                ggml_tensor * inp_rand,
+                int step_idx) const;
+    };
+
+    //
+    // code2wav: RVQ codes -> raw PCM (quantizer + pre_conv + pre_transformer + upsample + DAC).
+    //
+    struct code2wav : clip_graph {
+        code2wav(const clip_graph & parent) : clip_graph(parent) {}
+        ggml_cgraph * build() override { GGML_ABORT("call decode() instead"); }
+
+        // state_in: previous call's persisted state, by slot name (see list_c2w_state_slots())
+        std::map<std::string, ggml_tensor *> state_in;
+        // state_out: this call's state to persist, added to the graph outputs by build()
+        mutable std::vector<std::pair<std::string, ggml_tensor *>> state_out;
+
+        // stateful conv ops: read/update their state via state_in/state_out[state_name]
+        ggml_tensor * causal_conv1d(ggml_tensor * x, ggml_tensor * w, ggml_tensor * b, int dilation, const std::string & state_name) const;
+        ggml_tensor * causal_conv1d_dw(ggml_tensor * x, ggml_tensor * w, ggml_tensor * b, const std::string & state_name) const;
+        ggml_tensor * causal_conv_transpose1d(ggml_tensor * x, ggml_tensor * w, ggml_tensor * b, int stride, const std::string & state_name) const;
+        ggml_tensor * snake(ggml_tensor * x, ggml_tensor * alpha, ggml_tensor * beta) const;
+
+        ggml_tensor * quant_decode(ggml_tensor * inp_codes) const;
+        ggml_tensor * tfm_layer_forward(ggml_tensor * cur, const clip_layer & layer, int il) const;
+        ggml_tensor * convnext_block(ggml_tensor * x, const clip_code2wav::upsample_block & blk, const std::string & state_prefix) const;
+        ggml_tensor * dac_res_unit(ggml_tensor * x, const clip_code2wav::dac_res & res, int dilation, const std::string & state_name) const;
+
+        // inp_codes [1, n_codes] I32 -> this frame's audio samples [n_samples] F32, clamped to [-1, 1]
+        ggml_tensor * decode(ggml_tensor * inp_codes) const;
+    };
+};
+
+// one persisted state buffer used by code2wav, see qwen3tts-gen.cpp
+struct c2w_state_slot {
+    std::string name;
+    int64_t     ne0;
+    int64_t     ne1;
+};
+std::vector<c2w_state_slot> list_c2w_state_slots(const clip_hparams & hparams, const clip_model & model);
+
 struct clip_graph_kimik25 : clip_graph {
     clip_graph_kimik25(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
     ggml_cgraph * build() override;

tools/mtmd/models/qwen3tts-gen.cpp

@@ -0,0 +1,766 @@
+#include "models.h"
+
+#include <string>
+
+// on-device sampling: top-k, top-p, then a random draw
+ggml_tensor * clip_graph_qwen3tts_gen::code_gen::do_sampling(ggml_tensor * logits, ggml_tensor * inp_rand) const {
+    logits = ggml_reshape_1d(ctx0, logits, ggml_nelements(logits));
+    const int64_t n_vocab = logits->ne[0];
+
+    // sort a's rows by idx
+    auto sort_by = [this](ggml_tensor * a, ggml_tensor * idx) {
+        ggml_tensor * a2d = ggml_reshape_2d(ctx0, a, 1, a->ne[0]);
+        return ggml_reshape_1d(ctx0, ggml_get_rows(ctx0, a2d, idx), idx->ne[0]);
+    };
+
+    ggml_tensor * cur        = logits;
+    ggml_tensor * candidates = nullptr; // maps row index back to vocab id
+
+    if (top_k > 0 && top_k < n_vocab) {
+        ggml_tensor * idx = ggml_top_k(ctx0, cur, top_k);
+        candidates = idx;
+        cur        = sort_by(cur, idx);
+        cb(cur, "sample_top_k_logits", -1);
+    }
+
+    if (top_p < 1.0f) {
+        ggml_tensor * sorted_idx    = ggml_argsort(ctx0, cur, GGML_SORT_ORDER_DESC);
+        ggml_tensor * sorted_logits = sort_by(cur, sorted_idx);
+        candidates = candidates ? sort_by(candidates, sorted_idx) : sorted_idx;
+
+        ggml_tensor * probs = ggml_soft_max(ctx0, sorted_logits);
+        ggml_tensor * cdf   = ggml_cumsum(ctx0, probs);
+
+        // keep_mask[i] = 1 once cdf[i] crosses top_p
+        ggml_tensor * cdf_scaled = ggml_scale_bias(ctx0, cdf, -1.0f, top_p);
+        ggml_tensor * keep_mask  = ggml_step(ctx0, cdf_scaled);
+        ggml_tensor * idxf       = ggml_sum(ctx0, keep_mask);
+        idxf = ggml_clamp(ctx0, idxf, 0.0f, (float) keep_mask->ne[0] - 1);
+        ggml_tensor * ones = ggml_scale_bias(ctx0, idxf, 0.0f, 1.0f);
+
+        // top-p must include the crossing element, so force it to 1
+        ggml_tensor * keep_mask_2d = ggml_reshape_2d(ctx0, keep_mask, 1, keep_mask->ne[0]);
+        keep_mask_2d = ggml_set_rows(ctx0, keep_mask_2d, ones, ggml_cast(ctx0, idxf, GGML_TYPE_I32));
+        keep_mask    = ggml_reshape_1d(ctx0, keep_mask_2d, keep_mask->ne[0]);
+
+        // log(1) = 0 (keep), log(0) = -inf (drop)
+        ggml_tensor * bias = ggml_log(ctx0, keep_mask);
+        cur = ggml_add(ctx0, sorted_logits, bias);
+        cb(cur, "sample_top_p_logits", -1);
+    }
+
+    // draw one token: find where the cdf crosses inp_rand
+    ggml_tensor * probs  = ggml_soft_max(ctx0, cur);
+    ggml_tensor * cumsum = ggml_cumsum(ctx0, probs);
+
+    ggml_tensor * diff       = ggml_sub(ctx0, cumsum, inp_rand);
+    ggml_tensor * cross_mask = ggml_step(ctx0, diff);
+    ggml_tensor * idxf       = ggml_sum(ctx0, cross_mask);
+    ggml_tensor * idx        = ggml_cast(ctx0, ggml_scale_bias(ctx0, idxf, -1.0f, (float) cross_mask->ne[0]), GGML_TYPE_I32);
+
+    if (candidates) {
+        ggml_tensor * cand_2d = ggml_reshape_2d(ctx0, candidates, 1, candidates->ne[0]);
+        idx = ggml_get_rows(ctx0, cand_2d, idx);
+    }
+    cb(idx, "sample_token_id", -1);
+
+    return idx;
+}
+
+// returns a new cache with row row_idx set to value
+ggml_tensor * clip_graph_qwen3tts_gen::code_gen::cache_set(ggml_tensor * cache, int row_idx, ggml_tensor * value) const {
+    const int64_t n_embd  = cache->ne[0];
+    const int64_t n_cache = cache->ne[1];
+    GGML_ASSERT(row_idx >= 0 && row_idx < n_cache);
+
+    // append value as the last row, then gather it back into place
+    ggml_tensor * value_2d  = ggml_reshape_2d(ctx0, value, n_embd, 1);
+    ggml_tensor * cache_ext = ggml_concat(ctx0, cache, value_2d, 1); // [n_embd, n_cache + 1]
+
+    // gather indices [0..row_idx-1, n_cache, row_idx+1..n_cache-1]
+    // built via concat, since ggml_set_rows needs F32/F16 values, not an I32 index array
+    ggml_tensor * idx = const_i32(cache, (float) n_cache);
+    if (row_idx > 0) {
+        ggml_tensor * prefix = ggml_cast(ctx0, ggml_arange(ctx0, 0.0f, (float) row_idx, 1.0f), GGML_TYPE_I32);
+        idx = ggml_concat(ctx0, prefix, idx, 0);
+    }
+    if (row_idx < n_cache - 1) {
+        ggml_tensor * suffix = ggml_cast(ctx0, ggml_arange(ctx0, (float) (row_idx + 1), (float) n_cache, 1.0f), GGML_TYPE_I32);
+        idx = ggml_concat(ctx0, idx, suffix, 0);
+    }
+
+    ggml_tensor * result = ggml_get_rows(ctx0, cache_ext, idx);
+    cb(result, "cache_set_out", -1);
+    return result;
+}
+
+// builds a const i32 with no host upload: view a tensor, zero it via scale, add value, cast to i32
+ggml_tensor * clip_graph_qwen3tts_gen::code_gen::const_i32(ggml_tensor * anchor, float value) const {
+    ggml_tensor * v = ggml_view_1d(ctx0, anchor, 1, 0);
+    if (v->type != GGML_TYPE_F32) {
+        v = ggml_cast(ctx0, v, GGML_TYPE_F32);
+    }
+    return ggml_cast(ctx0, ggml_scale_bias(ctx0, v, 0.0f, value), GGML_TYPE_I32);
+}
+
+// causal keep-mask row for a query at position pos, window size n_kv_pad
+ggml_tensor * clip_graph_qwen3tts_gen::code_gen::causal_mask_row(int64_t n_kv_pad, int pos) const {
+    ggml_tensor * ones = ggml_fill(ctx0, ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_kv_pad, n_kv_pad), 1.0f);
+    ggml_tensor * keep = ggml_tri(ctx0, ones, GGML_TRI_TYPE_LOWER_DIAG);
+    ggml_tensor * row  = ggml_view_1d(ctx0, keep, n_kv_pad, (size_t) pos * keep->nb[1]);
+    ggml_tensor * mask = ggml_log(ctx0, row); // 0 = keep, -inf = masked
+    return ggml_reshape_4d(ctx0, mask, n_kv_pad, 1, 1, 1);
+}
+
+// talker hidden size -> predictor hidden size (small_to_mtp_projection)
+ggml_tensor * clip_graph_qwen3tts_gen::code_gen::project_in(ggml_tensor * cur) const {
+    if (!model.gen_code_proj_in_w) {
+        return cur;
+    }
+    cur = ggml_mul_mat(ctx0, model.gen_code_proj_in_w, cur);
+    if (model.gen_code_proj_in_b) {
+        cur = ggml_add(ctx0, cur, model.gen_code_proj_in_b);
+    }
+    return cur;
+}
+
+// one transformer layer at position pos; writes k/v into k_cache_layer/v_cache_layer at row pos
+ggml_tensor * clip_graph_qwen3tts_gen::code_gen::layer_forward(
+        ggml_tensor * cur,
+        const clip_layer & layer,
+        ggml_tensor * inp_pos,
+        ggml_tensor * kq_mask,
+        ggml_tensor *& k_cache_layer,
+        ggml_tensor *& v_cache_layer,
+        int64_t n_kv_pad,
+        int pos,
+        int il) const {
+    const int     n_head    = hparams.n_head;
+    const int     n_head_kv = hparams.n_head_kv;
+    const int64_t d_head    = layer.q_w->ne[1] / n_head; // real head_dim, not n_embd / n_head
+    const float   kq_scale  = 1.0f / sqrtf((float) d_head);
+
+    ggml_tensor * residual = cur;
+
+    ggml_tensor * h = ggml_rms_norm(ctx0, cur, hparams.eps);
+    h = ggml_mul(ctx0, h, layer.ln_1_w);
+
+    ggml_tensor * q = ggml_mul_mat(ctx0, layer.q_w, h);
+    ggml_tensor * k = ggml_mul_mat(ctx0, layer.k_w, h);
+    ggml_tensor * v = ggml_mul_mat(ctx0, layer.v_w, h);
+
+    q = ggml_reshape_3d(ctx0, q, d_head, n_head, 1);
+    k = ggml_reshape_3d(ctx0, k, d_head, n_head_kv, 1);
+
+    q = ggml_rms_norm(ctx0, q, hparams.eps);
+    q = ggml_mul(ctx0, q, layer.q_norm);
+    k = ggml_rms_norm(ctx0, k, hparams.eps);
+    k = ggml_mul(ctx0, k, layer.k_norm);
+
+    q = ggml_rope_ext(ctx0, q, inp_pos, nullptr, (int) d_head, GGML_ROPE_TYPE_NEOX, 0,
+                      hparams.rope_theta, 1.0f, 0.0f, 1.0f, 0.0f, 0.0f);
+    k = ggml_rope_ext(ctx0, k, inp_pos, nullptr, (int) d_head, GGML_ROPE_TYPE_NEOX, 0,
+                      hparams.rope_theta, 1.0f, 0.0f, 1.0f, 0.0f, 0.0f);
+
+    // write k/v into the cache at row pos, flat layout
+    ggml_tensor * k_flat = ggml_reshape_1d(ctx0, k, d_head * n_head_kv);
+    k_cache_layer = cache_set(k_cache_layer, pos, k_flat);
+    v_cache_layer = cache_set(v_cache_layer, pos, v);
+
+    ggml_tensor * q_cur = ggml_reshape_4d(ctx0, q, d_head, n_head, 1, 1);
+    ggml_tensor * k_cur = ggml_reshape_4d(ctx0, k_cache_layer, d_head, n_head_kv, n_kv_pad, 1);
+    ggml_tensor * v_cur = ggml_reshape_4d(ctx0, v_cache_layer, d_head, n_head_kv, n_kv_pad, 1);
+
+    ggml_tensor * attn_out = build_attn(layer.o_w, layer.o_b, q_cur, k_cur, v_cur, kq_mask, kq_scale, il);
+
+    cur = ggml_add(ctx0, residual, attn_out);
+
+    ggml_tensor * h2 = ggml_rms_norm(ctx0, cur, hparams.eps);
+    h2 = ggml_mul(ctx0, h2, layer.ln_2_w);
+
+    ggml_tensor * gate = ggml_mul_mat(ctx0, layer.ff_gate_w, h2);
+    ggml_tensor * up   = ggml_mul_mat(ctx0, layer.ff_up_w, h2);
+    ggml_tensor * gu   = ggml_swiglu_split(ctx0, gate, up);
+    ggml_tensor * down = ggml_mul_mat(ctx0, layer.ff_down_w, gu);
+
+    return ggml_add(ctx0, cur, down);
+}
+
+// position 0: hidden bridge, seeds the k/v cache, no sampling
+// position 1: embed(code0), sample with lm_head[0], write out_code_cache[1]
+void clip_graph_qwen3tts_gen::code_gen::prefill(
+        std::vector<ggml_tensor *> & k_cache,
+        std::vector<ggml_tensor *> & v_cache,
+        ggml_tensor *& out_code_cache,
+        ggml_tensor * h_state,
+        ggml_tensor * code0_embd,
+        ggml_tensor * inp_rand) const {
+    const int64_t n_kv_pad = k_cache[0]->ne[1];
+
+    {
+        ggml_tensor * cur     = project_in(h_state);
+        ggml_tensor * kq_mask = causal_mask_row(n_kv_pad, 0);
+        ggml_tensor * inp_pos = const_i32(k_cache[0], 0.0f);
+        for (size_t il = 0; il < model.layers.size(); il++) {
+            cur = layer_forward(cur, model.layers[il], inp_pos, kq_mask, k_cache[il], v_cache[il], n_kv_pad, 0, (int) il);
+        }
+        // position 0's output is unused, it only seeded the cache
+    }
+
+    {
+        ggml_tensor * cur     = project_in(code0_embd);
+        ggml_tensor * kq_mask = causal_mask_row(n_kv_pad, 1);
+        ggml_tensor * inp_pos = const_i32(k_cache[0], 1.0f);
+        for (size_t il = 0; il < model.layers.size(); il++) {
+            cur = layer_forward(cur, model.layers[il], inp_pos, kq_mask, k_cache[il], v_cache[il], n_kv_pad, 1, (int) il);
+        }
+
+        cur = ggml_rms_norm(ctx0, cur, hparams.eps);
+        cur = ggml_mul(ctx0, cur, model.gen_code_norm_w);
+
+        ggml_tensor * head_w = model.gen_code_head_w;
+        ggml_tensor * head_g = ggml_view_2d(ctx0, head_w, head_w->ne[0], head_w->ne[1], head_w->nb[1], 0); // lm_head[0]
+        ggml_tensor * logits = ggml_mul_mat(ctx0, head_g, cur);
+
+        ggml_tensor * sampled = do_sampling(logits, inp_rand);
+        out_code_cache = cache_set(out_code_cache, 1, sampled);
+    }
+}
+
+// one decode step of code_predictor
+// at step_idx g:
+// - read code from out_code_cache[g], then embed it with codebook table g-1
+// - write new kv at cache row g+1, sample with lm_head[g]
+// - write result to out_code_cache[g+1]
+// step_idx must be in [1, n_acoustic - 1]
+ggml_tensor * clip_graph_qwen3tts_gen::code_gen::step(
+        std::vector<ggml_tensor *> & k_cache,
+        std::vector<ggml_tensor *> & v_cache,
+        ggml_tensor * out_code_cache,
+        ggml_tensor * inp_rand,
+        int step_idx) const {
+    const int64_t n_acoustic = model.gen_code_head_w->ne[2];
+    GGML_ASSERT(step_idx >= 1 && step_idx < n_acoustic);
+    GGML_ASSERT(k_cache.size() == model.layers.size());
+    GGML_ASSERT(v_cache.size() == model.layers.size());
+
+    const int64_t n_kv_pad = k_cache[0]->ne[1];
+    const int     pos      = step_idx + 1; // new cache row and RoPE position
+
+    // embed the previous code via this step's codebook table (rows are already scalars)
+    ggml_tensor * code_in = ggml_view_1d(ctx0, out_code_cache, 1, (size_t) step_idx * out_code_cache->nb[1]);
+
+    ggml_tensor * embd_w = model.gen_code_embd_w; // [n_embd_talker, vocab, n_acoustic]
+    ggml_tensor * embd_g = ggml_view_2d(ctx0, embd_w, embd_w->ne[0], embd_w->ne[1], embd_w->nb[1],
+                                        (size_t) (step_idx - 1) * embd_w->nb[2]);
+    ggml_tensor * cur = ggml_get_rows(ctx0, embd_g, code_in);
+    cur = ggml_reshape_1d(ctx0, cur, cur->ne[0]);
+    cb(cur, "step_embd_in", step_idx);
+
+    cur = project_in(cur);
+    cb(cur, "step_proj_in", step_idx);
+
+    ggml_tensor * kq_mask = causal_mask_row(n_kv_pad, pos);
+    ggml_tensor * inp_pos = const_i32(k_cache[0], (float) pos);
+
+    for (size_t il = 0; il < model.layers.size(); il++) {
+        cur = layer_forward(cur, model.layers[il], inp_pos, kq_mask, k_cache[il], v_cache[il], n_kv_pad, pos, (int) il);
+        cb(cur, "step_layer_out", (int) il);
+    }
+
+    // final norm, this step's lm_head, sample, write the result
+    cur = ggml_rms_norm(ctx0, cur, hparams.eps);
+    cur = ggml_mul(ctx0, cur, model.gen_code_norm_w);
+
+    ggml_tensor * head_w = model.gen_code_head_w; // [n_embd_pred, vocab, n_acoustic]
+    ggml_tensor * head_g = ggml_view_2d(ctx0, head_w, head_w->ne[0], head_w->ne[1], head_w->nb[1],
+                                        (size_t) step_idx * head_w->nb[2]);
+    ggml_tensor * logits = ggml_mul_mat(ctx0, head_g, cur);
+    cb(logits, "step_logits", step_idx);
+
+    ggml_tensor * sampled = do_sampling(logits, inp_rand);
+    cb(sampled, "step_sampled", step_idx);
+
+    return cache_set(out_code_cache, pos, sampled);
+}
+
+// causal conv1d, stride 1: prepend persisted left-context instead of zero-padding, then a plain conv
+// x: [T, IC] (T-first). w: [K, IC, OC]. state_name empty means K == 1 (no left-context). returns [T, OC]
+ggml_tensor * clip_graph_qwen3tts_gen::code2wav::causal_conv1d(ggml_tensor * x, ggml_tensor * w, ggml_tensor * b, int dilation, const std::string & state_name) const {
+    const int K   = (int) w->ne[0];
+    const int pad = (K - 1) * dilation;
+
+    ggml_tensor * x_full = x;
+    if (pad > 0) {
+        ggml_tensor * left = state_in.at(state_name); // [pad, IC]
+        x_full = ggml_concat(ctx0, left, x, 0);
+    }
+    ggml_tensor * y = ggml_conv_1d(ctx0, w, x_full, 1, 0, dilation); // [T, OC, 1]
+    y = ggml_reshape_2d(ctx0, y, y->ne[0], y->ne[1]);
+    if (b) {
+        y = ggml_add(ctx0, y, ggml_reshape_2d(ctx0, b, 1, b->ne[0]));
+    }
+    if (pad > 0) {
+        ggml_tensor * new_left = ggml_cont(ctx0, ggml_view_2d(ctx0, x_full, pad, x_full->ne[1], x_full->nb[1],
+                                                              (size_t) (x_full->ne[0] - pad) * x_full->nb[0]));
+        state_out.push_back({state_name, new_left});
+    }
+    return y;
+}
+
+// causal depthwise conv1d, stride 1, dilation 1, kernel from w's shape.
+// x: [T, C]. w: [K, 1, C]. returns [T, C]. see causal_conv1d for the state contract.
+ggml_tensor * clip_graph_qwen3tts_gen::code2wav::causal_conv1d_dw(ggml_tensor * x, ggml_tensor * w, ggml_tensor * b, const std::string & state_name) const {
+    const int K   = (int) w->ne[0];
+    const int pad = K - 1;
+
+    ggml_tensor * x_full = x;
+    if (pad > 0) {
+        ggml_tensor * left = state_in.at(state_name); // [pad, C]
+        x_full = ggml_concat(ctx0, left, x, 0);
+    }
+    ggml_tensor * y = ggml_conv_1d_dw(ctx0, w, x_full, 1, 0, 1); // [T, C, 1]
+    y = ggml_reshape_2d(ctx0, y, y->ne[0], y->ne[1]);
+    if (b) {
+        y = ggml_add(ctx0, y, ggml_reshape_2d(ctx0, b, 1, b->ne[0]));
+    }
+    if (pad > 0) {
+        ggml_tensor * new_left = ggml_cont(ctx0, ggml_view_2d(ctx0, x_full, pad, x_full->ne[1], x_full->nb[1],
+                                                              (size_t) (x_full->ne[0] - pad) * x_full->nb[0]));
+        state_out.push_back({state_name, new_left});
+    }
+    return y;
+}
+
+// causal ConvTranspose1d, the (kernel - stride) overlap tail is kept as state for the next call
+// x: [T, IC], w: [K, OC, IC]. state_name empty means K == stride (no overlap). returns [T * stride, OC]
+ggml_tensor * clip_graph_qwen3tts_gen::code2wav::causal_conv_transpose1d(ggml_tensor * x, ggml_tensor * w, ggml_tensor * b, int stride, const std::string & state_name) const {
+    const int     K        = (int) w->ne[0];
+    const int     OC       = (int) w->ne[1];
+    const int     trim     = K - stride;
+    const int64_t emit_len = x->ne[0] * stride;
+
+    // transposed conv as GEMM + col2im scatter-add, y: [emit_len + trim, OC]
+    ggml_tensor * w2  = ggml_reshape_2d(ctx0, w, (int64_t) K * OC, w->ne[2]);
+    w2                = ggml_cont(ctx0, ggml_transpose(ctx0, w2));
+    ggml_tensor * xt  = ggml_cont(ctx0, ggml_transpose(ctx0, x));
+    ggml_tensor * col = ggml_mul_mat(ctx0, w2, xt);
+    ggml_tensor * y   = ggml_col2im_1d(ctx0, col, stride, OC, 0);
+
+    ggml_tensor * out = y;
+    if (trim > 0) {
+        ggml_tensor * tail = state_in.at(state_name); // [trim, OC]
+        ggml_tensor * head = ggml_add(ctx0, ggml_view_2d(ctx0, y, trim, y->ne[1], y->nb[1], 0), tail);
+        if (emit_len > trim) {
+            ggml_tensor * middle = ggml_view_2d(ctx0, y, emit_len - trim, y->ne[1], y->nb[1], (size_t) trim * y->nb[0]);
+            out = ggml_concat(ctx0, head, middle, 0);
+        } else {
+            out = head;
+        }
+        ggml_tensor * new_tail = ggml_cont(ctx0, ggml_view_2d(ctx0, y, trim, y->ne[1], y->nb[1], (size_t) emit_len * y->nb[0]));
+        state_out.push_back({state_name, new_tail});
+    }
+    if (b) {
+        out = ggml_add(ctx0, out, ggml_reshape_2d(ctx0, b, 1, b->ne[0]));
+    }
+    return out;
+}
+
+// SnakeBeta activation: y = x + sin(alpha*x)^2 * inv_beta (alpha/inv_beta folded via exp/reciprocal at conversion time)
+// x: [T, C]. alpha/beta: [C], broadcasts over T
+ggml_tensor * clip_graph_qwen3tts_gen::code2wav::snake(ggml_tensor * x, ggml_tensor * alpha, ggml_tensor * beta) const {
+    ggml_tensor * a = ggml_reshape_2d(ctx0, alpha, 1, alpha->ne[0]);
+    ggml_tensor * b = ggml_reshape_2d(ctx0, beta,  1, beta->ne[0]);
+
+    // expand reshapes first so mul/sin/sqr/mul/add lands as consecutive nodes, letting backends fuse them
+    ggml_build_forward_expand(gf, a);
+    ggml_build_forward_expand(gf, b);
+
+    ggml_tensor * s = ggml_sin(ctx0, ggml_mul(ctx0, x, a));
+    s = ggml_sqr(ctx0, s);
+    s = ggml_mul(ctx0, s, b);
+    return ggml_add(ctx0, x, s);
+}
+
+// RVQ codebook decode: T frames of 16 codes -> 512-dim hidden (C-first, [512, T])
+// codebook 0 (semantic) and 1..15 (acoustic) sum within their group, project separately, then add
+ggml_tensor * clip_graph_qwen3tts_gen::code2wav::quant_decode(ggml_tensor * inp_codes) const {
+    const auto & c2w = model.c2w;
+    const int64_t T = inp_codes->ne[0];
+
+    // ids for codebook group g over all T frames, [T] I32
+    auto group_ids = [&](int g) {
+        return ggml_view_1d(ctx0, inp_codes, T, (size_t) g * inp_codes->nb[1]);
+    };
+
+    ggml_tensor * sem     = ggml_get_rows(ctx0, c2w.quant_first_cb_w, group_ids(0)); // [256, T]
+    ggml_tensor * sem_out = ggml_mul_mat(ctx0, c2w.quant_first_out_w, sem);          // [512, T]
+
+    ggml_tensor * acc = nullptr;
+    const int64_t n_acoustic = c2w.quant_rest_cb_w->ne[2];
+    for (int g = 1; g <= n_acoustic; g++) {
+        ggml_tensor * cb_g  = ggml_view_2d(ctx0, c2w.quant_rest_cb_w, c2w.quant_rest_cb_w->ne[0], c2w.quant_rest_cb_w->ne[1],
+                                           c2w.quant_rest_cb_w->nb[1], (size_t) (g - 1) * c2w.quant_rest_cb_w->nb[2]);
+        ggml_tensor * embd = ggml_get_rows(ctx0, cb_g, group_ids(g)); // [256, T]
+        acc = acc ? ggml_add(ctx0, acc, embd) : embd;
+    }
+    ggml_tensor * ac_out = ggml_mul_mat(ctx0, c2w.quant_rest_out_w, acc); // [512, T]
+
+    ggml_tensor * hidden = ggml_add(ctx0, sem_out, ac_out);
+    cb(hidden, "wav_quant_hidden", -1);
+    return hidden;
+}
+
+// one pre_transformer layer over a batch of N = sliding_window new frames
+// attention runs over [(W-1)-frame prefix from the last batch] + [N new frames]
+// RoPE positions come from a persisted counter, so phases line up across batches
+ggml_tensor * clip_graph_qwen3tts_gen::code2wav::tfm_layer_forward(ggml_tensor * cur, const clip_layer & layer, int il) const {
+    const int     n_head    = hparams.wav_tfm_n_head;
+    const int     n_head_kv = hparams.wav_tfm_n_head_kv;
+    const int64_t d_head    = layer.q_w->ne[1] / n_head;
+    const float   kq_scale  = 1.0f / sqrtf((float) d_head);
+    const int64_t W         = hparams.wav_tfm_swa; // == N, frames per batch
+    const int64_t N         = cur->ne[1];
+    const int64_t prefix    = W - 1;
+    const int64_t total_kv  = prefix + N;
+
+    ggml_tensor * residual = cur;
+    ggml_tensor * h = ggml_rms_norm(ctx0, cur, hparams.wav_tfm_eps);
+    h = ggml_mul(ctx0, h, layer.ln_1_w);
+
+    ggml_tensor * q = ggml_mul_mat(ctx0, layer.q_w, h); // [n_head*d_head, N]
+    ggml_tensor * k = ggml_mul_mat(ctx0, layer.k_w, h); // [n_head_kv*d_head, N]
+    ggml_tensor * v = ggml_mul_mat(ctx0, layer.v_w, h); // [n_head_kv*d_head, N]
+
+    q = ggml_reshape_3d(ctx0, q, d_head, n_head, N);
+    k = ggml_reshape_3d(ctx0, k, d_head, n_head_kv, N);
+
+    // real, ever-increasing positions: base (persisted) .. base+N-1
+    ggml_tensor * base   = ggml_reshape_1d(ctx0, state_in.at("tfm_pos"), 1);
+    ggml_tensor * offset = ggml_arange(ctx0, 0.0f, (float) N, 1.0f);
+    ggml_tensor * pos    = ggml_cast(ctx0, ggml_add(ctx0, offset, base), GGML_TYPE_I32);
+
+    q = ggml_rope_ext(ctx0, q, pos, nullptr, (int) d_head, GGML_ROPE_TYPE_NEOX, 0,
+                      hparams.wav_tfm_rope_theta, 1.0f, 0.0f, 1.0f, 0.0f, 0.0f);
+    k = ggml_rope_ext(ctx0, k, pos, nullptr, (int) d_head, GGML_ROPE_TYPE_NEOX, 0,
+                      hparams.wav_tfm_rope_theta, 1.0f, 0.0f, 1.0f, 0.0f, 0.0f);
+
+    // the position counter is the same for all layers, push it once from layer 0
+    if (il == 0) {
+        state_out.push_back({"tfm_pos", ggml_scale_bias(ctx0, state_in.at("tfm_pos"), 1.0f, (float) N)});
+    }
+
+    ggml_tensor * k_new = ggml_reshape_2d(ctx0, k, d_head * n_head_kv, N);
+    ggml_tensor * v_new = ggml_reshape_2d(ctx0, v, d_head * n_head_kv, N);
+
+    ggml_tensor * old_k = state_in.at("tfm_k_" + std::to_string(il)); // [d_head*n_head_kv, W-1]
+    ggml_tensor * old_v = state_in.at("tfm_v_" + std::to_string(il));
+
+    ggml_tensor * k_full = ggml_concat(ctx0, old_k, k_new, 1); // [.., prefix+N]
+    ggml_tensor * v_full = ggml_concat(ctx0, old_v, v_new, 1);
+
+    // next batch's prefix: the last (W-1) frames of this batch
+    state_out.push_back({"tfm_k_" + std::to_string(il),
+        ggml_cont(ctx0, ggml_view_2d(ctx0, k_full, k_full->ne[0], prefix, k_full->nb[1], (size_t) N * k_full->nb[1]))});
+    state_out.push_back({"tfm_v_" + std::to_string(il),
+        ggml_cont(ctx0, ggml_view_2d(ctx0, v_full, v_full->ne[0], prefix, v_full->nb[1], (size_t) N * v_full->nb[1]))});
+
+    // banded causal mask: key j is visible to query i iff 0 <= (prefix+i) - j < W
+    ggml_tensor * pos_k = ggml_reshape_2d(ctx0, ggml_arange(ctx0, 0.0f, (float) total_kv, 1.0f), total_kv, 1);
+    ggml_tensor * pos_q = ggml_reshape_2d(ctx0, ggml_arange(ctx0, (float) prefix, (float) (prefix + N), 1.0f), 1, N);
+    ggml_tensor * pos_q_grid = ggml_repeat_4d(ctx0, pos_q, total_kv, N, 1, 1);
+    ggml_tensor * diff = ggml_sub(ctx0, pos_q_grid, pos_k); // [total_kv, N]
+
+    ggml_tensor * causal_keep = ggml_step(ctx0, ggml_scale_bias(ctx0, diff, 1.0f, 0.5f));            // diff >= 0
+    ggml_tensor * in_window   = ggml_step(ctx0, ggml_scale_bias(ctx0, diff, -1.0f, (float) W - 0.5f)); // diff < W
+    ggml_tensor * keep = ggml_mul(ctx0, causal_keep, in_window);
+
+    // on a cold start, key j is real state only when j >= prefix - tfm_pos, mask out the rest
+    ggml_tensor * warm = ggml_step(ctx0, ggml_scale_bias(ctx0, ggml_add(ctx0, pos_k, base),
+                                                         1.0f, 0.5f - (float) prefix)); // j + pos > prefix - 0.5
+    keep = ggml_mul(ctx0, keep, warm);
+
+    ggml_tensor * mask = ggml_reshape_4d(ctx0, ggml_log(ctx0, keep), total_kv, N, 1, 1); // 0 = keep, -inf = masked
+
+    ggml_tensor * q_cur = ggml_reshape_4d(ctx0, q, d_head, n_head, N, 1);
+    ggml_tensor * k_cur = ggml_reshape_4d(ctx0, k_full, d_head, n_head_kv, total_kv, 1);
+    ggml_tensor * v_cur = ggml_reshape_4d(ctx0, v_full, d_head, n_head_kv, total_kv, 1);
+
+    ggml_tensor * attn_out = build_attn(layer.o_w, layer.o_b, q_cur, k_cur, v_cur, mask, kq_scale, il);
+    if (layer.ls_1_w) {
+        attn_out = ggml_mul(ctx0, attn_out, layer.ls_1_w);
+    }
+    cur = ggml_add(ctx0, residual, attn_out);
+
+    ggml_tensor * residual2 = cur;
+    ggml_tensor * h2 = ggml_rms_norm(ctx0, cur, hparams.wav_tfm_eps);
+    h2 = ggml_mul(ctx0, h2, layer.ln_2_w);
+
+    ggml_tensor * gate = ggml_mul_mat(ctx0, layer.ff_gate_w, h2);
+    ggml_tensor * up   = ggml_mul_mat(ctx0, layer.ff_up_w, h2);
+    ggml_tensor * gu   = ggml_swiglu_split(ctx0, gate, up);
+    ggml_tensor * down = ggml_mul_mat(ctx0, layer.ff_down_w, gu);
+    if (layer.ls_2_w) {
+        down = ggml_mul(ctx0, down, layer.ls_2_w);
+    }
+    return ggml_add(ctx0, residual2, down);
+}
+
+// dwconv -> LayerNorm -> pwconv1 -> GELU -> pwconv2 -> layer scale -> residual
+// x: [T, C] T-first; LayerNorm/pwconv need C on ne0, so this transposes in and back out
+ggml_tensor * clip_graph_qwen3tts_gen::code2wav::convnext_block(ggml_tensor * x, const clip_code2wav::upsample_block & blk, const std::string & state_prefix) const {
+    ggml_tensor * residual = x;
+
+    ggml_tensor * h = causal_conv1d_dw(x, blk.dwconv_w, blk.dwconv_b, state_prefix + "_dwconv"); // [T, C]
+    ggml_tensor * hc = ggml_cont(ctx0, ggml_transpose(ctx0, h)); // [C, T]
+
+    hc = ggml_norm(ctx0, hc, 1e-6f);
+    hc = ggml_mul(ctx0, hc, blk.norm_w);
+    hc = ggml_add(ctx0, hc, blk.norm_b);
+
+    ggml_tensor * g = ggml_mul_mat(ctx0, blk.pw1_w, hc);
+    g = ggml_add(ctx0, g, blk.pw1_b);
+    g = ggml_gelu(ctx0, g);
+    g = ggml_mul_mat(ctx0, blk.pw2_w, g);
+    g = ggml_add(ctx0, g, blk.pw2_b);
+    g = ggml_mul(ctx0, g, blk.gamma);
+
+    ggml_tensor * g_t = ggml_cont(ctx0, ggml_transpose(ctx0, g)); // back to [T, C]
+    return ggml_add(ctx0, residual, g_t);
+}
+
+// SnakeBeta -> dilated causal conv (k=7) -> SnakeBeta -> pointwise causal conv (k=1) -> residual.
+// x: [T, C]. returns [T, C].
+ggml_tensor * clip_graph_qwen3tts_gen::code2wav::dac_res_unit(ggml_tensor * x, const clip_code2wav::dac_res & res, int dilation, const std::string & state_name) const {
+    ggml_tensor * residual = x;
+    ggml_tensor * h = snake(x, res.act1_alpha, res.act1_beta);
+    h = causal_conv1d(h, res.conv1_w, res.conv1_b, dilation, state_name);
+    h = snake(h, res.act2_alpha, res.act2_beta);
+    h = causal_conv1d(h, res.conv2_w, res.conv2_b, 1, ""); // k=1, no left-context needed
+    return ggml_add(ctx0, residual, h);
+}
+
+// RVQ codes -> raw PCM for a batch of N = sliding_window frames
+ggml_tensor * clip_graph_qwen3tts_gen::code2wav::decode(ggml_tensor * inp_codes) const {
+    const auto & c2w = model.c2w;
+
+    // 1. quantizer decode: N frames of 16 codes -> [512, N] (C-first)
+    ggml_tensor * hidden = quant_decode(inp_codes);
+
+    // 2. pre_conv: [512, N] -> T-first [N, 512] -> causal conv k=3 -> [N, 1024]
+    ggml_tensor * x = ggml_cont(ctx0, ggml_transpose(ctx0, hidden)); // [N, 512]
+    x = causal_conv1d(x, c2w.pre_conv_w, c2w.pre_conv_b, 1, "pre_conv"); // [N, 1024]
+    cb(x, "wav_pre_conv_out", -1);
+
+    // 3. pre_transformer: back to C-first [1024, N], project down, run the layers, project back up
+    ggml_tensor * cur = ggml_cont(ctx0, ggml_transpose(ctx0, x)); // [1024, N]
+    cur = ggml_mul_mat(ctx0, c2w.tfm_in_proj_w, cur);
+    cur = ggml_add(ctx0, cur, c2w.tfm_in_proj_b); // [512 (tfm hidden), N]
+
+    for (int il = 0; il < hparams.wav_tfm_n_layer; il++) {
+        cur = tfm_layer_forward(cur, c2w.tfm_layers[il], il);
+    }
+
+    cur = ggml_rms_norm(ctx0, cur, hparams.wav_tfm_eps);
+    cur = ggml_mul(ctx0, cur, c2w.tfm_output_norm_w);
+    cur = ggml_mul_mat(ctx0, c2w.tfm_out_proj_w, cur);
+    cur = ggml_add(ctx0, cur, c2w.tfm_out_proj_b); // [1024, N]
+    cb(cur, "wav_tfm_out", -1);
+
+    // 4. upsample: 2x (causal ConvTranspose1d, stride 2 + ConvNeXt block), back to T-first
+    // kernel == stride here, so there is no overlap tail to persist
+    x = ggml_cont(ctx0, ggml_transpose(ctx0, cur)); // [N, 1024]
+    for (size_t il = 0; il < c2w.upsample.size(); il++) {
+        const auto & up = c2w.upsample[il];
+        x = causal_conv_transpose1d(x, up.conv_w, up.conv_b, 2, "");
+        x = convnext_block(x, up, "up" + std::to_string(il));
+        cb(x, "wav_upsample_out", (int) il);
+    }
+
+    // 5. DAC decoder: conv_pre -> n blocks (SnakeBeta -> ConvTranspose1d -> 3 res units) -> conv_post
+    static constexpr int DAC_DILATIONS[3] = { 1, 3, 9 };
+
+    x = causal_conv1d(x, c2w.dac_entry_w, c2w.dac_entry_b, 1, "dac_entry");
+    cb(x, "wav_dac_entry_out", -1);
+
+    for (size_t il = 0; il < c2w.dac.size(); il++) {
+        const auto & blk = c2w.dac[il];
+        const int stride = (int) (blk.conv_w->ne[0] / 2); // kernel == 2*stride for all 4 blocks
+        const std::string blk_name = "dac" + std::to_string(il);
+        x = snake(x, blk.snake_alpha, blk.snake_beta);
+        x = causal_conv_transpose1d(x, blk.conv_w, blk.conv_b, stride, blk_name + "_tail");
+        for (size_t ir = 0; ir < blk.res.size(); ir++) {
+            x = dac_res_unit(x, blk.res[ir], DAC_DILATIONS[ir], blk_name + "_res" + std::to_string(ir));
+        }
+        cb(x, "wav_dac_block_out", (int) il);
+    }
+
+    x = snake(x, c2w.dac_post_snake_alpha, c2w.dac_post_snake_beta);
+    x = causal_conv1d(x, c2w.dac_post_conv_w, c2w.dac_post_conv_b, 1, "dac_post_conv"); // [n_samples, 1]
+
+    x = ggml_clamp(ctx0, x, -1.0f, 1.0f);
+    x = ggml_reshape_1d(ctx0, x, x->ne[0]);
+    cb(x, "wav_audio_out", -1);
+    return x;
+}
+
+// code2wav's persisted state buffers: RoPE position counter, K/V per pre_transformer layer,
+// left-context/tail per stateful conv. shape lookup only, no graph needed
+std::vector<c2w_state_slot> list_c2w_state_slots(const clip_hparams & hparams, const clip_model & model) {
+    const auto & c2w = model.c2w;
+    std::vector<c2w_state_slot> slots;
+
+    slots.push_back({"tfm_pos", 1, 1});
+
+    // prefix is (W-1) frames, the batch itself gives the other N=W frames (see tfm_layer_forward)
+    const int64_t d_head = c2w.tfm_layers[0].q_w->ne[1] / hparams.wav_tfm_n_head;
+    const int64_t kv_ch  = d_head * hparams.wav_tfm_n_head_kv;
+    const int64_t prefix = hparams.wav_tfm_swa - 1;
+    for (int il = 0; il < hparams.wav_tfm_n_layer; il++) {
+        slots.push_back({"tfm_k_" + std::to_string(il), kv_ch, prefix});
+        slots.push_back({"tfm_v_" + std::to_string(il), kv_ch, prefix});
+    }
+
+    slots.push_back({"pre_conv", c2w.pre_conv_w->ne[0] - 1, c2w.pre_conv_w->ne[1]});
+
+    for (size_t il = 0; il < c2w.upsample.size(); il++) {
+        const auto & up = c2w.upsample[il];
+        slots.push_back({"up" + std::to_string(il) + "_dwconv", up.dwconv_w->ne[0] - 1, up.dwconv_w->ne[2]});
+    }
+
+    slots.push_back({"dac_entry", c2w.dac_entry_w->ne[0] - 1, c2w.dac_entry_w->ne[1]});
+
+    static constexpr int DAC_DILATIONS[3] = { 1, 3, 9 };
+    for (size_t il = 0; il < c2w.dac.size(); il++) {
+        const auto & blk = c2w.dac[il];
+        const int64_t stride = blk.conv_w->ne[0] / 2; // kernel == 2*stride for all 4 blocks
+        const std::string blk_name = "dac" + std::to_string(il);
+        slots.push_back({blk_name + "_tail", stride, blk.conv_w->ne[1]});
+        for (size_t ir = 0; ir < blk.res.size(); ir++) {
+            const auto & res = blk.res[ir];
+            slots.push_back({blk_name + "_res" + std::to_string(ir),
+                              (res.conv1_w->ne[0] - 1) * DAC_DILATIONS[ir], res.conv1_w->ne[1]});
+        }
+    }
+
+    slots.push_back({"dac_post_conv", c2w.dac_post_conv_w->ne[0] - 1, c2w.dac_post_conv_w->ne[1]});
+
+    return slots;
+}
+
+// both sub-graphs are always built, so the topology stays constant
+// ggml_build_forward_select() then picks the one that actually runs
+ggml_cgraph * clip_graph_qwen3tts_gen::build() {
+    GGML_ASSERT(n_batch == 1); // this module only ever processes one frame at a time
+
+    int idx;
+    switch (gen_process) {
+        case CLIP_GEN_PROCESS_GEN_CODE: idx = 0; break;
+        case CLIP_GEN_PROCESS_GEN_WAV:  idx = 1; break;
+        default: GGML_ABORT("unknown gen_process");
+    }
+
+    // ---- CLIP_GEN_PROCESS_GEN_CODE: backbone hidden state -> 16 RVQ codes + next-step embd ----
+    // not build_inp_raw(), a GEN_WAV call's `img` has no hidden-state data
+    ggml_tensor * h_state = ggml_new_tensor_1d(ctx0, GGML_TYPE_F32, n_mmproj_embd);
+    ggml_set_name(h_state, "inp_raw"); // must keep this exact name, clip_encode() sets it by name
+    ggml_set_input(h_state);
+
+    ggml_tensor * code0 = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, 1);
+    ggml_set_name(code0, "inp_code0");
+    ggml_set_input(code0);
+
+    ggml_tensor * code0_embd = ggml_get_rows(ctx0, model.gen_code_out_embd_w, code0);
+    code0_embd = ggml_reshape_1d(ctx0, code0_embd, code0_embd->ne[0]);
+    cb(code0_embd, "code0_embd", -1);
+
+    const int64_t n_acoustic = model.gen_code_head_w->ne[2]; // 15
+    const int     n_codes    = (int) n_acoustic + 1;         // 16
+    const int64_t n_kv_pad   = n_codes;
+    const int     n_layer    = (int) model.layers.size();
+    const int     n_head     = hparams.n_head;
+    const int     n_head_kv  = hparams.n_head_kv;
+    const int64_t d_head     = model.layers[0].q_w->ne[1] / n_head;
+
+    // zero-filled per layer k/v caches, so masked-out rows can't hold garbage
+    std::vector<ggml_tensor *> k_cache(n_layer), v_cache(n_layer);
+    for (int il = 0; il < n_layer; il++) {
+        k_cache[il] = ggml_fill(ctx0, ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, d_head * n_head_kv, n_kv_pad), 0.0f);
+        v_cache[il] = ggml_fill(ctx0, ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, d_head * n_head_kv, n_kv_pad), 0.0f);
+    }
+
+    code_gen cg(*this, top_k, top_p);
+
+    ggml_tensor * out_code_cache = ggml_new_tensor_2d(ctx0, GGML_TYPE_I32, 1, n_codes);
+    out_code_cache = cg.cache_set(out_code_cache, 0, code0);
+
+    ggml_tensor * inp_rand0 = ggml_new_tensor_1d(ctx0, GGML_TYPE_F32, 1);
+    ggml_set_name(inp_rand0, "inp_rand_0");
+    ggml_set_input(inp_rand0);
+
+    cg.prefill(k_cache, v_cache, out_code_cache, h_state, code0_embd, inp_rand0);
+
+    for (int g = 1; g < n_acoustic; g++) {
+        ggml_tensor * inp_rand = ggml_new_tensor_1d(ctx0, GGML_TYPE_F32, 1);
+        ggml_set_name(inp_rand, ("inp_rand_" + std::to_string(g)).c_str());
+        ggml_set_input(inp_rand);
+        out_code_cache = cg.step(k_cache, v_cache, out_code_cache, inp_rand, g);
+    }
+
+    // output 1: this frame's 16 sampled codes, for the caller's code2wav window
+    ggml_tensor * out_codes = ggml_cont(ctx0, out_code_cache);
+    ggml_set_name(out_codes, "out_codes");
+    ggml_set_output(out_codes);
+
+    // output 2: sum of all 16 codebook embeddings, fed back to the talker for the next frame
+    ggml_tensor * out_embd = code0_embd;
+    for (int g = 1; g <= n_acoustic; g++) {
+        ggml_tensor * code_g = ggml_view_1d(ctx0, out_code_cache, 1, (size_t) g * out_code_cache->nb[1]);
+
+        ggml_tensor * embd_g = ggml_view_2d(ctx0, model.gen_code_embd_w, model.gen_code_embd_w->ne[0], model.gen_code_embd_w->ne[1],
+                                            model.gen_code_embd_w->nb[1], (size_t) (g - 1) * model.gen_code_embd_w->nb[2]);
+        ggml_tensor * e = ggml_get_rows(ctx0, embd_g, code_g);
+        e = ggml_reshape_1d(ctx0, e, e->ne[0]);
+
+        out_embd = ggml_add(ctx0, out_embd, e);
+    }
+    out_embd = ggml_reshape_2d(ctx0, out_embd, out_embd->ne[0], 1);
+    cb(out_embd, "gen_audio_out", -1);
+
+    // ---- CLIP_GEN_PROCESS_GEN_WAV: 16 RVQ codes -> raw PCM ----
+    const int n_frames = hparams.wav_tfm_swa; // frames per batch, == the attention window
+
+    ggml_tensor * inp_codes = ggml_new_tensor_2d(ctx0, GGML_TYPE_I32, n_frames, n_codes);
+    ggml_set_name(inp_codes, "inp_codes");
+    ggml_set_input(inp_codes);
+
+    code2wav c2w(*this);
+    for (const auto & slot : list_c2w_state_slots(hparams, model)) {
+        ggml_tensor * t = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, slot.ne0, slot.ne1);
+        ggml_set_name(t, ("state_in_" + slot.name).c_str());
+        ggml_set_input(t);
+        c2w.state_in[slot.name] = t;
+    }
+
+    ggml_tensor * out_audio = c2w.decode(inp_codes);
+    ggml_set_name(out_audio, "out_audio");
+    ggml_set_output(out_audio);
+
+    for (auto & slot : c2w.state_out) {
+        ggml_set_name(slot.second, ("state_out_" + slot.first).c_str());
+        ggml_set_output(slot.second);
+    }
+
+    // out_embd goes last, clip_encode() reads it back via ggml_graph_node(gf, -1)
+    ggml_tensor * outs[2];
+    outs[0] = out_codes; outs[1] = out_audio;
+    ggml_build_forward_select(gf, outs, 2, idx);
+    for (auto & slot : c2w.state_out) {
+        outs[0] = out_codes; outs[1] = slot.second;
+        ggml_build_forward_select(gf, outs, 2, idx);
+    }
+    outs[0] = out_embd; outs[1] = out_audio;
+    ggml_build_forward_select(gf, outs, 2, idx);
+
+    return gf;
+}

tools/mtmd/models/qwen3tts-spkenc.cpp

@@ -0,0 +1,197 @@
+#include "models.h"
+
+static constexpr int SPK_RES2NET_SCALE = 8; // enc_res2net_scale
+static constexpr int SPK_DILATIONS[3]  = { 2, 3, 4 }; // enc_dilations[1..3]
+
+// conv1d, kernel K, padding "same" (reflect), dilation d
+// x: [C, T] (ne[0]=C, ne[1]=T) -> [out_c, T]
+ggml_tensor * clip_graph_qwen3tts_spkenc::conv1d_same(ggml_tensor * x, ggml_tensor * w, ggml_tensor * b, int dilation) const {
+    const int K   = (int) w->ne[0];
+    const int IC  = (int) w->ne[1];
+    const int OC  = (int) w->ne[2];
+    const int pad = ((K - 1) * dilation) / 2;
+
+    // ggml_pad_reflect_1d pads ne[0], so bring T onto ne[0] first, same layout as im2col wants
+    ggml_tensor * x_t = ggml_cont(ctx0, ggml_transpose(ctx0, x)); // [T, IC]
+    if (pad > 0) {
+        x_t = ggml_pad_reflect_1d(ctx0, x_t, pad, pad); // [T + 2*pad, IC]
+    }
+    ggml_tensor * x4d = ggml_reshape_4d(ctx0, x_t, x_t->ne[0], IC, 1, 1);
+
+    // dummy F32 kernel, im2col only reads its shape, so a quantized w does not assert
+    ggml_tensor * dummy = ggml_new_tensor_4d(ctx0, GGML_TYPE_F32, K, IC, 1, 1);
+
+    ggml_tensor * col = ggml_im2col(ctx0, dummy, x4d, 1, 1, 0, 0, dilation, 1, false, GGML_TYPE_F32);
+    const int64_t T_out = col->ne[1];
+    col = ggml_reshape_2d(ctx0, col, (int64_t) K * IC, T_out);
+
+    ggml_tensor * w2d = ggml_reshape_2d(ctx0, w, (int64_t) K * IC, OC);
+    ggml_tensor * y   = ggml_mul_mat(ctx0, w2d, col); // [OC, T_out]
+    ggml_mul_mat_set_prec(y, GGML_PREC_F32);
+
+    ggml_tensor * b2d = ggml_reshape_2d(ctx0, b, OC, 1);
+    y = ggml_add(ctx0, y, b2d);
+    return y;
+}
+
+// Res2Net: split channel axis into `scale` chunks, chain dilated conv1d branches
+// x: [C, T] -> [C, T]
+ggml_tensor * clip_graph_qwen3tts_spkenc::res2net(ggml_tensor * x, const clip_layer & layer, int dilation, int scale) const {
+    const int64_t C  = x->ne[0];
+    const int64_t T  = x->ne[1];
+    const int64_t Cs = C / scale;
+
+    std::vector<ggml_tensor *> outs;
+    outs.reserve(scale);
+
+    auto chunk = [&](int i) -> ggml_tensor * {
+        return ggml_view_2d(ctx0, x, Cs, T, x->nb[1], (size_t) i * Cs * x->nb[0]);
+    };
+
+    ggml_tensor * prev = nullptr;
+    for (int i = 0; i < scale; i++) {
+        ggml_tensor * c = ggml_cont(ctx0, chunk(i));
+        if (i == 0) {
+            outs.push_back(c);
+            continue;
+        }
+        ggml_tensor * inp = (i >= 2) ? ggml_add(ctx0, c, prev) : c;
+        ggml_tensor * y   = conv1d_same(inp, layer.res2_conv_w[i - 1], layer.res2_conv_b[i - 1], dilation);
+        y                 = ggml_relu(ctx0, y);
+        outs.push_back(y);
+        prev = y;
+    }
+
+    ggml_tensor * acc = outs[0];
+    for (int i = 1; i < scale; i++) {
+        acc = ggml_concat(ctx0, acc, outs[i], 0);
+    }
+    return acc;
+}
+
+// squeeze-and-excitation gate. x: [C, T] -> [C, T]
+ggml_tensor * clip_graph_qwen3tts_spkenc::se_block(ggml_tensor * x, const clip_layer & layer) const {
+    // temporal mean, keepdim: transpose so T is on ne[0], reduce, transpose back
+    ggml_tensor * x_t  = ggml_cont(ctx0, ggml_transpose(ctx0, x));    // [T, C]
+    ggml_tensor * mean = ggml_mean(ctx0, x_t);                        // [1, C]
+    mean               = ggml_cont(ctx0, ggml_transpose(ctx0, mean)); // [C, 1]
+
+    ggml_tensor * h = conv1d_same(mean, layer.se_conv1_w, layer.se_conv1_b, 1);
+    h = ggml_relu(ctx0, h);
+    h = conv1d_same(h, layer.se_conv2_w, layer.se_conv2_b, 1);
+    h = ggml_sigmoid(ctx0, h); // [C, 1]
+
+    return ggml_mul(ctx0, x, h); // broadcast gate over T
+}
+
+// tdnn1 -> res2net -> tdnn2 -> se, plus residual. x: [C, T] -> [C, T]
+ggml_tensor * clip_graph_qwen3tts_spkenc::se_res2net_block(ggml_tensor * x, const clip_layer & layer, int dilation, int scale) const {
+    ggml_tensor * residual = x;
+    ggml_tensor * h  = conv1d_same(x, layer.conv_pw1_w, layer.conv_pw1_b, 1); // tdnn1
+    h = ggml_relu(ctx0, h);
+    h = res2net(h, layer, dilation, scale);
+    h = conv1d_same(h, layer.conv_pw2_w, layer.conv_pw2_b, 1); // tdnn2
+    h = ggml_relu(ctx0, h);
+    h = se_block(h, layer);
+    return ggml_add(ctx0, h, residual);
+}
+
+// attentive statistics pooling. x: [C, T] -> [2*C, 1]
+ggml_tensor * clip_graph_qwen3tts_spkenc::attentive_stats_pool(ggml_tensor * x) const {
+    const int64_t T = x->ne[1];
+
+    // mean over T: [C, 1]
+    ggml_tensor * x_t  = ggml_cont(ctx0, ggml_transpose(ctx0, x));
+    ggml_tensor * mean = ggml_mean(ctx0, x_t);
+    mean               = ggml_cont(ctx0, ggml_transpose(ctx0, mean));
+
+    // std over T: sqrt(clamp(mean((x - mean)^2), eps))
+    ggml_tensor * mean_rep = ggml_repeat(ctx0, mean, x);
+    ggml_tensor * centered = ggml_sub(ctx0, x, mean_rep);
+    ggml_tensor * var_t    = ggml_cont(ctx0, ggml_transpose(ctx0, ggml_sqr(ctx0, centered)));
+    ggml_tensor * var      = ggml_mean(ctx0, var_t);
+    var                    = ggml_cont(ctx0, ggml_transpose(ctx0, var));
+    var                    = ggml_scale_bias(ctx0, var, 1.0f, 1e-12f);
+    ggml_tensor * std      = ggml_sqrt(ctx0, var);
+
+    // attention input: cat([x, mean, std]) along channel axis -> [3C, T]
+    ggml_tensor * std_rep = ggml_repeat(ctx0, std, x);
+    ggml_tensor * cat     = ggml_concat(ctx0, x, mean_rep, 0);
+    cat                   = ggml_concat(ctx0, cat, std_rep, 0);
+
+    // attention TDNN (3C -> attn_c) + ReLU, tanh, then 1x1 conv (attn_c -> C)
+    ggml_tensor * a = conv1d_same(cat, model.spk_asp_tdnn_w, model.spk_asp_tdnn_b, 1);
+    a = ggml_relu(ctx0, a);
+    a = ggml_tanh(ctx0, a);
+    a = conv1d_same(a, model.spk_asp_attn_w, model.spk_asp_attn_b, 1);
+
+    // softmax over T
+    ggml_tensor * a_t = ggml_cont(ctx0, ggml_transpose(ctx0, a));   // [T, C]
+    ggml_tensor * w_t = ggml_soft_max(ctx0, a_t);
+    ggml_tensor * w   = ggml_cont(ctx0, ggml_transpose(ctx0, w_t)); // [C, T]
+
+    // weighted mean: sum(w * x) over T, multiply by T to undo ggml_mean's 1/T scaling
+    ggml_tensor * wx     = ggml_mul(ctx0, w, x);
+    ggml_tensor * wx_t   = ggml_cont(ctx0, ggml_transpose(ctx0, wx));
+    ggml_tensor * w_mean = ggml_mean(ctx0, wx_t);
+    w_mean = ggml_scale(ctx0, w_mean, (float) T);
+    w_mean = ggml_cont(ctx0, ggml_transpose(ctx0, w_mean)); // [C, 1]
+
+    // weighted std: sum(w * (x - w_mean)^2) over T
+    ggml_tensor * w_mean_rep = ggml_repeat(ctx0, w_mean, x);
+    ggml_tensor * dev        = ggml_sub(ctx0, x, w_mean_rep);
+    ggml_tensor * w_var_in   = ggml_mul(ctx0, w, ggml_sqr(ctx0, dev));
+    ggml_tensor * w_var_t    = ggml_cont(ctx0, ggml_transpose(ctx0, w_var_in));
+    ggml_tensor * w_var      = ggml_mean(ctx0, w_var_t);
+    w_var                    = ggml_scale(ctx0, w_var, (float) T);
+    w_var                    = ggml_cont(ctx0, ggml_transpose(ctx0, w_var));
+    w_var                    = ggml_scale_bias(ctx0, w_var, 1.0f, 1e-12f);
+    ggml_tensor * w_std      = ggml_sqrt(ctx0, w_var);
+
+    return ggml_concat(ctx0, w_mean, w_std, 0); // [2C, 1]
+}
+
+ggml_cgraph * clip_graph_qwen3tts_spkenc::build() {
+    // inp_raw: [T, n_mel, 1, 1], from mtmd_audio_preprocessor_qwen3tts_spk
+    ggml_tensor * inp = build_inp_raw(1);
+    inp = ggml_reshape_2d(ctx0, inp, inp->ne[0], inp->ne[1]);
+
+    // this file's convention is [C, T]; the preprocessor delivers [T, C]
+    ggml_tensor * mel = ggml_cont(ctx0, ggml_transpose(ctx0, inp)); // [n_mel, T]
+    cb(mel, "mel", -1);
+
+    // frontend conv0 TDNN k=5, dilation=1: 128 -> 512
+    ggml_tensor * cur = conv1d_same(mel, model.conv1d_1_w, model.conv1d_1_b, 1);
+    cur = ggml_relu(ctx0, cur);
+    cb(cur, "frontend", -1);
+
+    // 3 SE-Res2Net blocks at dilations 2, 3, 4
+    GGML_ASSERT((int) model.layers.size() == 3);
+    std::vector<ggml_tensor *> blk_out(3);
+    for (int il = 0; il < 3; il++) {
+        cur = se_res2net_block(cur, model.layers[il], SPK_DILATIONS[il], SPK_RES2NET_SCALE);
+        blk_out[il] = cur;
+        cb(cur, "block_out", il);
+    }
+
+    // multi-layer feature aggregation: cat blk[0..2] then TDNN k=1 + ReLU
+    ggml_tensor * cat = ggml_concat(ctx0, blk_out[0], blk_out[1], 0);
+    cat = ggml_concat(ctx0, cat, blk_out[2], 0); // [1536, T]
+    ggml_tensor * mfa = conv1d_same(cat, model.conv_out_w, model.conv_out_b, 1);
+    mfa = ggml_relu(ctx0, mfa);
+    cb(mfa, "mfa", -1);
+
+    // attentive statistics pooling: [1536, T] -> [3072, 1]
+    ggml_tensor * stats = attentive_stats_pool(mfa);
+    cb(stats, "asp", -1);
+
+    // final FC k=1: [3072, 1] -> [enc_dim, 1]
+    ggml_tensor * emb = conv1d_same(stats, model.mm_fc_w, model.mm_fc_b, 1);
+
+    emb = ggml_reshape_1d(ctx0, emb, emb->ne[0]);
+    emb = ggml_cont(ctx0, emb);
+    cb(emb, "spk_embedding", -1);
+
+    ggml_build_forward_expand(gf, emb);
+    return gf;
+}

tools/mtmd/mtmd-audio.cpp

@@ -791,6 +791,66 @@ bool mtmd_audio_preprocessor_mimo_audio::preprocess(const float *
     return true;
 }
 
+//
+// mtmd_audio_preprocessor_qwen3tts_spk
+//
+// same as mel_spectrogram() in modeling_qwen3_tts.py
+// ECAPA-TDNN takes the whole clip in one pass, so no Whisper-style chunking or normalization
+//
+
+void mtmd_audio_preprocessor_qwen3tts_spk::initialize() {
+    cache.fill_sin_cos_table(hparams.audio_n_fft);
+    cache.fill_hann_window(hparams.audio_window_len, true);
+    cache.fill_mel_filterbank_matrix(hparams.n_mel_bins, hparams.audio_n_fft, hparams.audio_sample_rate);
+}
+
+bool mtmd_audio_preprocessor_qwen3tts_spk::preprocess(const float *                 samples,
+                                                      size_t                        n_samples,
+                                                      std::vector<mtmd_audio_mel> & output) {
+    if (n_samples == 0) {
+        return false;
+    }
+
+    GGML_ASSERT(!cache.sin_vals.empty());
+    GGML_ASSERT(!cache.cos_vals.empty());
+    GGML_ASSERT(!cache.filters.data.empty());
+
+    // reflect pad by (n_fft - hop) / 2 = 384, matching center=False STFT framing
+    const int pad = (hparams.audio_n_fft - hparams.audio_hop_len) / 2;
+    if (n_samples < (size_t) pad + 1) {
+        return false;
+    }
+
+    std::vector<float> padded(n_samples + 2 * pad, 0.0f);
+    for (int i = 0; i < pad; i++) {
+        padded[i] = samples[pad - i];
+    }
+    std::copy(samples, samples + n_samples, padded.begin() + pad);
+    for (int i = 0; i < pad; i++) {
+        padded[n_samples + pad + i] = samples[n_samples - 2 - i];
+    }
+
+    filter_params params;
+    params.n_mel            = hparams.n_mel_bins;
+    params.n_fft_bins       = 1 + (hparams.audio_n_fft / 2);
+    params.hann_window_size = hparams.audio_window_len;
+    params.hop_length       = hparams.audio_hop_len;
+    params.sample_rate      = hparams.audio_sample_rate;
+    params.no_padding       = true; // reflect padding already applied above
+    params.use_natural_log  = true;
+    params.use_magnitude    = true;
+    params.mel_floor        = 1e-5f;
+
+    mtmd_audio_mel out;
+    bool ok = log_mel_spectrogram(padded.data(), (int) padded.size(), 4, params, cache, out);
+    if (!ok) {
+        return false;
+    }
+
+    output.push_back(std::move(out));
+    return true;
+}
+
 //
 // mtmd_audio_preprocessor_conformer
 //

tools/mtmd/mtmd-audio.h

@@ -120,6 +120,15 @@ struct mtmd_audio_preprocessor_mimo_audio : mtmd_audio_preprocessor {
     mtmd_audio_cache cache;
 };
 
+struct mtmd_audio_preprocessor_qwen3tts_spk : mtmd_audio_preprocessor {
+    mtmd_audio_preprocessor_qwen3tts_spk(const clip_ctx * ctx) : mtmd_audio_preprocessor(ctx) {}
+    void initialize() override;
+    bool preprocess(const float * samples, size_t n_samples, std::vector<mtmd_audio_mel> & output) override;
+
+  private:
+    mtmd_audio_cache cache;
+};
+
 struct mtmd_audio_preprocessor_parakeet : mtmd_audio_preprocessor {
     mtmd_audio_preprocessor_parakeet(clip_ctx * ctx) : mtmd_audio_preprocessor(ctx) { }
     void initialize() override;

tools/mtmd/mtmd-cli.cpp

@@ -116,6 +116,14 @@ struct mtmd_cli_context {
             exit(1);
         }
 
+        init_vision_context(params);
+
+        if (!mtmd_helper_model_can_chat(lctx, ctx_vision.get())) {
+            LOG_ERR("Model does not support chat mode\n");
+            LOG_ERR("Hint: for TTS models, please use llama-tts\n");
+            exit(1);
+        }
+
         if (!llama_model_chat_template(model, nullptr) && params.chat_template.empty()) {
             LOG_ERR("Model does not have chat template.\n");
             LOG_ERR("  For old llava models, you may need to use '--chat-template vicuna'\n");
@@ -129,8 +137,6 @@ struct mtmd_cli_context {
         chat_history.clear();
         LOG_INF("%s: chat template example:\n%s\n", __func__, common_chat_format_example(tmpls.get(), params.use_jinja, params.default_template_kwargs).c_str());
 
-        init_vision_context(params);
-
         // load antiprompt tokens for legacy templates
         if (params.chat_template == "vicuna") {
             antiprompt_tokens = common_tokenize(lctx, "ASSISTANT:", false, true);

tools/mtmd/mtmd-helper-common.h

@@ -0,0 +1,180 @@
+#pragma once
+
+// shared internal utilities for the mtmd-helper-*.cpp translation units
+// (mtmd-helper.cpp, mtmd-helper-gen.cpp)
+// NOT part of the public mtmd-helper.h API
+
+#include "ggml.h"
+#include "llama.h"
+#include "mtmd.h"
+
+#include <cstdarg>
+#include <cstdio>
+#include <cstdlib>
+#include <vector>
+
+//
+// logging
+//
+
+struct mtmd_helper_logger {
+    ggml_log_callback default_callback = [](ggml_log_level level, const char * text, void * user_data) {
+        (void) level;
+        (void) user_data;
+        fputs(text, stderr);
+        fflush(stderr);
+    };
+
+    ggml_log_callback log_callback = default_callback;
+    void * log_callback_user_data;
+
+    void log_v(enum ggml_log_level level, const char * format, va_list args) {
+        if (format == NULL) {
+            return;
+        }
+        va_list args_copy;
+        va_copy(args_copy, args);
+        char buffer[128];
+        int len = vsnprintf(buffer, 128, format, args);
+        if (len < 128) {
+            log_callback(level, buffer, log_callback_user_data);
+        } else {
+            char * buffer2 = (char *) calloc(len + 1, sizeof(char));
+            vsnprintf(buffer2, len + 1, format, args_copy);
+            buffer2[len] = 0;
+            log_callback(level, buffer2, log_callback_user_data);
+            free(buffer2);
+        }
+        va_end(args_copy);
+    }
+
+    void log(enum ggml_log_level level, const char * format, ...) {
+        va_list args;
+        va_start(args, format);
+        log_v(level, format, args);
+        va_end(args);
+    }
+};
+
+// inline, so all TUs including this header share one instance
+inline mtmd_helper_logger g_logger;
+
+#define LOG_DBG(...) g_logger.log(GGML_LOG_LEVEL_DEBUG, __VA_ARGS__)
+#define LOG_INF(...) g_logger.log(GGML_LOG_LEVEL_INFO,  __VA_ARGS__)
+#define LOG_WRN(...) g_logger.log(GGML_LOG_LEVEL_WARN,  __VA_ARGS__)
+#define LOG_ERR(...) g_logger.log(GGML_LOG_LEVEL_ERROR, __VA_ARGS__)
+
+//
+// embd batch
+//
+
+// helper struct to make working with embd batch easier
+// note: this will be removed after llama_batch_ext refactoring
+struct decode_embd_batch {
+    int n_pos_per_embd;
+    int n_mmproj_embd;
+    std::vector<llama_pos>      pos;
+    std::vector<llama_pos>      pos_view; // used by mrope
+    std::vector<int32_t>        n_seq_id;
+    std::vector<llama_seq_id>   seq_id_0;
+    std::vector<llama_seq_id *> seq_ids;
+    std::vector<int8_t>         logits;
+    llama_batch batch;
+    decode_embd_batch(float * embd, int32_t n_tokens, int n_pos_per_embd, int n_mmproj_embd) : n_pos_per_embd(n_pos_per_embd), n_mmproj_embd(n_mmproj_embd) {
+        GGML_ASSERT(n_tokens > 0 && n_pos_per_embd > 0 && n_mmproj_embd > 0);
+        pos     .resize(n_tokens * n_pos_per_embd);
+        n_seq_id.resize(n_tokens);
+        seq_ids .resize(n_tokens + 1);
+        logits  .resize(n_tokens);
+        seq_id_0.resize(1);
+        seq_ids [n_tokens] = nullptr;
+        batch = {
+            /*n_tokens       =*/ n_tokens,
+            /*tokens         =*/ nullptr,
+            /*embd           =*/ embd,
+            /*pos            =*/ pos.data(),
+            /*n_seq_id       =*/ n_seq_id.data(),
+            /*seq_id         =*/ seq_ids.data(),
+            /*logits         =*/ logits.data(),
+        };
+    }
+
+    void set_position_normal(llama_pos pos_0, llama_seq_id seq_id) {
+        seq_id_0[0] = seq_id;
+        for (int i = 0; i < batch.n_tokens; i++) {
+            batch.pos     [i] = pos_0 + i;
+            batch.n_seq_id[i] = 1;
+            batch.seq_id  [i] = seq_id_0.data();
+            batch.logits  [i] = false;
+        }
+    }
+
+    // M-RoPE for image
+    void set_position_mrope_2d(const std::vector<mtmd_decoder_pos> & rel_pos, llama_seq_id seq_id) {
+        GGML_ASSERT(n_pos_per_embd == 4);
+        GGML_ASSERT(!rel_pos.empty() && (int32_t)rel_pos.size() == batch.n_tokens);
+        seq_id_0[0] = seq_id;
+        for (int32_t i = 0; i < batch.n_tokens; i++) {
+            pos[i                     ] = rel_pos[i].t;
+            pos[i + batch.n_tokens    ] = rel_pos[i].y;
+            pos[i + batch.n_tokens * 2] = rel_pos[i].x;
+            pos[i + batch.n_tokens * 3] = rel_pos[i].z;
+        }
+        for (int i = 0; i < batch.n_tokens; i++) {
+            batch.n_seq_id[i] = 1;
+            batch.seq_id  [i] = seq_id_0.data();
+            batch.logits  [i] = false;
+        }
+    }
+
+    // M-RoPE for audio
+    void set_position_mrope_1d(llama_pos pos_0, llama_seq_id seq_id) {
+        GGML_ASSERT(n_pos_per_embd == 4);
+        seq_id_0[0] = seq_id;
+        for (int i = 0; i < batch.n_tokens; i++) {
+            pos[i                     ] = pos_0 + i;
+            pos[i + batch.n_tokens    ] = pos_0 + i;
+            pos[i + batch.n_tokens * 2] = pos_0 + i;
+            pos[i + batch.n_tokens * 3] = pos_0 + i;
+        }
+        for (int i = 0; i < batch.n_tokens; i++) {
+            batch.n_seq_id[i] = 1;
+            batch.seq_id  [i] = seq_id_0.data();
+            batch.logits  [i] = false;
+        }
+    }
+
+    llama_batch get_view(int offset, int n_tokens) {
+        GGML_ASSERT(offset >= 0 && n_tokens > 0 && offset + n_tokens <= batch.n_tokens);
+        llama_pos * pos_ptr;
+        pos_view.clear();
+        pos_view.reserve(n_tokens * n_pos_per_embd);
+        if (n_pos_per_embd > 1) {
+            // mrope
+            // for example, with layout of src: 1234...1234...1234...1234...
+            //       offset 2 will give us dst: 34...34...34...34...
+            for (int i = 0; i < n_pos_per_embd; i++) {
+                // assume n_tokens is less than or equal to batch.n_tokens
+                // batch.n_tokens is number of **total** tokens
+                // n_tokens is number of viewed token
+                size_t src_idx = i * batch.n_tokens + offset;
+                pos_view.insert(pos_view.end(),
+                    pos.data() + src_idx,
+                    pos.data() + src_idx + n_tokens);
+            }
+            pos_ptr = pos_view.data();
+        } else {
+            // normal
+            pos_ptr = pos.data() + offset;
+        }
+        return {
+            /*n_tokens       =*/ n_tokens,
+            /*tokens         =*/ nullptr,
+            /*embd           =*/ batch.embd     + offset * n_mmproj_embd,
+            /*pos            =*/ pos_ptr,
+            /*n_seq_id       =*/ batch.n_seq_id + offset,
+            /*seq_id         =*/ batch.seq_id   + offset,
+            /*logits         =*/ batch.logits   + offset,
+        };
+    }
+};

tools/mtmd/mtmd-helper-gen.cpp

@@ -0,0 +1,505 @@
+#include "mtmd.h"
+#include "mtmd-helper.h"
+#include "mtmd-helper-common.h"
+#include "llama.h"
+#include "../src/llama-ext.h"
+
+#include <algorithm>
+#include <cstring>
+#include <memory>
+#include <string>
+#include <unordered_map>
+#include <vector>
+
+#ifdef MTMD_INTERNAL_HEADER
+#error "mtmd-helper is a public library outside of mtmd. it must not include internal headers"
+#endif
+
+//
+// Audio generation helpers
+//
+
+// --tts-lang codes -> language names used by the codec_language special tokens
+static const std::unordered_map<std::string, std::string> tts_lang_codes = {
+    { "zh", "chinese"    },
+    { "en", "english"    },
+    { "de", "german"     },
+    { "it", "italian"    },
+    { "pt", "portuguese" },
+    { "es", "spanish"    },
+    { "ja", "japanese"   },
+    { "ko", "korean"     },
+    { "fr", "french"     },
+    { "ru", "russian"    },
+};
+
+static std::string tts_resolve_lang(const std::string & lang) {
+    auto it = tts_lang_codes.find(lang);
+    return it != tts_lang_codes.end() ? it->second : lang;
+}
+
+static llama_token find_special_token(const llama_vocab * vocab, const std::string & piece) {
+    const int32_t n = llama_vocab_n_tokens(vocab);
+    for (llama_token t = 0; t < n; t++) {
+        if (piece == llama_vocab_get_text(vocab, t)) {
+            return t;
+        }
+    }
+    return LLAMA_TOKEN_NULL;
+}
+
+static bool write_wav16(std::vector<char> & buf, const std::vector<float> & pcm, int32_t rate) {
+    // RIFF chunk sizes are 32-bit; refuse to emit a file with a truncated header
+    if (pcm.size() > ((size_t) UINT32_MAX - 36) / 2) {
+        return false;
+    }
+    const uint32_t data_sz   = (uint32_t) (pcm.size() * 2);
+    const uint32_t riff_sz   = 36 + data_sz;
+    const uint32_t fmt_sz    = 16, byte_rate = (uint32_t) rate * 2;
+    const uint16_t fmt = 1, ch = 1, align = 2, bits = 16;
+    const uint32_t rate32    = (uint32_t) rate;
+    auto put = [&](const void * p, size_t n) {
+        const char * c = (const char *) p;
+        buf.insert(buf.end(), c, c + n);
+    };
+    put("RIFF", 4); put(&riff_sz, 4); put("WAVE", 4);
+    put("fmt ", 4); put(&fmt_sz, 4);
+    put(&fmt, 2); put(&ch, 2); put(&rate32, 4);
+    put(&byte_rate, 4); put(&align, 2); put(&bits, 2);
+    put("data", 4); put(&data_sz, 4);
+    for (float v : pcm) {
+        int16_t s = (int16_t) (std::max(-1.0f, std::min(1.0f, v)) * 32767.0f);
+        put(&s, 2);
+    }
+    return true;
+}
+
+class mtmd_gen_audio_pipeline {
+public:
+    mtmd_gen_audio_pipeline(llama_context * lctx, mtmd_context * mctx)
+        : lctx(lctx), mctx(mctx), model(llama_get_model(lctx)), vocab(llama_model_get_vocab(model)),
+          n_embd(llama_model_n_embd(model)), info(mtmd_gen_audio_get_info(mctx)) {}
+    virtual ~mtmd_gen_audio_pipeline() = default;
+
+    virtual void reset() = 0;
+    virtual int32_t set_input(const mtmd_helper_gen_audio_inp * inp) = 0;
+    // decodes at most n_batch prompt tokens; returns remaining count (0 = done), <0 on error
+    virtual int32_t step_prompt(int32_t n_batch) = 0;
+    // sampled can be LLAMA_TOKEN_NULL for pipelines with no discrete backbone token,
+    // those read what they need from h_state_in instead
+    virtual int32_t step_gen(llama_token sampled, const float * h_state_in, const float ** h_state_out) = 0;
+    virtual int32_t get_output(int32_t * out_sample_rate, const char ** out_data, size_t * out_data_len, int64_t * out_n_samples) = 0;
+
+protected:
+    llama_context * lctx;
+    mtmd_context  * mctx;
+    const llama_model * model;
+    const llama_vocab  * vocab;
+    int n_embd;
+    mtmd_gen_audio_info info;
+};
+
+// Qwen3-TTS: backbone samples codec_0, code_predictor gives the other 15 codebooks,
+// then code2wav decodes them to PCM
+class qwen3tts_gen_audio_pipeline : public mtmd_gen_audio_pipeline {
+public:
+    using mtmd_gen_audio_pipeline::mtmd_gen_audio_pipeline;
+
+    void reset() override {
+        seq_id = 0;
+        pos = 0;
+        codes_buf.clear();
+        c2w_state.clear();
+        audio_pcm.clear();
+        overlay.clear();
+        overlay_idx = 0;
+        h_state_buf.clear();
+        out_buf.clear();
+        prompt_embd_buf.clear();
+        prompt_batch.reset();
+        n_prompt = 0;
+        prompt_pos = 0;
+    }
+
+    int32_t set_input(const mtmd_helper_gen_audio_inp * inp) override {
+        reset();
+        seq_id = inp->seq_id;
+
+        if (!ensure_cache()) {
+            return 1;
+        }
+
+        const std::string lang   = tts_resolve_lang((inp->lang && inp->lang[0]) ? inp->lang : "english");
+        const llama_token c_lang = find_special_token(vocab, ("<|codec_language_" + lang + "|>").c_str());
+        if (c_lang == LLAMA_TOKEN_NULL) {
+            LOG_ERR("mtmd_helper_gen_audio: unknown language '%s'\n", lang.c_str());
+            return 1;
+        }
+
+        std::vector<float> speaker_embd;
+        if (inp->speaker_ref) {
+            if (!encode_speaker(inp->speaker_ref, speaker_embd)) {
+                return 1;
+            }
+        }
+
+        const int n_e = n_embd;
+        auto row = [&](llama_token t) {
+            return std::vector<float>(tok_embd.begin() + (size_t) t * n_e,
+                                       tok_embd.begin() + (size_t) (t + 1) * n_e);
+        };
+        auto sum_row = [&](llama_token a, llama_token b) {
+            std::vector<float> va = row(a), vb = row(b);
+            for (int i = 0; i < n_e; i++) va[(size_t) i] += vb[(size_t) i];
+            return va;
+        };
+        auto sum_vec = [&](llama_token a, const std::vector<float> & vb) {
+            std::vector<float> va = row(a);
+            for (int i = 0; i < n_e; i++) va[(size_t) i] += vb[(size_t) i];
+            return va;
+        };
+
+        // upstream chat wrap, then slices: [0:3] role, [3:-5] utterance body
+        const std::string full = "<|im_start|>assistant\n" + std::string(inp->prompt, inp->prompt_len) +
+                                  "<|im_end|>\n<|im_start|>assistant\n";
+        std::vector<llama_token> ids(full.size() + 16);
+        int n_ids = llama_tokenize(vocab, full.c_str(), (int32_t) full.size(), ids.data(), (int32_t) ids.size(),
+                                   false, true);
+        if (n_ids < 8) {
+            LOG_ERR("mtmd_helper_gen_audio: tokenization failed\n");
+            return 1;
+        }
+        ids.resize((size_t) n_ids);
+
+        std::vector<std::vector<float>> prompt;
+        for (int i = 0; i < 3; i++) prompt.push_back(row(ids[(size_t) i]));
+        prompt.push_back(sum_row(tts_pad, c_think));
+        prompt.push_back(sum_row(tts_pad, c_think_b));
+        prompt.push_back(sum_row(tts_pad, c_lang));
+        prompt.push_back(sum_row(tts_pad, c_think_e));
+        if (!speaker_embd.empty()) prompt.push_back(sum_vec(tts_pad, speaker_embd));
+        prompt.push_back(sum_row(tts_bos, codec_pad));
+        for (int i = 3; i < n_ids - 5; i++) prompt.push_back(sum_row(ids[(size_t) i], codec_pad));
+        prompt.push_back(sum_row(tts_eos, codec_pad));
+        prompt.push_back(sum_row(tts_pad, codec_bos));
+
+        n_prompt = (int) prompt.size();
+
+        // the talker uses the qwen3vl interleaved mrope, all sections are equal for a text/codec stream
+        mrope = llama_model_rope_type(model) == LLAMA_ROPE_TYPE_MROPE ||
+                llama_model_rope_type(model) == LLAMA_ROPE_TYPE_IMROPE;
+        const int n_pos_per_embd = mrope ? 4 : 1;
+
+        prompt_embd_buf.resize((size_t) n_prompt * (size_t) n_e);
+        for (int i = 0; i < n_prompt; i++) {
+            memcpy(prompt_embd_buf.data() + (size_t) i * n_e, prompt[(size_t) i].data(), (size_t) n_e * sizeof(float));
+        }
+
+        prompt_batch.reset(new decode_embd_batch(prompt_embd_buf.data(), n_prompt, n_pos_per_embd, n_e));
+        if (mrope) prompt_batch->set_position_mrope_1d(0, seq_id);
+        else       prompt_batch->set_position_normal  (0, seq_id);
+        prompt_pos = 0;
+
+        pos = 0;
+        top_k = inp->top_k > 0 ? inp->top_k : 50;
+        top_p = inp->top_p > 0 ? inp->top_p : 1.0f;
+        out_type = inp->out_type;
+
+        // the text stream keeps flowing during generation: after frame k, the input adds
+        // trailing text row k on top of the codes embedding, then tts_eos, then tts_pad
+        for (int i = 3; i < n_ids - 5; i++) overlay.push_back(row(ids[(size_t) i]));
+        overlay.push_back(row(tts_eos));
+        overlay.push_back(row(tts_pad));
+
+        return 0;
+    }
+
+    int32_t step_prompt(int32_t n_batch) override {
+        GGML_ASSERT(n_batch > 0);
+        if (prompt_pos >= n_prompt) {
+            return 0;
+        }
+        const int32_t n_tokens_batch = std::min(n_batch, n_prompt - prompt_pos);
+        llama_batch batch_view = prompt_batch->get_view(prompt_pos, n_tokens_batch);
+
+        const bool is_last_batch = (prompt_pos + n_tokens_batch) == n_prompt;
+        if (is_last_batch) {
+            batch_view.logits[n_tokens_batch - 1] = 1;
+        }
+
+        if (llama_decode(lctx, batch_view) != 0) {
+            LOG_ERR("mtmd_helper_gen_audio: prompt decode failed\n");
+            return -1;
+        }
+
+        pos        += n_tokens_batch;
+        prompt_pos += n_tokens_batch;
+
+        if (prompt_pos >= n_prompt) {
+            // prompt fully processed, its embedding buffer is no longer needed
+            prompt_batch.reset();
+            prompt_embd_buf.clear();
+            return 0;
+        }
+        return n_prompt - prompt_pos;
+    }
+
+    int32_t step_gen(llama_token sampled, const float * h_state_in, const float ** h_state_out) override {
+        mtmd_gen_inp inp{};
+        inp.type  = MTMD_GEN_PROCESS_TYPE_GEN_CODE;
+        inp.code0 = sampled - codec_0;
+        inp.embd  = const_cast<float *>(h_state_in);
+        inp.top_k = top_k;
+        inp.top_p = top_p;
+        mtmd_gen_out out{};
+        if (mtmd_gen_audio_process(mctx, &inp, &out) != 0) {
+            LOG_ERR("mtmd_helper_gen_audio: gen_code process failed\n");
+            return 1;
+        }
+
+        codes_buf.insert(codes_buf.end(), out.codes, out.codes + out.n_codes);
+        if (out.n_codes > 0 && codes_buf.size() / out.n_codes >= window_frames) {
+            if (!flush_gen_wav()) {
+                return 1;
+            }
+        }
+
+        std::vector<float> fb(out.embd, out.embd + n_embd);
+        const auto & ov = overlay[std::min(overlay_idx, overlay.size() - 1)];
+        for (int i = 0; i < n_embd; i++) fb[(size_t) i] += ov[(size_t) i];
+        overlay_idx++;
+
+        const int n_pos_per_embd = mrope ? 4 : 1;
+        decode_embd_batch batch_embd(fb.data(), 1, n_pos_per_embd, n_embd);
+        if (mrope) batch_embd.set_position_mrope_1d(pos, seq_id);
+        else       batch_embd.set_position_normal  (pos, seq_id);
+        batch_embd.batch.logits[0] = 1;
+        pos++;
+
+        if (llama_decode(lctx, batch_embd.batch) != 0) {
+            LOG_ERR("mtmd_helper_gen_audio: decode failed\n");
+            return 1;
+        }
+
+        const float * he = llama_get_embeddings_ith(lctx, -1);
+        h_state_buf.assign(he, he + n_embd);
+        *h_state_out = h_state_buf.data();
+
+        return 0;
+    }
+
+    int32_t get_output(int32_t * out_sample_rate, const char ** out_data, size_t * out_data_len, int64_t * out_n_samples) override {
+        if (!flush_gen_wav()) {
+            return 1;
+        }
+
+        *out_sample_rate = info.sample_rate;
+        if (out_n_samples) {
+            *out_n_samples = (int64_t) audio_pcm.size();
+        }
+
+        if (out_type == MTMD_HELPER_GEN_AUDIO_OUTTYPE_PCM) {
+            *out_data     = (const char *) audio_pcm.data();
+            *out_data_len = audio_pcm.size() * sizeof(float);
+            return 0;
+        }
+
+        out_buf.clear();
+        if (!write_wav16(out_buf, audio_pcm, info.sample_rate)) {
+            LOG_ERR("mtmd_helper_gen_audio: output too large for WAV\n");
+            return 1;
+        }
+        *out_data     = out_buf.data();
+        *out_data_len = out_buf.size();
+        return 0;
+    }
+
+private:
+    bool ensure_cache() {
+        if (specials_ok) {
+            return true;
+        }
+        codec_0   = find_special_token(vocab, "<|codec_0|>");
+        codec_bos = find_special_token(vocab, "<|codec_bos|>");
+        codec_eos = find_special_token(vocab, "<|codec_eos_token|>");
+        codec_pad = find_special_token(vocab, "<|codec_pad|>");
+        c_think   = find_special_token(vocab, "<|codec_think|>");
+        c_think_b = find_special_token(vocab, "<|codec_think_bos|>");
+        c_think_e = find_special_token(vocab, "<|codec_think_eos|>");
+        tts_pad   = find_special_token(vocab, "<tts_pad>");
+        tts_bos   = find_special_token(vocab, "<tts_text_bos>");
+        tts_eos   = find_special_token(vocab, "<tts_text_eod>");
+        for (llama_token t : { codec_0, codec_bos, codec_eos, codec_pad,
+                               c_think, c_think_b, c_think_e,
+                               tts_pad, tts_bos, tts_eos }) {
+            if (t == LLAMA_TOKEN_NULL) {
+                LOG_ERR("mtmd_helper_gen_audio: missing a required special token in vocab\n");
+                return false;
+            }
+        }
+        const uint32_t n_tok_embd = llama_model_get_tok_embd(model, nullptr);
+        if (n_tok_embd == 0) {
+            LOG_ERR("mtmd_helper_gen_audio: model has no token embeddings\n");
+            return false;
+        }
+        tok_embd.resize(n_tok_embd);
+        if (llama_model_get_tok_embd(model, tok_embd.data()) != n_tok_embd) {
+            LOG_ERR("mtmd_helper_gen_audio: token embedding copy failed\n");
+            return false;
+        }
+        specials_ok = true;
+        return true;
+    }
+
+    // runs the reference wav through the speaker encoder, returns one x-vector embedding row
+    bool encode_speaker(mtmd_bitmap * bitmap, std::vector<float> & out) {
+        if (!mtmd_support_audio(mctx)) {
+            LOG_ERR("mtmd_helper_gen_audio: mmproj has no speaker/audio encoder\n");
+            return false;
+        }
+        const std::string  marker = mtmd_default_marker();
+        mtmd_input_text     text{ marker.c_str(), marker.size(), false, true };
+        mtmd_input_chunks * chunks = mtmd_input_chunks_init();
+        const mtmd_bitmap * bptr = bitmap;
+        bool ok = mtmd_tokenize(mctx, chunks, &text, &bptr, 1) == 0;
+        if (ok) {
+            ok = false;
+            for (size_t i = 0; i < mtmd_input_chunks_size(chunks); i++) {
+                const mtmd_input_chunk * chunk = mtmd_input_chunks_get(chunks, i);
+                if (mtmd_input_chunk_get_type(chunk) != MTMD_INPUT_CHUNK_TYPE_AUDIO) {
+                    continue;
+                }
+                if (mtmd_encode_chunk(mctx, chunk) != 0) {
+                    LOG_ERR("mtmd_helper_gen_audio: speaker encode failed\n");
+                    break;
+                }
+                const float * embd = mtmd_get_output_embd(mctx);
+                const size_t  n = (size_t) llama_model_n_embd_inp(model) * mtmd_input_chunk_get_n_tokens(chunk);
+                out.assign(embd, embd + n);
+                ok = true;
+                break;
+            }
+        }
+        mtmd_input_chunks_free(chunks);
+        return ok;
+    }
+
+    // one GEN_WAV process() call over the buffered codes, state is carried across batches
+    bool flush_gen_wav() {
+        if (codes_buf.empty()) {
+            return true;
+        }
+        mtmd_gen_inp inp{};
+        inp.type       = MTMD_GEN_PROCESS_TYPE_GEN_WAV;
+        inp.codes      = codes_buf.data();
+        inp.n_codes    = codes_buf.size();
+        inp.state_data = c2w_state.empty() ? nullptr : (const char *) c2w_state.data();
+        inp.state_size = c2w_state.size();
+        mtmd_gen_out out{};
+        if (mtmd_gen_audio_process(mctx, &inp, &out) != 0) {
+            LOG_ERR("mtmd_helper_gen_audio: gen_wav process failed\n");
+            return false;
+        }
+        audio_pcm.insert(audio_pcm.end(), out.audio, out.audio + out.n_samples);
+        c2w_state.assign(out.state_data, out.state_data + out.state_size);
+        codes_buf.clear();
+        return true;
+    }
+
+    // vocab specials fixed across the whole session, looked up once
+    bool specials_ok = false;
+    llama_token codec_0    = LLAMA_TOKEN_NULL;
+    llama_token codec_bos  = LLAMA_TOKEN_NULL;
+    llama_token codec_eos  = LLAMA_TOKEN_NULL;
+    llama_token codec_pad  = LLAMA_TOKEN_NULL;
+    llama_token c_think    = LLAMA_TOKEN_NULL;
+    llama_token c_think_b  = LLAMA_TOKEN_NULL;
+    llama_token c_think_e  = LLAMA_TOKEN_NULL;
+    llama_token tts_pad    = LLAMA_TOKEN_NULL;
+    llama_token tts_bos    = LLAMA_TOKEN_NULL;
+    llama_token tts_eos    = LLAMA_TOKEN_NULL;
+    std::vector<float> tok_embd; // whole token embedding matrix, n_vocab * n_embd
+
+    // must match hparams.wav_tfm_swa hardcoded in clip.cpp
+    size_t window_frames = 72;
+
+    // per-generation state, cleared by reset()
+    llama_seq_id seq_id = 0;
+    bool mrope = false;
+    int pos = 0;
+    // prompt decode state, consumed batch-by-batch by step_prompt()
+    std::vector<float> prompt_embd_buf;
+    std::unique_ptr<decode_embd_batch> prompt_batch;
+    int n_prompt = 0;
+    int prompt_pos = 0;
+    int32_t top_k = 50;
+    float   top_p = 1.0f;
+    std::vector<int32_t> codes_buf;
+    std::vector<uint8_t> c2w_state;
+    std::vector<float>   audio_pcm;
+    std::vector<std::vector<float>> overlay;
+    size_t overlay_idx = 0;
+    std::vector<float> h_state_buf;
+    mtmd_helper_gen_audio_outtype out_type = MTMD_HELPER_GEN_AUDIO_OUTTYPE_WAV;
+    std::vector<char> out_buf;
+};
+
+static std::unique_ptr<mtmd_gen_audio_pipeline> make_pipeline(llama_context * lctx, mtmd_context * mctx) {
+    switch (mtmd_gen_audio_get_info(mctx).type) {
+        case MTMD_GEN_AUDIO_TYPE_QWEN3TTS:
+            return std::unique_ptr<mtmd_gen_audio_pipeline>(new qwen3tts_gen_audio_pipeline(lctx, mctx));
+        default:
+            return nullptr;
+    }
+}
+
+struct mtmd_helper_gen_audio {
+    std::unique_ptr<mtmd_gen_audio_pipeline> pipeline;
+};
+
+mtmd_helper_gen_audio * mtmd_helper_gen_audio_init(struct llama_context * lctx, struct mtmd_context * mctx) {
+    auto * ctx = new mtmd_helper_gen_audio();
+    ctx->pipeline = make_pipeline(lctx, mctx);
+    return ctx;
+}
+
+void mtmd_helper_gen_audio_free(mtmd_helper_gen_audio * ctx) {
+    delete ctx;
+}
+
+void mtmd_helper_gen_audio_reset(mtmd_helper_gen_audio * ctx) {
+    if (ctx->pipeline) {
+        ctx->pipeline->reset();
+    }
+}
+
+int32_t mtmd_helper_gen_audio_set_input(mtmd_helper_gen_audio * ctx, const mtmd_helper_gen_audio_inp * inp) {
+    if (!ctx->pipeline) {
+        LOG_ERR("mtmd_helper_gen_audio: unsupported or missing gen-audio pipeline\n");
+        return 1;
+    }
+    return ctx->pipeline->set_input(inp);
+}
+
+int32_t mtmd_helper_gen_audio_step_prompt(mtmd_helper_gen_audio * ctx, int32_t n_batch) {
+    if (!ctx->pipeline) {
+        return -1;
+    }
+    return ctx->pipeline->step_prompt(n_batch);
+}
+
+int32_t mtmd_helper_gen_audio_step_gen(mtmd_helper_gen_audio * ctx, llama_token sampled,
+                                       const float * h_state_in, const float ** h_state_out) {
+    if (!ctx->pipeline) {
+        return 1;
+    }
+    return ctx->pipeline->step_gen(sampled, h_state_in, h_state_out);
+}
+
+int32_t mtmd_helper_gen_audio_get_output(mtmd_helper_gen_audio * ctx, int32_t * out_sample_rate,
+                                         const char ** out_data, size_t * out_data_len, int64_t * out_n_samples) {
+    if (!ctx->pipeline) {
+        return 1;
+    }
+    return ctx->pipeline->get_output(out_sample_rate, out_data, out_data_len, out_n_samples);
+}

tools/mtmd/mtmd-helper.cpp

@@ -9,6 +9,7 @@
 
 #include "mtmd.h"
 #include "mtmd-helper.h"
+#include "mtmd-helper-common.h"
 #include "llama.h"
 
 #include <algorithm>
@@ -45,50 +46,6 @@
 // internal logging functions
 //
 
-struct mtmd_helper_logger {
-    ggml_log_callback default_callback = [](ggml_log_level level, const char * text, void * user_data) {
-        (void) level;
-        (void) user_data;
-        fputs(text, stderr);
-        fflush(stderr);
-    };
-
-    ggml_log_callback log_callback = default_callback;
-    void * log_callback_user_data;
-
-    void log_v(enum ggml_log_level level, const char * format, va_list args) {
-        if (format == NULL) {
-            return;
-        }
-        va_list args_copy;
-        va_copy(args_copy, args);
-        char buffer[128];
-        int len = vsnprintf(buffer, 128, format, args);
-        if (len < 128) {
-            log_callback(level, buffer, log_callback_user_data);
-        } else {
-            char * buffer2 = (char *) calloc(len + 1, sizeof(char));
-            vsnprintf(buffer2, len + 1, format, args_copy);
-            buffer2[len] = 0;
-            log_callback(level, buffer2, log_callback_user_data);
-            free(buffer2);
-        }
-        va_end(args_copy);
-    }
-
-    void log(enum ggml_log_level level, const char * format, ...) {
-        va_list args;
-        va_start(args, format);
-        log_v(level, format, args);
-        va_end(args);
-    }
-} g_logger;
-
-#define LOG_DBG(...) g_logger.log(GGML_LOG_LEVEL_DEBUG, __VA_ARGS__)
-#define LOG_INF(...) g_logger.log(GGML_LOG_LEVEL_INFO,  __VA_ARGS__)
-#define LOG_WRN(...) g_logger.log(GGML_LOG_LEVEL_WARN,  __VA_ARGS__)
-#define LOG_ERR(...) g_logger.log(GGML_LOG_LEVEL_ERROR, __VA_ARGS__)
-
 void mtmd_helper_log_set(ggml_log_callback log_callback, void * user_data) {
     if (log_callback == nullptr) {
         log_callback = g_logger.default_callback;
@@ -127,117 +84,6 @@ void mtmd_helper_image_get_decoder_pos(const mtmd_image_tokens * chunks, llama_p
     }
 }
 
-// helper struct to make working with embd batch easier
-// note: this will be removed after llama_batch_ext refactoring
-struct decode_embd_batch {
-    int n_pos_per_embd;
-    int n_mmproj_embd;
-    std::vector<llama_pos>      pos;
-    std::vector<llama_pos>      pos_view; // used by mrope
-    std::vector<int32_t>        n_seq_id;
-    std::vector<llama_seq_id>   seq_id_0;
-    std::vector<llama_seq_id *> seq_ids;
-    std::vector<int8_t>         logits;
-    llama_batch batch;
-    decode_embd_batch(float * embd, int32_t n_tokens, int n_pos_per_embd, int n_mmproj_embd) : n_pos_per_embd(n_pos_per_embd), n_mmproj_embd(n_mmproj_embd) {
-        GGML_ASSERT(n_tokens > 0 && n_pos_per_embd > 0 && n_mmproj_embd > 0);
-        pos     .resize(n_tokens * n_pos_per_embd);
-        n_seq_id.resize(n_tokens);
-        seq_ids .resize(n_tokens + 1);
-        logits  .resize(n_tokens);
-        seq_id_0.resize(1);
-        seq_ids [n_tokens] = nullptr;
-        batch = {
-            /*n_tokens       =*/ n_tokens,
-            /*tokens         =*/ nullptr,
-            /*embd           =*/ embd,
-            /*pos            =*/ pos.data(),
-            /*n_seq_id       =*/ n_seq_id.data(),
-            /*seq_id         =*/ seq_ids.data(),
-            /*logits         =*/ logits.data(),
-        };
-    }
-
-    void set_position_normal(llama_pos pos_0, llama_seq_id seq_id) {
-        seq_id_0[0] = seq_id;
-        for (int i = 0; i < batch.n_tokens; i++) {
-            batch.pos     [i] = pos_0 + i;
-            batch.n_seq_id[i] = 1;
-            batch.seq_id  [i] = seq_id_0.data();
-            batch.logits  [i] = false;
-        }
-    }
-
-    // M-RoPE for image
-    void set_position_mrope_2d(const std::vector<mtmd_decoder_pos> & rel_pos, llama_seq_id seq_id) {
-        GGML_ASSERT(n_pos_per_embd == 4);
-        GGML_ASSERT(!rel_pos.empty() && (int32_t)rel_pos.size() == batch.n_tokens);
-        seq_id_0[0] = seq_id;
-        for (int32_t i = 0; i < batch.n_tokens; i++) {
-            pos[i                     ] = rel_pos[i].t;
-            pos[i + batch.n_tokens    ] = rel_pos[i].y;
-            pos[i + batch.n_tokens * 2] = rel_pos[i].x;
-            pos[i + batch.n_tokens * 3] = rel_pos[i].z;
-        }
-        for (int i = 0; i < batch.n_tokens; i++) {
-            batch.n_seq_id[i] = 1;
-            batch.seq_id  [i] = seq_id_0.data();
-            batch.logits  [i] = false;
-        }
-    }
-
-    // M-RoPE for audio
-    void set_position_mrope_1d(llama_pos pos_0, llama_seq_id seq_id) {
-        GGML_ASSERT(n_pos_per_embd == 4);
-        seq_id_0[0] = seq_id;
-        for (int i = 0; i < batch.n_tokens; i++) {
-            pos[i                     ] = pos_0 + i;
-            pos[i + batch.n_tokens    ] = pos_0 + i;
-            pos[i + batch.n_tokens * 2] = pos_0 + i;
-            pos[i + batch.n_tokens * 3] = pos_0 + i;
-        }
-        for (int i = 0; i < batch.n_tokens; i++) {
-            batch.n_seq_id[i] = 1;
-            batch.seq_id  [i] = seq_id_0.data();
-            batch.logits  [i] = false;
-        }
-    }
-
-    llama_batch get_view(int offset, int n_tokens) {
-        GGML_ASSERT(offset >= 0 && n_tokens > 0 && offset + n_tokens <= batch.n_tokens);
-        llama_pos * pos_ptr;
-        pos_view.clear();
-        pos_view.reserve(n_tokens * n_pos_per_embd);
-        if (n_pos_per_embd > 1) {
-            // mrope
-            // for example, with layout of src: 1234...1234...1234...1234...
-            //       offset 2 will give us dst: 34...34...34...34...
-            for (int i = 0; i < n_pos_per_embd; i++) {
-                // assume n_tokens is less than or equal to batch.n_tokens
-                // batch.n_tokens is number of **total** tokens
-                // n_tokens is number of viewed token
-                size_t src_idx = i * batch.n_tokens + offset;
-                pos_view.insert(pos_view.end(),
-                    pos.data() + src_idx,
-                    pos.data() + src_idx + n_tokens);
-            }
-            pos_ptr = pos_view.data();
-        } else {
-            // normal
-            pos_ptr = pos.data() + offset;
-        }
-        return {
-            /*n_tokens       =*/ n_tokens,
-            /*tokens         =*/ nullptr,
-            /*embd           =*/ batch.embd     + offset * n_mmproj_embd,
-            /*pos            =*/ pos_ptr,
-            /*n_seq_id       =*/ batch.n_seq_id + offset,
-            /*seq_id         =*/ batch.seq_id   + offset,
-            /*logits         =*/ batch.logits   + offset,
-        };
-    }
-};
-
 // Helper class to set non-causal attention via RAII
 class scope_non_causal {
 public:
@@ -1084,3 +930,18 @@ int32_t mtmd_helper_video_read_next(mtmd_helper_video * ctx,
     GGML_ASSERT(false && "video is not supported in this build (MTMD_VIDEO is set to OFF)");
 #endif
 }
+
+bool mtmd_helper_model_can_chat(llama_context * lctx, mtmd_context * mctx) {
+    if (!mctx) {
+        return true;
+    }
+
+    auto * model = llama_get_model(lctx);
+    auto * tmpl = llama_model_chat_template(model, nullptr);
+    auto info = mtmd_gen_audio_get_info(mctx);
+
+    // tts-only model cannot be used for chat (no chat template)
+    bool is_tts_only = info.type != MTMD_GEN_AUDIO_TYPE_NONE && tmpl == nullptr;
+
+    return !is_tts_only;
+}

tools/mtmd/mtmd-helper.h

@@ -157,6 +157,73 @@ MTMD_API int32_t mtmd_helper_video_read_next(mtmd_helper_video * ctx,
             mtmd_bitmap ** out_bitmap,
             char ** out_text);
 
+// return true if model can be used for chat
+MTMD_API bool mtmd_helper_model_can_chat(struct llama_context * lctx, struct mtmd_context * mctx);
+
+//
+// Audio generation helpers
+// (early-stage experimental, subjected to breaking changes)
+//
+
+// audio generation helper context
+// contains accumulator for generated audio features and PCM audio
+struct mtmd_helper_gen_audio;
+typedef struct mtmd_helper_gen_audio mtmd_helper_gen_audio;
+
+enum mtmd_helper_gen_audio_outtype {
+    MTMD_HELPER_GEN_AUDIO_OUTTYPE_PCM, // raw PCM
+    MTMD_HELPER_GEN_AUDIO_OUTTYPE_WAV, // WAV PCM 16-bit LE, mono
+};
+struct mtmd_helper_gen_audio_inp {
+    llama_seq_id seq_id;
+
+    const char * prompt;
+    size_t       prompt_len;
+
+    mtmd_bitmap * speaker_ref; // optional, can be NULL
+    const char * lang; // optional, can be NULL
+
+    int32_t top_k;
+    float   top_p;
+
+    enum mtmd_helper_gen_audio_outtype out_type;
+};
+
+MTMD_API mtmd_helper_gen_audio * mtmd_helper_gen_audio_init(
+                                    struct llama_context * lctx,
+                                    struct mtmd_context * mctx);
+
+MTMD_API void mtmd_helper_gen_audio_free(mtmd_helper_gen_audio * ctx);
+
+MTMD_API void mtmd_helper_gen_audio_reset(mtmd_helper_gen_audio * ctx);
+
+MTMD_API int32_t mtmd_helper_gen_audio_set_input(
+                        mtmd_helper_gen_audio * ctx,
+                        const struct mtmd_helper_gen_audio_inp * inp);
+
+// processes at most n_batch prompt tokens per call
+// returns: >0 = number of prompt tokens remaining, 0 = done, <0 = error
+MTMD_API int32_t mtmd_helper_gen_audio_step_prompt(
+                        mtmd_helper_gen_audio * ctx,
+                        int32_t n_batch);
+
+// generates one frame; must only be called after step_prompt() has returned 0
+// h_state_out is valid until next step_gen() or reset() call
+MTMD_API int32_t mtmd_helper_gen_audio_step_gen(
+                        mtmd_helper_gen_audio * ctx,
+                        llama_token sampled,
+                        const float *  h_state_in,
+                        const float ** h_state_out);
+
+// out_data valid until next get_output() or reset() call
+// out_n_samples (optional, can be NULL) receives the number of generated PCM samples
+MTMD_API int32_t mtmd_helper_gen_audio_get_output(
+                        mtmd_helper_gen_audio * ctx,
+                        int32_t * out_sample_rate,
+                        const char ** out_data,
+                        size_t * out_data_len,
+                        int64_t * out_n_samples);
+
 #ifdef __cplusplus
 } // extern "C"
 #endif
@@ -177,6 +244,31 @@ struct mtmd_helper_video_deleter {
 };
 using video_ptr = std::unique_ptr<mtmd_helper_video, mtmd_helper_video_deleter>;
 
+// audio generation-related C++ wrappers
+struct mtmd_helper_gen_audio_deleter {
+    void operator()(mtmd_helper_gen_audio * val) { mtmd_helper_gen_audio_free(val); }
+};
+using gen_audio_ptr = std::unique_ptr<mtmd_helper_gen_audio, mtmd_helper_gen_audio_deleter>;
+struct gen_audio {
+    gen_audio_ptr ctx;
+    gen_audio(struct llama_context * lctx, struct mtmd_context * mctx) : ctx(mtmd_helper_gen_audio_init(lctx, mctx)) {}
+    void reset() {
+        mtmd_helper_gen_audio_reset(ctx.get());
+    }
+    int32_t set_input(const struct mtmd_helper_gen_audio_inp * inp) {
+        return mtmd_helper_gen_audio_set_input(ctx.get(), inp);
+    }
+    int32_t step_prompt(int32_t n_batch) {
+        return mtmd_helper_gen_audio_step_prompt(ctx.get(), n_batch);
+    }
+    int32_t step_gen(llama_token sampled, const float * h_state, const float ** h_state_out) {
+        return mtmd_helper_gen_audio_step_gen(ctx.get(), sampled, h_state, h_state_out);
+    }
+    int32_t get_output(int32_t * out_sample_rate, const char ** out_data, size_t * out_data_len, int64_t * out_n_samples = nullptr) {
+        return mtmd_helper_gen_audio_get_output(ctx.get(), out_sample_rate, out_data, out_data_len, out_n_samples);
+    }
+};
+
 } // namespace mtmd_helper
 #endif
 

tools/mtmd/mtmd.cpp

@@ -262,6 +262,13 @@ struct mtmd_context {
     struct clip_ctx * ctx_a; // audio
     std::vector<float> out_embd; // image embedding vector
 
+    // generation context
+    struct clip_ctx * ctx_gen_a; // audio
+    std::vector<int32_t> gen_out_codes; // this frame's 16 sampled codes (GEN_CODE)
+    std::vector<float>   gen_out_embd;  // next-step hidden state fed back to backbone (GEN_CODE)
+    std::vector<float>   gen_out_audio; // decoded PCM samples for the current frame (GEN_WAV)
+    std::vector<uint8_t> gen_out_state; // state to feed into the next GEN_WAV call
+
     bool print_timings;
     int n_threads;
     std::string media_marker;
@@ -354,6 +361,7 @@ struct mtmd_context {
         auto res = clip_init(mmproj_fname, ctx_clip_params);
         ctx_v = res.ctx_v;
         ctx_a = res.ctx_a;
+        ctx_gen_a = res.ctx_gen_a;
         if (!ctx_v && !ctx_a) {
             throw std::runtime_error(string_format("Failed to load CLIP model from %s\n", mmproj_fname));
         }
@@ -378,6 +386,15 @@ struct mtmd_context {
                 "hint: you may be using wrong mmproj\n",
                 n_embd_text, n_embd_clip));
         }
+        if (ctx_gen_a) {
+            int n_embd_gen = clip_n_mmproj_embd(ctx_gen_a);
+            if (n_embd_text > 0 && n_embd_text != n_embd_gen) {
+                throw std::runtime_error(string_format(
+                    "mismatch between text model (n_embd = %d) and gen-audio mmproj (n_embd = %d)\n"
+                    "hint: you may be using wrong mmproj\n",
+                    n_embd_text, n_embd_gen));
+            }
+        }
         if (ctx_v) {
             init_vision();
         }
@@ -740,6 +757,10 @@ struct mtmd_context {
                     aud_end = "<|mimo_audio_end|>";
                     audio_preproc = std::make_unique<mtmd_audio_preprocessor_mimo_audio>(ctx_a);
                 } break;
+            case PROJECTOR_TYPE_QWEN3TTS_SPKENC:
+                {
+                    audio_preproc = std::make_unique<mtmd_audio_preprocessor_qwen3tts_spk>(ctx_a);
+                } break;
             default:
                 throw std::runtime_error(string_format("%s: unexpected audio projector type %d\n", __func__, proj));
         }
@@ -780,6 +801,7 @@ struct mtmd_context {
     ~mtmd_context() {
         clip_free(ctx_a);
         clip_free(ctx_v);
+        clip_free(ctx_gen_a);
     }
 
 private:
@@ -1553,6 +1575,125 @@ float * mtmd_get_output_embd(mtmd_context * ctx) {
     return ctx->out_embd.data();
 }
 
+//
+// audio generation
+//
+
+mtmd_gen_audio_info mtmd_gen_audio_get_info(const mtmd_context * ctx) {
+    mtmd_gen_audio_info info;
+    if (!ctx->ctx_gen_a) {
+        info.type = MTMD_GEN_AUDIO_TYPE_NONE;
+        return info;
+    }
+    switch (clip_get_projector_type(ctx->ctx_gen_a)) {
+        case PROJECTOR_TYPE_QWEN3TTS_GEN:
+            info.type = MTMD_GEN_AUDIO_TYPE_QWEN3TTS;
+            info.sample_rate = 24000;
+            break;
+        default:
+            info.type = MTMD_GEN_AUDIO_TYPE_NONE;
+            break;
+    }
+    return info;
+}
+
+static int32_t mtmd_gen_audio_process_impl(mtmd_context * ctx, const mtmd_gen_inp * inp, mtmd_gen_out * out) {
+    clip_ctx * ctx_clip = ctx->ctx_gen_a;
+    if (!ctx_clip) {
+        LOG_ERR("%s: model does not support audio generation\n", __func__);
+        return 1;
+    }
+
+    if (inp->type == MTMD_GEN_PROCESS_TYPE_GEN_CODE) {
+        const size_t n_embd = (size_t) clip_n_mmproj_embd(ctx_clip);
+
+        clip_image_f32 hidden_state;
+        hidden_state.set_size({(int) n_embd, 1}, false, true);
+        hidden_state.cpy_buf(std::vector<float>(inp->embd, inp->embd + n_embd));
+
+        clip_image_f32_batch batch;
+        batch.is_audio = true;
+        batch.entries.push_back(std::move(hidden_state));
+
+        std::vector<float>   out_embd(n_embd);
+        std::vector<int32_t> out_codes;
+
+        clip_encode_params params;
+        params.imgs        = &batch;
+        params.n_threads   = ctx->n_threads;
+        params.gen_process = CLIP_GEN_PROCESS_GEN_CODE;
+        params.out_embd    = &out_embd;
+        params.out_codes   = &out_codes;
+        params.code0       = inp->code0;
+        params.top_k       = inp->top_k;
+        params.top_p       = inp->top_p;
+
+        if (!clip_encode(ctx_clip, &params)) {
+            LOG_ERR("%s: clip_encode failed (gen_code)\n", __func__);
+            return 1;
+        }
+
+        ctx->gen_out_embd  = std::move(out_embd);
+        ctx->gen_out_codes = std::move(out_codes);
+
+        out->embd    = ctx->gen_out_embd.data();
+        out->codes   = ctx->gen_out_codes.data();
+        out->n_codes = ctx->gen_out_codes.size();
+        return 0;
+    }
+
+    // MTMD_GEN_PROCESS_TYPE_GEN_WAV
+    if (!inp->codes || inp->n_codes == 0) {
+        LOG_ERR("%s: codes required for gen_wav\n", __func__);
+        return 1;
+    }
+    std::vector<int32_t> in_codes(inp->codes, inp->codes + inp->n_codes);
+    std::vector<uint8_t> in_state;
+    if (inp->state_data) {
+        in_state.assign(inp->state_data, inp->state_data + inp->state_size);
+    }
+
+    // gen_wav has no hidden-state input, the batch entry is an unused placeholder
+    // TODO @ngxson : some models in the future may require hidden-state input, need to update this code later
+    clip_image_f32 dummy;
+    dummy.set_size({1, 1}, false, true);
+    dummy.cpy_buf(std::vector<float>(1, 0.0f));
+
+    clip_image_f32_batch batch;
+    batch.is_audio = true;
+    batch.entries.push_back(std::move(dummy));
+
+    clip_encode_params params;
+    params.imgs        = &batch;
+    params.n_threads   = ctx->n_threads;
+    params.gen_process = CLIP_GEN_PROCESS_GEN_WAV;
+    params.codes       = &in_codes;
+    params.out_audio   = &ctx->gen_out_audio;
+    params.state_in    = inp->state_data ? &in_state : nullptr;
+    params.state_out   = &ctx->gen_out_state;
+
+    if (!clip_encode(ctx_clip, &params)) {
+        LOG_ERR("%s: clip_encode failed (code2wav)\n", __func__);
+        return 1;
+    }
+
+    out->audio      = ctx->gen_out_audio.data();
+    out->n_samples  = ctx->gen_out_audio.size();
+    out->state_data = (const char *) ctx->gen_out_state.data();
+    out->state_size = ctx->gen_out_state.size();
+
+    return 0;
+}
+
+int32_t mtmd_gen_audio_process(mtmd_context * ctx, const struct mtmd_gen_inp * inp, struct mtmd_gen_out * out) {
+    try {
+        return mtmd_gen_audio_process_impl(ctx, inp, out);
+    } catch (const std::exception & e) {
+        LOG_ERR("%s: error: %s\n", __func__, e.what());
+        return 1;
+    }
+}
+
 mtmd_batch * mtmd_batch_init(mtmd_context * ctx) {
     return new mtmd_batch(ctx);
 }

tools/mtmd/mtmd.h

@@ -327,6 +327,60 @@ struct mtmd_caps {
 };
 MTMD_API struct mtmd_caps mtmd_get_cap_from_file(const char * mmproj_fname);
 
+/////////////////////////////////////////
+// EXPERIMENTAL API for audio generation, subjected to breaking changes
+
+// represent the pipeline type
+enum mtmd_gen_audio_type {
+    MTMD_GEN_AUDIO_TYPE_NONE, // not supported
+    MTMD_GEN_AUDIO_TYPE_QWEN3TTS,
+};
+struct mtmd_gen_audio_info {
+    enum mtmd_gen_audio_type type;
+    int32_t sample_rate; // in Hz, for example 24000 for qwen3tts
+};
+MTMD_API struct mtmd_gen_audio_info mtmd_gen_audio_get_info(const mtmd_context * ctx);
+
+enum mtmd_gen_process_type {
+    MTMD_GEN_PROCESS_TYPE_GEN_CODE, // h_state to semantic (codes, mel-spectrogram, etc.)
+    MTMD_GEN_PROCESS_TYPE_GEN_WAV,  // convert semantic to PCM audio
+                                    // for qwen3tts, this is code2wav
+};
+struct mtmd_gen_inp {
+    enum mtmd_gen_process_type type;
+
+    // for MTMD_GEN_PROCESS_TYPE_GEN_CODE
+    int32_t code0;  // the sampled codebook 0 entry from backbone
+    float * embd;   // the hidden state from backbone, must have n_text_embd elements
+    int32_t top_k;
+    float   top_p;
+
+    // for MTMD_GEN_PROCESS_TYPE_GEN_WAV
+    int32_t * codes;
+    size_t    n_codes;
+    const char * state_data;
+    size_t       state_size;
+};
+struct mtmd_gen_out {
+    // note: output memory is allocated by the context, valid until next process() call
+
+    // for MTMD_GEN_PROCESS_TYPE_GEN_CODE
+    const int32_t * codes;
+    size_t n_codes;
+    const float * embd; // the generated hidden state, to be fed back to backbone
+                        // it must have n_text_embd elements
+
+    // for MTMD_GEN_PROCESS_TYPE_GEN_WAV
+    const float * audio;
+    size_t        n_samples;
+    const char * state_data;
+    size_t       state_size;
+};
+// note: this API is stateless, caller must handle state management and audio frame accumulation
+MTMD_API int32_t mtmd_gen_audio_process(mtmd_context * ctx,
+                                const struct mtmd_gen_inp * inp,
+                                struct mtmd_gen_out * out);
+
 /////////////////////////////////////////
 
 // test function, to be used in test-mtmd-c-api.c

tools/server/README-dev.md

@@ -201,7 +201,6 @@ Invoke a tool call, request body is a JSON object with:
 
 Headers:
 - `x-tool-cwd`: optional; if set, use as the CWD for tool; this is not part of tool's params because it's meant to be set by the runtime, not the LLM itself
-- `x-tool-docker`: optional; if set, use this docker container ID as tool runtime environment
 
 Returns JSON object. There are two response formats (MCP tools use the same two formats: their result content is concatenated into `plain_text_response`, and RPC or tool errors are surfaced as the `error` string):
 

tools/server/README.md

@@ -71,6 +71,7 @@ For the full list of features, please refer to [server's changelog](https://gith
 | `-ctk, --cache-type-k TYPE` | KV cache data type for K<br/>allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1<br/>(default: f16)<br/>(env: LLAMA_ARG_CACHE_TYPE_K) |
 | `-ctv, --cache-type-v TYPE` | KV cache data type for V<br/>allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1<br/>(default: f16)<br/>(env: LLAMA_ARG_CACHE_TYPE_V) |
 | `-dt, --defrag-thold N` | KV cache defragmentation threshold (DEPRECATED)<br/>(env: LLAMA_ARG_DEFRAG_THOLD) |
+| `--rpc SERVERS` | comma-separated list of RPC servers (host:port)<br/>(env: LLAMA_ARG_RPC) |
 | `--mlock` | DEPRECATED in favor of `--load-mode`: force system to keep model in RAM rather than swapping or compressing<br/>(env: LLAMA_ARG_MLOCK) |
 | `--mmap, --no-mmap` | DEPRECATED in favor of `--load-mode`: whether to memory-map model. (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>(env: LLAMA_ARG_MMAP) |
 | `-dio, --direct-io, -ndio, --no-direct-io` | DEPRECATED in favor of `--load-mode`: use DirectIO if available<br/>(env: LLAMA_ARG_DIO) |
@@ -197,8 +198,6 @@ For the full list of features, please refer to [server's changelog](https://gith
 | `--ui-config, --webui-config JSON` | JSON that provides default UI settings (overrides UI defaults)<br/>(env: LLAMA_ARG_UI_CONFIG) |
 | `--ui-config-file, --webui-config-file PATH` | JSON file that provides default UI settings (overrides UI defaults)<br/>(env: LLAMA_ARG_UI_CONFIG_FILE) |
 | `--ui-mcp-proxy, --webui-mcp-proxy, --no-ui-mcp-proxy, --no-webui-mcp-proxy` | experimental: whether to enable MCP CORS proxy - do not enable in untrusted environments (default: disabled)<br/>(env: LLAMA_ARG_UI_MCP_PROXY) |
-| `--tools TOOL1,TOOL2,...` | experimental: whether to enable built-in tools for AI agents - do not enable in untrusted environments (default: no tools)<br/>specify "all" to enable all tools<br/>available tools: read_file, file_glob_search, grep_search, exec_shell_command, write_file, edit_file, get_datetime<br/>note: for security reasons, this will limit --cors-origins to localhost by default<br/>(env: LLAMA_ARG_TOOLS) |
-| `--tools-runtime OPTION` | experimental: run tools in a separate runtime environment (default: none, use host environment)<br/>available options:<br/>  'docker:<image>': spin up a new Docker container and reuse it for all invocations, clean up on server exit<br/>  'docker-container:<id>': use an existing Docker container by ID, won't stop on server exit<br/><br/>(env: LLAMA_ARG_TOOLS_RUNTIME) |
 | `--tools TOOL1,TOOL2,...` | experimental: whether to enable built-in tools for AI agents - do not enable in untrusted environments (default: no tools)<br/>specify "all" to enable all tools<br/>available tools: read_file, file_glob_search, grep_search, exec_shell_command, write_file, edit_file, get_datetime, get_info<br/>note: for security reasons, this will limit --cors-origins to localhost by default<br/>(env: LLAMA_ARG_TOOLS) |
 | `--mcp-servers-config PATH` | experimental: path to JSON file with MCP server definitions (Cursor-compatible format) - do not enable in untrusted environments (default: none)<br/>note: for security reasons, this will limit --cors-origins to localhost by default<br/>(env: LLAMA_ARG_MCP_SERVERS_CONFIG) |
 | `--mcp-servers-json JSON` | experimental: inline JSON with MCP server definitions (Cursor-compatible format) - do not enable in untrusted environments (default: none)<br/>note: for security reasons, this will limit --cors-origins to localhost by default<br/>(env: LLAMA_ARG_MCP_SERVERS_JSON) |

tools/server/server-tools.cpp

@@ -10,12 +10,10 @@
 #include <ctime>
 #include <atomic>
 #include <cstring>
-#include <cstdint>
 #include <algorithm>
 #include <unordered_set>
 #include <functional>
 #include <memory>
-#include <mutex>
 
 namespace fs = std::filesystem;
 
@@ -64,85 +62,6 @@ public:
             const std::function<bool(const std::string &)> & on_chunk = nullptr) const = 0;
 };
 
-// shared subprocess execution helper, used by both the local and the docker-backed tools_io implementations.
-// combine_stderr=false when the raw stdout bytes must not be tainted by stderr, e.g. reading file contents.
-static tools_io::exec_result run_subprocess(
-        const std::vector<std::string> & args,
-        size_t max_output,
-        int timeout_secs,
-        const std::function<bool(const std::string &)> & on_chunk,
-        bool combine_stderr,
-        const std::string & cwd = "") {
-    tools_io::exec_result res;
-
-    common_subproc proc;
-
-    int options = subprocess_option_no_window
-                | subprocess_option_inherit_environment
-                | subprocess_option_search_user_path;
-    if (combine_stderr) {
-        options |= subprocess_option_combined_stdout_stderr;
-    }
-
-    if (!proc.create(args, options, {}, cwd.empty() ? nullptr : cwd.c_str())) {
-        res.output = "failed to spawn process";
-        return res;
-    }
-
-    std::atomic<bool> done{false};
-    std::atomic<bool> timed_out{false};
-
-    std::thread timeout_thread([&]() {
-        auto deadline = std::chrono::steady_clock::now() + std::chrono::seconds(timeout_secs);
-        while (!done.load()) {
-            if (std::chrono::steady_clock::now() >= deadline) {
-                timed_out.store(true);
-                proc.terminate();
-                return;
-            }
-            std::this_thread::sleep_for(std::chrono::milliseconds(100));
-        }
-    });
-
-    FILE * f = proc.stdout_file();
-    std::string output;
-    bool truncated = false;
-    if (f) {
-        char buf[4096];
-        while (fgets(buf, sizeof(buf), f) != nullptr) {
-            if (!truncated) {
-                size_t len = strlen(buf);
-                if (output.size() + len <= max_output) {
-                    output.append(buf, len);
-                    if (on_chunk && !on_chunk(std::string(buf, len))) {
-                        proc.terminate();
-                        break;
-                    }
-                } else {
-                    size_t remaining = max_output - output.size();
-                    output.append(buf, remaining);
-                    if (on_chunk && remaining > 0) on_chunk(std::string(buf, remaining));
-                    truncated = true;
-                }
-            }
-        }
-    }
-
-    done.store(true);
-    if (timeout_thread.joinable()) {
-        timeout_thread.join();
-    }
-
-    res.exit_code = proc.join();
-
-    res.output    = output;
-    res.timed_out = timed_out.load();
-    if (truncated) {
-        res.output += "\n[output truncated]";
-    }
-    return res;
-}
-
 class tools_io_basic : public tools_io {
 public:
     // cwd, if non-empty, is used to resolve relative paths and as the working directory for run()
@@ -221,7 +140,72 @@ public:
             size_t max_output,
             int timeout_secs,
             const std::function<bool(const std::string &)> & on_chunk = nullptr) const override {
-        return run_subprocess(args, max_output, timeout_secs, on_chunk, /*combine_stderr=*/true, cwd);
+        exec_result res;
+
+        common_subproc proc;
+
+        int options = subprocess_option_no_window
+                    | subprocess_option_combined_stdout_stderr
+                    | subprocess_option_inherit_environment
+                    | subprocess_option_search_user_path;
+
+        if (!proc.create(args, options, {}, cwd.empty() ? nullptr : cwd.c_str())) {
+            res.output = "failed to spawn process";
+            return res;
+        }
+
+        std::atomic<bool> done{false};
+        std::atomic<bool> timed_out{false};
+
+        std::thread timeout_thread([&]() {
+            auto deadline = std::chrono::steady_clock::now() + std::chrono::seconds(timeout_secs);
+            while (!done.load()) {
+                if (std::chrono::steady_clock::now() >= deadline) {
+                    timed_out.store(true);
+                    proc.terminate();
+                    return;
+                }
+                std::this_thread::sleep_for(std::chrono::milliseconds(100));
+            }
+        });
+
+        FILE * f = proc.stdout_file();
+        std::string output;
+        bool truncated = false;
+        if (f) {
+            char buf[4096];
+            while (fgets(buf, sizeof(buf), f) != nullptr) {
+                if (!truncated) {
+                    size_t len = strlen(buf);
+                    if (output.size() + len <= max_output) {
+                        output.append(buf, len);
+                        if (on_chunk && !on_chunk(std::string(buf, len))) {
+                            proc.terminate();
+                            break;
+                        }
+                    } else {
+                        size_t remaining = max_output - output.size();
+                        output.append(buf, remaining);
+                        if (on_chunk && remaining > 0) on_chunk(std::string(buf, remaining));
+                        truncated = true;
+                    }
+                }
+            }
+        }
+
+        done.store(true);
+        if (timeout_thread.joinable()) {
+            timeout_thread.join();
+        }
+
+        res.exit_code = proc.join();
+
+        res.output    = output;
+        res.timed_out = timed_out.load();
+        if (truncated) {
+            res.output += "\n[output truncated]";
+        }
+        return res;
     }
 
 private:
@@ -273,180 +257,8 @@ private:
     }
 };
 
-// timeout for auxiliary docker exec calls (stat/mkdir/ls/cp helpers); exec_shell_command uses its own
-// caller-controlled timeout instead, enforced separately in run()
-static constexpr int SERVER_TOOL_DOCKER_EXEC_TIMEOUT = 15; // seconds
-static constexpr size_t SERVER_TOOL_DOCKER_READ_FILE_MAX_SIZE = 64 * 1024 * 1024; // 64 MB
-
-// runs every tools_io operation inside an already-running docker container via `docker exec`/`docker cp`.
-// the container itself is started, mounted, and torn down externally by the caller.
-class tools_io_docker : public tools_io {
-public:
-    // cwd, if non-empty, is used to resolve relative paths and as the working directory for run()
-    tools_io_docker(std::string container_id, std::string cwd = "")
-        : container_id(std::move(container_id)), cwd(std::move(cwd)) {}
-
-    bool is_directory(const std::string & path) const override {
-        return shell_test("-d", resolve(path));
-    }
-
-    bool is_regular_file(const std::string & path) const override {
-        return shell_test("-f", resolve(path));
-    }
-
-    bool file_size(const std::string & path, uintmax_t & out_size) const override {
-        auto res = exec({"sh", "-c", "wc -c < \"$1\"", "_", resolve(path)}, 64, true);
-        if (res.exit_code != 0 || res.timed_out) return false;
-        try {
-            size_t pos;
-            out_size = (uintmax_t) std::stoull(res.output, &pos);
-        } catch (...) {
-            return false;
-        }
-        return true;
-    }
-
-    bool read_file(const std::string & path, std::string & out) const override {
-        // combine_stderr=false: stderr must not be spliced into raw file bytes
-        auto res = exec({"cat", "--", resolve(path)}, SERVER_TOOL_DOCKER_READ_FILE_MAX_SIZE, false);
-        if (res.exit_code != 0 || res.timed_out) return false;
-        out = res.output;
-        return true;
-    }
-
-    bool write_file(const std::string & path, const std::string & content) const override {
-        std::string abs_path = resolve(path);
-
-        std::error_code ec;
-        fs::path tmp_dir = fs::temp_directory_path(ec);
-        if (ec) return false;
-
-        static std::atomic<uint64_t> tmp_counter{0};
-        fs::path tmp = tmp_dir / string_format(
-            "llama-tools-io-docker-%zu-%llu.tmp",
-            std::hash<std::thread::id>{}(std::this_thread::get_id()),
-            (unsigned long long) tmp_counter.fetch_add(1));
-
-        {
-            std::ofstream f(tmp, std::ios::binary);
-            if (!f) return false;
-            f << content;
-            if (!f) return false;
-        }
-
-        bool ok = shell_run({"sh", "-c", "mkdir -p \"$(dirname \"$1\")\"", "_", abs_path});
-        if (ok) {
-            auto res = run_subprocess(
-                {"docker", "cp", tmp.string(), container_id + ":" + abs_path},
-                4096, SERVER_TOOL_DOCKER_EXEC_TIMEOUT, nullptr, true);
-            ok = res.exit_code == 0 && !res.timed_out;
-        }
-
-        std::error_code rm_ec;
-        fs::remove(tmp, rm_ec);
-        return ok;
-    }
-
-    std::vector<std::string> list_files(const std::string & base, std::string & err) const override {
-        err.clear();
-        std::string abs_base = resolve(base);
-        if (!is_directory(base)) {
-            err = "path does not exist or is not a directory: " + base;
-            return {};
-        }
-
-        auto res = exec(
-            {"sh", "-c", "cd \"$1\" && git ls-files --cached --others --exclude-standard", "_", abs_base},
-            SERVER_TOOL_GIT_LS_FILES_MAX_OUTPUT, true);
-
-        if (res.exit_code == 0 && !res.timed_out) {
-            return split_lines(res.output, /*strip_dot_slash=*/false);
-        }
-
-        static const char * prune_names[] = {
-            ".git", ".svn", ".hg", "node_modules", "__pycache__",
-            ".venv", "venv", "dist", "build", "target", ".cache", ".idea", ".vscode",
-        };
-        std::string prune_expr;
-        for (const char * n : prune_names) {
-            if (!prune_expr.empty()) prune_expr += " -o ";
-            prune_expr += std::string("-name ") + n;
-        }
-        std::string find_cmd = "cd \"$1\" && find . \\( " + prune_expr + " \\) -prune -o -type f -print";
-        auto find_res = exec({"sh", "-c", find_cmd, "_", abs_base}, SERVER_TOOL_GIT_LS_FILES_MAX_OUTPUT, true);
-
-        return split_lines(find_res.output, /*strip_dot_slash=*/true);
-    }
-
-    // wraps the command with an in-container `timeout`, since killing the local `docker exec` client
-    // does not kill the process tree running inside the container
-    exec_result run(
-            const std::vector<std::string> & args,
-            size_t max_output,
-            int timeout_secs,
-            const std::function<bool(const std::string &)> & on_chunk = nullptr) const override {
-        std::vector<std::string> docker_args = {"docker", "exec", "-i"};
-        if (!cwd.empty()) {
-            docker_args.push_back("-w");
-            docker_args.push_back(cwd);
-        }
-        docker_args.push_back(container_id);
-        docker_args.push_back("timeout");
-        docker_args.push_back(std::to_string(timeout_secs) + "s");
-        docker_args.insert(docker_args.end(), args.begin(), args.end());
-        // small buffer over timeout_secs so the in-container `timeout` has a chance to exit cleanly
-        // before the host-side supervisory timeout forcibly kills the docker exec client
-        return run_subprocess(docker_args, max_output, timeout_secs + 5, on_chunk, true);
-    }
-
-private:
-    std::string container_id;
-    std::string cwd;
-
-    // resolves `path` against `cwd` if `path` is relative and `cwd` is set; otherwise returns `path` unchanged.
-    // container paths are always POSIX-style ('/'), regardless of host OS.
-    std::string resolve(const std::string & path) const {
-        if (cwd.empty() || (!path.empty() && path[0] == '/')) {
-            return path;
-        }
-        return cwd + "/" + path;
-    }
-
-    exec_result exec(const std::vector<std::string> & inner, size_t max_output, bool combine_stderr) const {
-        std::vector<std::string> args = {"docker", "exec", container_id};
-        args.insert(args.end(), inner.begin(), inner.end());
-        return run_subprocess(args, max_output, SERVER_TOOL_DOCKER_EXEC_TIMEOUT, nullptr, combine_stderr);
-    }
-
-    bool shell_run(const std::vector<std::string> & inner) const {
-        auto res = exec(inner, 4096, true);
-        return res.exit_code == 0 && !res.timed_out;
-    }
-
-    bool shell_test(const char * flag, const std::string & path) const {
-        return shell_run({"sh", "-c", std::string("[ ") + flag + " \"$1\" ]", "_", path});
-    }
-
-    static std::vector<std::string> split_lines(const std::string & text, bool strip_dot_slash) {
-        std::vector<std::string> result;
-        std::istringstream iss(text);
-        std::string line;
-        while (std::getline(iss, line)) {
-            if (!line.empty() && line.back() == '\r') line.pop_back();
-            if (line.empty()) continue;
-            if (strip_dot_slash && line.rfind("./", 0) == 0) line = line.substr(2);
-            std::replace(line.begin(), line.end(), '\\', '/');
-            result.push_back(line);
-        }
-        return result;
-    }
-};
-
 static std::unique_ptr<tools_io> make_tools_io(const json & params) {
     std::string cwd = json_value(params, "cwd", std::string());
-    if (params.contains("docker_container_id")) {
-        return std::make_unique<tools_io_docker>(params.at("docker_container_id").get<std::string>(), cwd);
-    }
     return std::make_unique<tools_io_basic>(cwd);
 }
 
@@ -815,11 +627,8 @@ struct server_tool_exec_shell_command : server_tool {
         timeout    = std::min(timeout,    SERVER_TOOL_EXEC_SHELL_COMMAND_MAX_TIMEOUT);
         max_output = std::min(max_output, SERVER_TOOL_EXEC_SHELL_COMMAND_MAX_OUTPUT_SIZE);
 
-        // docker containers are Linux-based regardless of host OS, so a docker target always gets `sh -c`
 #ifdef _WIN32
-        std::vector<std::string> args = params.contains("docker_container_id")
-            ? std::vector<std::string>{"sh", "-c", command}
-            : std::vector<std::string>{"cmd", "/c", command};
+        std::vector<std::string> args = {"cmd", "/c", command};
 #else
         std::vector<std::string> args = {"sh", "-c", command};
 #endif
@@ -1309,16 +1118,13 @@ struct server_tool_get_info : server_tool {
     json invoke(json params, server_tool::stream *) const override {
         auto io = make_tools_io(params);
 
-        // inside docker, we always use the linux command
 #ifdef _WIN32
-        std::vector<std::string> args = params.contains("docker_container_id")
-            ? std::vector<std::string>{"uname", "-a"}
-            : std::vector<std::string>{"cmd", "/c", "ver"};
+        auto res = io->run({"cmd", "/c", "ver"}, 4096, 5);
 #else
-        std::vector<std::string> args = {"uname", "-a"};
+        auto res = io->run({"uname", "-a"}, 4096, 5);
 #endif
-
-        auto res = io->run(args, 4096, 5);
+        // "ver" prints a blank line before the version, so the output is stripped on both ends;
+        // a failed spawn or a timeout leaves a diagnostic in res.output, which is not an OS name
         std::string os_info = res.exit_code == 0 && !res.timed_out ? string_strip(res.output) : "unknown";
 
         std::string cwd = json_value(params, "cwd", std::string());
@@ -1418,104 +1224,6 @@ struct server_mcp_tool : server_tool {
     }
 };
 
-// owns the docker container used as the sandboxed runtime for tool invocations, as configured by
-// --tools-runtime. "spawned" mode starts and stops the container itself; "existing" mode just reuses
-// a container id the user already has running and never stops it.
-struct server_tools_docker_runtime {
-    server_tools_docker_runtime(const server_tools_docker_runtime &) = delete;
-
-    explicit server_tools_docker_runtime(const std::string & spec) {
-        static const std::string docker_prefix           = "docker:";
-        static const std::string docker_container_prefix = "docker-container:";
-        if (spec.rfind(docker_prefix, 0) == 0) {
-            spawned = true;
-            image   = spec.substr(docker_prefix.size());
-            if (image.empty()) {
-                throw std::runtime_error("--tools-runtime docker:<image> requires an image name");
-            }
-            spawn();
-        } else if (spec.rfind(docker_container_prefix, 0) == 0) {
-            spawned      = false;
-            container_id = spec.substr(docker_container_prefix.size());
-            if (container_id.empty()) {
-                throw std::runtime_error("--tools-runtime docker-container:<id> requires a container id");
-            }
-        } else {
-            throw std::runtime_error("unknown --tools-runtime option: " + spec);
-        }
-    }
-
-    ~server_tools_docker_runtime() {
-        if (spawned && !container_id.empty()) {
-            // closing stdin signals the container's shell (its pid 1) to exit; --rm then removes it
-            proc.close_stdin();
-            proc.join();
-        }
-    }
-
-    // container id to use for the next tool call; respawns a spawned container that died on its own,
-    // or throws if an externally-managed one is no longer reachable
-    std::string get_container_id() {
-        std::lock_guard<std::mutex> lock(mutex);
-        if (!spawned) {
-            if (!is_running(container_id)) {
-                throw std::runtime_error(string_format(
-                    "docker container \"%s\" is no longer running, restart it to keep using tools",
-                    container_id.c_str()));
-            }
-            return container_id;
-        }
-
-        if (!proc.alive()) {
-            SRV_WRN("docker tools runtime container \"%s\" died, respawning\n", container_id.c_str());
-            spawn();
-        }
-        return container_id;
-    }
-
-private:
-    bool spawned = false;
-    std::string image; // spawned mode only
-    std::string container_id;
-    common_subproc proc; // spawned mode only: `docker run` client that keeps the container alive
-    std::mutex mutex;
-
-    // spawns "docker run --rm -i <image> sh" and keeps its stdin open; the shell blocks reading stdin,
-    // so the container stays alive until we close it (see destructor) or it is killed from the outside
-    void spawn() {
-        std::error_code ec;
-        fs::path cidfile = fs::temp_directory_path(ec) / string_format(
-            "llama-tools-runtime-cid-%zu.tmp", std::hash<std::thread::id>{}(std::this_thread::get_id()));
-        fs::remove(cidfile, ec);
-
-        std::vector<std::string> args = {"docker", "run", "--rm", "-i", "--cidfile", cidfile.string(), image, "sh"};
-        int options = subprocess_option_no_window
-                    | subprocess_option_inherit_environment
-                    | subprocess_option_search_user_path;
-        if (!proc.create(args, options)) {
-            throw std::runtime_error("failed to spawn docker container for tools runtime (image: " + image + ")");
-        }
-
-        std::string cid;
-        for (int i = 0; i < 100 && cid.empty(); i++) {
-            std::ifstream f(cidfile);
-            if (f) std::getline(f, cid);
-            if (cid.empty()) std::this_thread::sleep_for(std::chrono::milliseconds(100));
-        }
-        fs::remove(cidfile, ec);
-        if (cid.empty()) {
-            proc.terminate();
-            throw std::runtime_error("timed out waiting for docker container to start (image: " + image + ")");
-        }
-        container_id = cid;
-    }
-
-    static bool is_running(const std::string & id) {
-        auto res = run_subprocess({"docker", "inspect", "-f", "{{.State.Running}}", id}, 16, 5, nullptr, true);
-        return res.exit_code == 0 && !res.timed_out && res.output.rfind("true", 0) == 0;
-    }
-};
-
 static server_tool & find_tool(std::vector<std::unique_ptr<server_tool>> & tools, const std::string & name, bool require_stream) {
     for (auto & t : tools) {
         if (t->name == name) {
@@ -1561,16 +1269,8 @@ static std::string get_header(const std::map<std::string, std::string> & headers
     return default_value;
 }
 
-server_tools::server_tools() = default;
-server_tools::~server_tools() = default;
-
 void server_tools::setup(const std::vector<std::string> & enabled_tools,
-                         server_mcp & mcp_mgr,
-                         const std::string & tools_runtime) {
-    if (!tools_runtime.empty()) {
-        docker_runtime = std::make_unique<server_tools_docker_runtime>(tools_runtime);
-    }
-
+                         server_mcp & mcp_mgr) {
     if (!enabled_tools.empty()) {
         if (!common_subproc::is_supported()) {
             throw std::runtime_error("subprocess is not enabled on this build");
@@ -1653,26 +1353,11 @@ void server_tools::setup(const std::vector<std::string> & enabled_tools,
             bool stream = body.value("stream", false);
 
             // accept x-tool-cwd header to override of the process
-            if (params.contains("cwd")) {
-                params.erase("cwd");
-            }
             auto cwd = get_header(req.headers, "x-tool-cwd");
             if (!cwd.empty()) {
                 params["cwd"] = cwd;
             }
 
-            // accept x-tool-docker header to route tool I/O through a running docker container;
-            // falls back to the --tools-runtime container, if configured
-            if (params.contains("docker_container_id")) {
-                params.erase("docker_container_id");
-            }
-            auto docker_container_id = get_header(req.headers, "x-tool-docker");
-            if (!docker_container_id.empty()) {
-                params["docker_container_id"] = docker_container_id;
-            } else if (docker_runtime) {
-                params["docker_container_id"] = docker_runtime->get_container_id();
-            }
-
             server_tool & tool = find_tool(tools, tool_name, stream);
 
             if (stream) {

tools/server/server-tools.h

@@ -30,8 +30,6 @@ struct server_tool {
     json to_json() const;
 };
 
-struct server_tools_docker_runtime; // impl detail, defined in server-tools.cpp
-
 struct server_tools {
     std::vector<std::unique_ptr<server_tool>> tools;
 
@@ -39,16 +37,9 @@ struct server_tools {
     server_response queue_res;
     std::atomic<int> res_id{0};
 
-    // set when --tools-runtime is configured; owns the docker container used to run tools, if any
-    std::unique_ptr<server_tools_docker_runtime> docker_runtime;
-
     void setup(const std::vector<std::string> & enabled_tools,
-               server_mcp & mcp_mgr,
-               const std::string & tools_runtime);
+               server_mcp & mcp_mgr);
 
     server_http_context::handler_t handle_get;
     server_http_context::handler_t handle_post;
-
-    server_tools();
-    ~server_tools();
 };

tools/server/server.cpp

@@ -338,7 +338,7 @@ int llama_server(common_params & params, int argc, char ** argv) {
 
     if (!params.server_tools.empty() || !mcp_mgr.empty()) {
         try {
-            tools.setup(params.server_tools, mcp_mgr, params.server_tools_runtime);
+            tools.setup(params.server_tools, mcp_mgr);
         } catch (const std::exception & e) {
             SRV_ERR("tools setup failed: %s\n", e.what());
             return 1;
@@ -348,9 +348,6 @@ int llama_server(common_params & params, int argc, char ** argv) {
         if (!params.server_tools.empty()) {
             warn_names.push_back("built-in tools (experimental)");
         }
-        if (!params.server_tools_runtime.empty()) {
-            warn_names.push_back("tools runtime (experimental)");
-        }
         if (!mcp_mgr.empty()) {
             warn_names.push_back("MCP servers (experimental)");
         }

tools/server/tests/unit/test_tools_builtin.py

@@ -1,6 +1,4 @@
 import os
-import shutil
-import subprocess
 
 import pytest
 from utils import *
@@ -148,83 +146,6 @@ def test_tools_builtin_cwd_header():
             os.remove(marker_path)
 
 
-def _docker_unavailable_reason() -> str | None:
-    """None if docker can be used to run a container, otherwise the reason it can't."""
-    docker_bin = shutil.which("docker")
-    if docker_bin is None:
-        return "docker is not installed"
-    try:
-        subprocess.run([docker_bin, "info"], capture_output=True, timeout=5, check=True)
-    except Exception as e:
-        return f"docker daemon is not usable: {e}"
-    return None
-
-
-@pytest.fixture
-def docker_container():
-    reason = _docker_unavailable_reason()
-    if reason is not None:
-        pytest.skip(reason)  # ty: ignore[too-many-positional-arguments, invalid-argument-type]
-
-    proc = subprocess.run(
-        ["docker", "run", "-d", "--rm", "busybox", "sleep", "300"],
-        capture_output=True, text=True,
-    )
-    if proc.returncode != 0:
-        pytest.skip(f"failed to start docker container: {proc.stderr.strip()}")  # ty: ignore[too-many-positional-arguments, invalid-argument-type]
-
-    container_id = proc.stdout.strip()
-    try:
-        yield container_id
-    finally:
-        subprocess.run(["docker", "rm", "-f", container_id], capture_output=True)
-
-
-def test_tools_builtin_docker_header(docker_container: str):
-    global server
-    server.start()
-
-    headers = {"x-tool-docker": docker_container, "x-tool-cwd": "/tmp"}
-
-    write_res = call_tool("write_file", {"path": "test.log", "content": "hello docker\n"}, headers=headers)
-    assert write_res["result"] == "file written successfully"
-
-    read_res = call_tool("read_file", {"path": "test.log"}, headers=headers)
-    assert read_res["plain_text_response"] == "hello docker\n"
-
-    exec_res = call_tool("exec_shell_command", {"command": "cat test.log"}, headers=headers)
-    assert "hello docker" in exec_res["plain_text_response"]
-
-
-def test_tools_builtin_docker_runtime_cleans_up_spawned_container():
-    reason = _docker_unavailable_reason()
-    if reason is not None:
-        pytest.skip(reason)  # ty: ignore[too-many-positional-arguments, invalid-argument-type]
-
-    global server
-    server.server_tools_runtime = "docker:busybox"
-    server.start()
-
-    # exec_shell_command runs inside the container spawned for --tools-runtime; docker sets
-    # the container's hostname to its own short id, so this also tells us which one to check
-    res = call_tool("exec_shell_command", {"command": "hostname"})
-    container_id = res["plain_text_response"].splitlines()[0].strip()
-    assert len(container_id) >= 8, res
-
-    running = subprocess.run(
-        ["docker", "inspect", "-f", "{{.State.Running}}", container_id],
-        capture_output=True, text=True,
-    )
-    assert running.returncode == 0 and running.stdout.strip() == "true", running.stderr
-
-    server.stop()
-
-    # a clean server shutdown must stop and remove the container it spawned (it runs with --rm),
-    # not leave it behind as an abandoned child
-    leftover = subprocess.run(["docker", "inspect", container_id], capture_output=True, text=True)
-    assert leftover.returncode != 0, f"container {container_id} was not cleaned up after server exit"
-
-
 def test_tools_builtin_edit_file_rejects_overlapping_edits():
     global server
     server.start()

tools/server/tests/utils.py

@@ -115,7 +115,6 @@ class ServerProcess:
     backend_sampling: bool = False
     gcp_compat: bool = False
     server_tools: str | None = None
-    server_tools_runtime: str | None = None
     mcp_servers_config: str | None = None
     mcp_servers_json: str | None = None
     cors_origins: str | None = None
@@ -268,8 +267,6 @@ class ServerProcess:
             server_args.append("--ui-mcp-proxy")
         if self.server_tools:
             server_args.extend(["--tools", self.server_tools])
-        if self.server_tools_runtime:
-            server_args.extend(["--tools-runtime", self.server_tools_runtime])
         if self.mcp_servers_config:
             server_args.extend(["--mcp-servers-config", self.mcp_servers_config])
         if self.mcp_servers_json:

tools/tts/CMakeLists.txt

@@ -1,6 +1,6 @@
 set(TARGET llama-tts)
 add_executable(${TARGET} tts.cpp)
-target_link_libraries(${TARGET} PRIVATE llama llama-common ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama llama-common mtmd ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 if(LLAMA_TOOLS_INSTALL)

tools/tts/README.md

@@ -1,117 +1,34 @@
-# llama.cpp/example/tts
-This example demonstrates the Text To Speech feature. It uses a
-[model](https://www.outeai.com/blog/outetts-0.2-500m) from
-[outeai](https://www.outeai.com/).
+# llama.cpp TTS
 
-## Quickstart
-If you have built llama.cpp with SSL support you can simply run the
-following command and the required models will be downloaded automatically:
-```console
-$ build/bin/llama-tts --tts-oute-default -p "Hello world" && aplay output.wav
-```
-For details about the models and how to convert them to the required format
-see the following sections.
+This is a tool to demonstrate audio generation capability in llama.cpp via `libmtmd`. It was added via PR [#26254](https://github.com/ggml-org/llama.cpp/pull/26254)
 
-### Model conversion
-Checkout or download the model that contains the LLM model:
-```console
-$ pushd models
-$ git clone --branch main --single-branch --depth 1 https://huggingface.co/OuteAI/OuteTTS-0.2-500M
-$ cd OuteTTS-0.2-500M && git lfs install && git lfs pull
-$ popd
-```
-Convert the model to .gguf format:
-```console
-(venv) python convert_hf_to_gguf.py models/OuteTTS-0.2-500M \
-    --outfile models/outetts-0.2-0.5B-f16.gguf --outtype f16
-```
-The generated model will be `models/outetts-0.2-0.5B-f16.gguf`.
+Note: this tool used to serve as a demo for OuteTTS, but it was converted to a more model-agnostic tool.
 
-We can optionally quantize this to Q8_0 using the following command:
-```console
-$ build/bin/llama-quantize models/outetts-0.2-0.5B-f16.gguf \
-    models/outetts-0.2-0.5B-q8_0.gguf q8_0
-```
-The quantized model will be `models/outetts-0.2-0.5B-q8_0.gguf`.
+## Common usage
 
-Next we do something similar for the audio decoder. First download or checkout
-the model for the voice decoder:
-```console
-$ pushd models
-$ git clone --branch main --single-branch --depth 1 https://huggingface.co/novateur/WavTokenizer-large-speech-75token
-$ cd WavTokenizer-large-speech-75token && git lfs install && git lfs pull
-$ popd
-```
-This model file is a PyTorch checkpoint (.ckpt) and we first need to convert it to
-huggingface format:
-```console
-(venv) python tools/tts/convert_pt_to_hf.py \
-    models/WavTokenizer-large-speech-75token/wavtokenizer_large_speech_320_24k.ckpt
-...
-Model has been successfully converted and saved to models/WavTokenizer-large-speech-75token/model.safetensors
-Metadata has been saved to models/WavTokenizer-large-speech-75token/index.json
-Config has been saved to models/WavTokenizer-large-speech-75tokenconfig.json
-```
-Then we can convert the huggingface format to gguf:
-```console
-(venv) python convert_hf_to_gguf.py models/WavTokenizer-large-speech-75token \
-    --outfile models/wavtokenizer-large-75-f16.gguf --outtype f16
-...
-INFO:hf-to-gguf:Model successfully exported to models/wavtokenizer-large-75-f16.gguf
+Simple usage:
+
+```sh
+llama-tts -hf ggml-org/Qwen3-TTS-12Hz-1.7B-Base-GGUF -p "Hello world" --output out.wav
 ```
 
-### Running the example
+Common params:
+- Sampling params such as `--top-k`, `--top-p`, `--temp`, etc.
+- `-n <number_of_frames>` limits the output length, e.g. `-n 500`. Note that how many milliseconds each frame represents varies by model
+- Core inference params such as `-ngl`, `-b`, `-ub`, etc.
 
-With both of the models generated, the LLM model and the voice decoder model,
-we can run the example:
-```console
-$ build/bin/llama-tts -m  ./models/outetts-0.2-0.5B-q8_0.gguf \
-    -mv ./models/wavtokenizer-large-75-f16.gguf \
-    -p "Hello world"
-...
-main: audio written to file 'output.wav'
-```
-The output.wav file will contain the audio of the prompt. This can be heard
-by playing the file with a media player. On Linux the following command will
-play the audio:
-```console
-$ aplay output.wav
-```
+## Qwen3-TTS
 
-### Running the example with llama-server
-Running this example with `llama-server` is also possible and requires two
-server instances to be started. One will serve the LLM model and the other
-will serve the voice decoder model.
+Available params:
+- `--tts-lang` can be `zh`, `en`, `de`, `it`, `pt`, `es`, `ja`, `ko`, `fr`, `ru` (default: `en`)
+- `--tts-speaker-file` should point to a speaker reference audio file (wav, mp3)
 
-The LLM model server can be started with the following command:
-```console
-$ ./build/bin/llama-server -m ./models/outetts-0.2-0.5B-q8_0.gguf --port 8020
-```
+Example usage:
 
-And the voice decoder model server can be started using:
-```console
-./build/bin/llama-server -m ./models/wavtokenizer-large-75-f16.gguf --port 8021 --embeddings --pooling none
-```
-
-Then we can run [tts-outetts.py](tts-outetts.py) to generate the audio.
-
-First create a virtual environment for python and install the required
-dependencies (this in only required to be done once):
-```console
-$ python3 -m venv venv
-$ source venv/bin/activate
-(venv) pip install requests numpy
-```
-
-And then run the python script using:
-```conole
-(venv) python ./tools/tts/tts-outetts.py http://localhost:8020 http://localhost:8021 "Hello world"
-spectrogram generated: n_codes: 90, n_embd: 1282
-converting to audio ...
-audio generated: 28800 samples
-audio written to file "output.wav"
-```
-And to play the audio we can again use aplay or any other media player:
-```console
-$ aplay output.wav
+```sh
+llama-tts -hf ggml-org/Qwen3-TTS-12Hz-1.7B-Base-GGUF \
+    -p "Hello world" \
+    --tts-lang english \
+    --tts-speaker-file speaker.mp3 \
+    --output out.wav
 ```

tools/tts/convert_pt_to_hf.py

@@ -1,180 +0,0 @@
-# convert the https://huggingface.co/novateur/WavTokenizer-large-speech-75token to HF format
-# the goal is to be able to reuse the convert_hf_to_gguf.py after that to create a GGUF file with the WavTokenizer decoder
-#
-# TODO: this script is LLM-generated and probably very inefficient and should be rewritten
-
-import torch
-import json
-import os
-import sys
-import re
-
-from safetensors.torch import save_file
-
-# default
-model_path = './model.pt'
-
-# read from CLI
-if len(sys.argv) > 1:
-    model_path = sys.argv[1]
-
-# get the directory of the input model
-path_dst = os.path.dirname(model_path)
-
-print(f"Loading model from {model_path}")
-
-model = torch.load(model_path, map_location='cpu')
-
-#print(model)
-
-# print all keys
-for key in model.keys():
-    print(key)
-    if key == 'hyper_parameters':
-        #print(model[key])
-        # dump as json pretty
-        print(json.dumps(model[key], indent=4))
-    #if key != 'state_dict' and key != 'optimizer_states':
-    #    print(model[key])
-
-# Check if the loaded model is a state_dict or a model instance
-if isinstance(model, torch.nn.Module):
-    state_dict = model.state_dict()
-else:
-    state_dict = model
-
-# Print the structure of the state_dict to understand its format
-print("State dictionary keys:")
-for key in state_dict.keys():
-    print(key)
-
-# Ensure the state_dict is flat and contains only torch.Tensor objects
-def flatten_state_dict(state_dict, parent_key='', sep='.'):
-    items = []
-    items_new = []
-
-    for k, v in state_dict.items():
-        new_key = f"{parent_key}{sep}{k}" if parent_key else k
-        if isinstance(v, torch.Tensor):
-            items.append((new_key, v))
-        elif isinstance(v, dict):
-            items.extend(flatten_state_dict(v, new_key, sep=sep).items())
-            return dict(items)
-
-    size_total_mb = 0
-
-    for key, value in list(items):
-        # keep only what we need for inference
-        if not key.startswith('state_dict.feature_extractor.encodec.quantizer.') and \
-           not key.startswith('state_dict.backbone.') and \
-           not key.startswith('state_dict.head.out'):
-               print('Skipping key: ', key)
-               continue
-
-        new_key = key
-
-        new_key = new_key.replace('state_dict.', '')
-        new_key = new_key.replace('pos_net', 'posnet')
-
-        # check if matches "backbone.posnet.%d.bias" or "backbone.posnet.%d.weight"
-        if new_key.startswith("backbone.posnet."):
-            match = re.match(r"backbone\.posnet\.(\d+)\.(bias|weight)", new_key)
-            if match:
-               new_key = f"backbone.posnet.{match.group(1)}.norm.{match.group(2)}"
-
-        # "feature_extractor.encodec.quantizer.vq.layers.0._codebook.embed" -> "backbone.embedding.weight"
-        if new_key == "feature_extractor.encodec.quantizer.vq.layers.0._codebook.embed":
-            new_key = "backbone.embedding.weight"
-
-        # these are the only rows used
-        # ref: https://github.com/edwko/OuteTTS/blob/a613e79c489d8256dd657ea9168d78de75895d82/outetts/wav_tokenizer/audio_codec.py#L100
-        if new_key.endswith("norm.scale.weight"):
-            new_key = new_key.replace("norm.scale.weight", "norm.weight")
-            value = value[0]
-
-        if new_key.endswith("norm.shift.weight"):
-            new_key = new_key.replace("norm.shift.weight", "norm.bias")
-            value = value[0]
-
-        if new_key.endswith("gamma"):
-            new_key = new_key.replace("gamma", "gamma.weight")
-
-        # convert from 1D [768] to 2D [768, 1] so that ggml_add can broadcast the bias
-        if (new_key.endswith("norm.weight") or new_key.endswith("norm1.weight") or new_key.endswith("norm2.weight") or new_key.endswith(".bias")) and (new_key.startswith("backbone.posnet") or new_key.startswith("backbone.embed.bias")):
-            value = value.unsqueeze(1)
-
-        if new_key.endswith("dwconv.bias"):
-            value = value.unsqueeze(1)
-
-        size_mb = value.element_size() * value.nelement() / (1024 * 1024)
-        print(f"{size_mb:8.2f} MB - {new_key}: {value.shape}")
-
-        size_total_mb += size_mb
-
-        #print(key, '->', new_key, ': ', value)
-        #print(key, '->', new_key)
-
-        items_new.append((new_key, value))
-
-    print(f"Total size: {size_total_mb:8.2f} MB")
-
-    return dict(items_new)
-
-flattened_state_dict = flatten_state_dict(state_dict)
-
-
-# Convert the model to the safetensors format
-output_path = path_dst + '/model.safetensors'
-save_file(flattened_state_dict, output_path)
-
-print(f"Model has been successfully converted and saved to {output_path}")
-
-# Calculate the total size of the .safetensors file
-total_size = os.path.getsize(output_path)
-
-# Create the weight map
-weight_map = {
-    "model.safetensors": ["*"]  # Assuming all weights are in one file
-}
-
-# Create metadata for the index.json file
-metadata = {
-    "total_size": total_size,
-    "weight_map": weight_map
-}
-
-# Save the metadata to index.json
-index_path = path_dst + '/index.json'
-with open(index_path, 'w') as f:
-    json.dump(metadata, f, indent=4)
-
-print(f"Metadata has been saved to {index_path}")
-
-config = {
-    "architectures": [
-        "WavTokenizerDec"
-    ],
-    "hidden_size": 1282,
-    "n_embd_features": 512,
-    "n_ff": 2304,
-    "vocab_size": 4096,
-    "n_head": 1,
-    "layer_norm_epsilon": 1e-6,
-    "group_norm_epsilon": 1e-6,
-    "group_norm_groups": 32,
-    "max_position_embeddings": 8192, # ?
-    "n_layer": 12,
-    "posnet": {
-        "n_embd": 768,
-        "n_layer": 6
-    },
-    "convnext": {
-        "n_embd": 768,
-        "n_layer": 12
-    },
-}
-
-with open(path_dst + '/config.json', 'w') as f:
-    json.dump(config, f, indent=4)
-
-print(f"Config has been saved to {path_dst + 'config.json'}")

tools/tts/tts-outetts.py

@@ -1,299 +0,0 @@
-import sys
-#import json
-#import struct
-import requests
-import re
-import struct
-import numpy as np
-from concurrent.futures import ThreadPoolExecutor
-
-
-def fill_hann_window(size, periodic=True):
-    if periodic:
-        return np.hanning(size + 1)[:-1]
-    return np.hanning(size)
-
-
-def irfft(n_fft, complex_input):
-    return np.fft.irfft(complex_input, n=n_fft)
-
-
-def fold(buffer, n_out, n_win, n_hop, n_pad):
-    result = np.zeros(n_out)
-    n_frames = len(buffer) // n_win
-
-    for i in range(n_frames):
-        start = i * n_hop
-        end = start + n_win
-        result[start:end] += buffer[i * n_win:(i + 1) * n_win]
-
-    return result[n_pad:-n_pad] if n_pad > 0 else result
-
-
-def process_frame(args):
-    l, n_fft, ST, hann = args
-    frame = irfft(n_fft, ST[l])
-    frame = frame * hann
-    hann2 = hann * hann
-    return frame, hann2
-
-
-def embd_to_audio(embd, n_codes, n_embd, n_thread=4):
-    embd = np.asarray(embd, dtype=np.float32).reshape(n_codes, n_embd)
-
-    n_fft = 1280
-    n_hop = 320
-    n_win = 1280
-    n_pad = (n_win - n_hop) // 2
-    n_out = (n_codes - 1) * n_hop + n_win
-
-    hann = fill_hann_window(n_fft, True)
-
-    E = np.zeros((n_embd, n_codes), dtype=np.float32)
-    for l in range(n_codes):
-        for k in range(n_embd):
-            E[k, l] = embd[l, k]
-
-    half_embd = n_embd // 2
-    S = np.zeros((n_codes, half_embd + 1), dtype=np.complex64)
-
-    for k in range(half_embd):
-        for l in range(n_codes):
-            mag = E[k, l]
-            phi = E[k + half_embd, l]
-
-            mag = np.clip(np.exp(mag), 0, 1e2)
-            S[l, k] = mag * np.exp(1j * phi)
-
-    res = np.zeros(n_codes * n_fft)
-    hann2_buffer = np.zeros(n_codes * n_fft)
-
-    with ThreadPoolExecutor(max_workers=n_thread) as executor:
-        args = [(l, n_fft, S, hann) for l in range(n_codes)]
-        results = list(executor.map(process_frame, args))
-
-        for l, (frame, hann2) in enumerate(results):
-            res[l*n_fft:(l+1)*n_fft] = frame
-            hann2_buffer[l*n_fft:(l+1)*n_fft] = hann2
-
-    audio = fold(res, n_out, n_win, n_hop, n_pad)
-    env = fold(hann2_buffer, n_out, n_win, n_hop, n_pad)
-
-    mask = env > 1e-10
-    audio[mask] /= env[mask]
-
-    return audio
-
-
-def save_wav(filename, audio_data, sample_rate):
-    num_channels = 1
-    bits_per_sample = 16
-    bytes_per_sample = bits_per_sample // 8
-    data_size = len(audio_data) * bytes_per_sample
-    byte_rate = sample_rate * num_channels * bytes_per_sample
-    block_align = num_channels * bytes_per_sample
-    chunk_size = 36 + data_size  # 36 = size of header minus first 8 bytes
-
-    header = struct.pack(
-        '<4sI4s4sIHHIIHH4sI',
-        b'RIFF',
-        chunk_size,
-        b'WAVE',
-        b'fmt ',
-        16,                # fmt chunk size
-        1,                 # audio format (PCM)
-        num_channels,
-        sample_rate,
-        byte_rate,
-        block_align,
-        bits_per_sample,
-        b'data',
-        data_size
-    )
-
-    audio_data = np.clip(audio_data * 32767, -32768, 32767)
-    pcm_data = audio_data.astype(np.int16)
-
-    with open(filename, 'wb') as f:
-        f.write(header)
-        f.write(pcm_data.tobytes())
-
-
-def process_text(text: str):
-    text = re.sub(r'\d+(\.\d+)?', lambda x: x.group(), text.lower()) # TODO this needs to be fixed
-    text = re.sub(r'[-_/,\.\\]', ' ', text)
-    text = re.sub(r'[^a-z\s]', '', text)
-    text = re.sub(r'\s+', ' ', text).strip()
-    return text.split()
-
-# usage:
-# python tts-outetts.py http://server-llm:port http://server-dec:port "text"
-
-if len(sys.argv) <= 3:
-    print("usage: python tts-outetts.py http://server-llm:port http://server-dec:port \"text\"")
-    exit(1)
-
-host_llm = sys.argv[1]
-host_dec = sys.argv[2]
-text = sys.argv[3]
-
-prefix = """<|im_start|>
-<|text_start|>the<|text_sep|>overall<|text_sep|>package<|text_sep|>from<|text_sep|>just<|text_sep|>two<|text_sep|>people<|text_sep|>is<|text_sep|>pretty<|text_sep|>remarkable<|text_sep|>sure<|text_sep|>i<|text_sep|>have<|text_sep|>some<|text_sep|>critiques<|text_sep|>about<|text_sep|>some<|text_sep|>of<|text_sep|>the<|text_sep|>gameplay<|text_sep|>aspects<|text_sep|>but<|text_sep|>its<|text_sep|>still<|text_sep|>really<|text_sep|>enjoyable<|text_sep|>and<|text_sep|>it<|text_sep|>looks<|text_sep|>lovely<|text_sep|>"""
-
-words = process_text(text)
-words = "<|text_sep|>".join([i.strip() for i in words])
-words += "<|text_end|>\n"
-
-# voice data
-# TODO: load from json
-#suffix = """<|audio_start|>
-#the<|t_0.08|><|code_start|><|257|><|740|><|636|><|913|><|788|><|1703|><|code_end|>
-#overall<|t_0.36|><|code_start|><|127|><|201|><|191|><|774|><|700|><|532|><|1056|><|557|><|798|><|298|><|1741|><|747|><|1662|><|1617|><|1702|><|1527|><|368|><|1588|><|1049|><|1008|><|1625|><|747|><|1576|><|728|><|1019|><|1696|><|1765|><|code_end|>
-#package<|t_0.56|><|code_start|><|935|><|584|><|1319|><|627|><|1016|><|1491|><|1344|><|1117|><|1526|><|1040|><|239|><|1435|><|951|><|498|><|723|><|1180|><|535|><|789|><|1649|><|1637|><|78|><|465|><|1668|><|901|><|595|><|1675|><|117|><|1009|><|1667|><|320|><|840|><|79|><|507|><|1762|><|1508|><|1228|><|1768|><|802|><|1450|><|1457|><|232|><|639|><|code_end|>
-#from<|t_0.19|><|code_start|><|604|><|782|><|1682|><|872|><|1532|><|1600|><|1036|><|1761|><|647|><|1554|><|1371|><|653|><|1595|><|950|><|code_end|>
-#just<|t_0.25|><|code_start|><|1782|><|1670|><|317|><|786|><|1748|><|631|><|599|><|1155|><|1364|><|1524|><|36|><|1591|><|889|><|1535|><|541|><|440|><|1532|><|50|><|870|><|code_end|>
-#two<|t_0.24|><|code_start|><|1681|><|1510|><|673|><|799|><|805|><|1342|><|330|><|519|><|62|><|640|><|1138|><|565|><|1552|><|1497|><|1552|><|572|><|1715|><|1732|><|code_end|>
-#people<|t_0.39|><|code_start|><|593|><|274|><|136|><|740|><|691|><|633|><|1484|><|1061|><|1138|><|1485|><|344|><|428|><|397|><|1562|><|645|><|917|><|1035|><|1449|><|1669|><|487|><|442|><|1484|><|1329|><|1832|><|1704|><|600|><|761|><|653|><|269|><|code_end|>
-#is<|t_0.16|><|code_start|><|566|><|583|><|1755|><|646|><|1337|><|709|><|802|><|1008|><|485|><|1583|><|652|><|10|><|code_end|>
-#pretty<|t_0.32|><|code_start|><|1818|><|1747|><|692|><|733|><|1010|><|534|><|406|><|1697|><|1053|><|1521|><|1355|><|1274|><|816|><|1398|><|211|><|1218|><|817|><|1472|><|1703|><|686|><|13|><|822|><|445|><|1068|><|code_end|>
-#remarkable<|t_0.68|><|code_start|><|230|><|1048|><|1705|><|355|><|706|><|1149|><|1535|><|1787|><|1356|><|1396|><|835|><|1583|><|486|><|1249|><|286|><|937|><|1076|><|1150|><|614|><|42|><|1058|><|705|><|681|><|798|><|934|><|490|><|514|><|1399|><|572|><|1446|><|1703|><|1346|><|1040|><|1426|><|1304|><|664|><|171|><|1530|><|625|><|64|><|1708|><|1830|><|1030|><|443|><|1509|><|1063|><|1605|><|1785|><|721|><|1440|><|923|><|code_end|>
-#sure<|t_0.36|><|code_start|><|792|><|1780|><|923|><|1640|><|265|><|261|><|1525|><|567|><|1491|><|1250|><|1730|><|362|><|919|><|1766|><|543|><|1|><|333|><|113|><|970|><|252|><|1606|><|133|><|302|><|1810|><|1046|><|1190|><|1675|><|code_end|>
-#i<|t_0.08|><|code_start|><|123|><|439|><|1074|><|705|><|1799|><|637|><|code_end|>
-#have<|t_0.16|><|code_start|><|1509|><|599|><|518|><|1170|><|552|><|1029|><|1267|><|864|><|419|><|143|><|1061|><|0|><|code_end|>
-#some<|t_0.16|><|code_start|><|619|><|400|><|1270|><|62|><|1370|><|1832|><|917|><|1661|><|167|><|269|><|1366|><|1508|><|code_end|>
-#critiques<|t_0.60|><|code_start|><|559|><|584|><|1163|><|1129|><|1313|><|1728|><|721|><|1146|><|1093|><|577|><|928|><|27|><|630|><|1080|><|1346|><|1337|><|320|><|1382|><|1175|><|1682|><|1556|><|990|><|1683|><|860|><|1721|><|110|><|786|><|376|><|1085|><|756|><|1523|><|234|><|1334|><|1506|><|1578|><|659|><|612|><|1108|><|1466|><|1647|><|308|><|1470|><|746|><|556|><|1061|><|code_end|>
-#about<|t_0.29|><|code_start|><|26|><|1649|><|545|><|1367|><|1263|><|1728|><|450|><|859|><|1434|><|497|><|1220|><|1285|><|179|><|755|><|1154|><|779|><|179|><|1229|><|1213|><|922|><|1774|><|1408|><|code_end|>
-#some<|t_0.23|><|code_start|><|986|><|28|><|1649|><|778|><|858|><|1519|><|1|><|18|><|26|><|1042|><|1174|><|1309|><|1499|><|1712|><|1692|><|1516|><|1574|><|code_end|>
-#of<|t_0.07|><|code_start|><|197|><|716|><|1039|><|1662|><|64|><|code_end|>
-#the<|t_0.08|><|code_start|><|1811|><|1568|><|569|><|886|><|1025|><|1374|><|code_end|>
-#gameplay<|t_0.48|><|code_start|><|1269|><|1092|><|933|><|1362|><|1762|><|1700|><|1675|><|215|><|781|><|1086|><|461|><|838|><|1022|><|759|><|649|><|1416|><|1004|><|551|><|909|><|787|><|343|><|830|><|1391|><|1040|><|1622|><|1779|><|1360|><|1231|><|1187|><|1317|><|76|><|997|><|989|><|978|><|737|><|189|><|code_end|>
-#aspects<|t_0.56|><|code_start|><|1423|><|797|><|1316|><|1222|><|147|><|719|><|1347|><|386|><|1390|><|1558|><|154|><|440|><|634|><|592|><|1097|><|1718|><|712|><|763|><|1118|><|1721|><|1311|><|868|><|580|><|362|><|1435|><|868|><|247|><|221|><|886|><|1145|><|1274|><|1284|><|457|><|1043|><|1459|><|1818|><|62|><|599|><|1035|><|62|><|1649|><|778|><|code_end|>
-#but<|t_0.20|><|code_start|><|780|><|1825|><|1681|><|1007|><|861|><|710|><|702|><|939|><|1669|><|1491|><|613|><|1739|><|823|><|1469|><|648|><|code_end|>
-#its<|t_0.09|><|code_start|><|92|><|688|><|1623|><|962|><|1670|><|527|><|599|><|code_end|>
-#still<|t_0.27|><|code_start|><|636|><|10|><|1217|><|344|><|713|><|957|><|823|><|154|><|1649|><|1286|><|508|><|214|><|1760|><|1250|><|456|><|1352|><|1368|><|921|><|615|><|5|><|code_end|>
-#really<|t_0.36|><|code_start|><|55|><|420|><|1008|><|1659|><|27|><|644|><|1266|><|617|><|761|><|1712|><|109|><|1465|><|1587|><|503|><|1541|><|619|><|197|><|1019|><|817|><|269|><|377|><|362|><|1381|><|507|><|1488|><|4|><|1695|><|code_end|>
-#enjoyable<|t_0.49|><|code_start|><|678|><|501|><|864|><|319|><|288|><|1472|><|1341|><|686|><|562|><|1463|><|619|><|1563|><|471|><|911|><|730|><|1811|><|1006|><|520|><|861|><|1274|><|125|><|1431|><|638|><|621|><|153|><|876|><|1770|><|437|><|987|><|1653|><|1109|><|898|><|1285|><|80|><|593|><|1709|><|843|><|code_end|>
-#and<|t_0.15|><|code_start|><|1285|><|987|><|303|><|1037|><|730|><|1164|><|502|><|120|><|1737|><|1655|><|1318|><|code_end|>
-#it<|t_0.09|><|code_start|><|848|><|1366|><|395|><|1601|><|1513|><|593|><|1302|><|code_end|>
-#looks<|t_0.27|><|code_start|><|1281|><|1266|><|1755|><|572|><|248|><|1751|><|1257|><|695|><|1380|><|457|><|659|><|585|><|1315|><|1105|><|1776|><|736|><|24|><|736|><|654|><|1027|><|code_end|>
-#lovely<|t_0.56|><|code_start|><|634|><|596|><|1766|><|1556|><|1306|><|1285|><|1481|><|1721|><|1123|><|438|><|1246|><|1251|><|795|><|659|><|1381|><|1658|><|217|><|1772|><|562|><|952|><|107|><|1129|><|1112|><|467|><|550|><|1079|><|840|><|1615|><|1469|><|1380|><|168|><|917|><|836|><|1827|><|437|><|583|><|67|><|595|><|1087|><|1646|><|1493|><|1677|><|code_end|>"""
-
-# TODO: tokenization is slow for some reason - here is pre-tokenized input
-suffix = [ 151667, 198, 1782, 155780, 151669, 151929, 152412, 152308, 152585, 152460, 153375, 151670, 198, 74455,
-          155808, 151669, 151799, 151873, 151863, 152446, 152372, 152204, 152728, 152229, 152470, 151970, 153413,
-          152419, 153334, 153289, 153374, 153199, 152040, 153260, 152721, 152680, 153297, 152419, 153248, 152400,
-          152691, 153368, 153437, 151670, 198, 1722, 155828, 151669, 152607, 152256, 152991, 152299, 152688, 153163,
-          153016, 152789, 153198, 152712, 151911, 153107, 152623, 152170, 152395, 152852, 152207, 152461, 153321,
-          153309, 151750, 152137, 153340, 152573, 152267, 153347, 151789, 152681, 153339, 151992, 152512, 151751,
-          152179, 153434, 153180, 152900, 153440, 152474, 153122, 153129, 151904, 152311, 151670, 198, 1499, 155791,
-          151669, 152276, 152454, 153354, 152544, 153204, 153272, 152708, 153433, 152319, 153226, 153043, 152325,
-          153267, 152622, 151670, 198, 4250, 155797, 151669, 153454, 153342, 151989, 152458, 153420, 152303, 152271,
-          152827, 153036, 153196, 151708, 153263, 152561, 153207, 152213, 152112, 153204, 151722, 152542, 151670, 198,
-          19789, 155796, 151669, 153353, 153182, 152345, 152471, 152477, 153014, 152002, 152191, 151734, 152312, 152810,
-          152237, 153224, 153169, 153224, 152244, 153387, 153404, 151670, 198, 16069, 155811, 151669, 152265, 151946,
-          151808, 152412, 152363, 152305, 153156, 152733, 152810, 153157, 152016, 152100, 152069, 153234, 152317,
-          152589, 152707, 153121, 153341, 152159, 152114, 153156, 153001, 153504, 153376, 152272, 152433, 152325,
-          151941, 151670, 198, 285, 155788, 151669, 152238, 152255, 153427, 152318, 153009, 152381, 152474, 152680,
-          152157, 153255, 152324, 151682, 151670, 198, 32955, 155804, 151669, 153490, 153419, 152364, 152405, 152682,
-          152206, 152078, 153369, 152725, 153193, 153027, 152946, 152488, 153070, 151883, 152890, 152489, 153144,
-          153375, 152358, 151685, 152494, 152117, 152740, 151670, 198, 37448, 480, 155840, 151669, 151902, 152720,
-          153377, 152027, 152378, 152821, 153207, 153459, 153028, 153068, 152507, 153255, 152158, 152921, 151958,
-          152609, 152748, 152822, 152286, 151714, 152730, 152377, 152353, 152470, 152606, 152162, 152186, 153071,
-          152244, 153118, 153375, 153018, 152712, 153098, 152976, 152336, 151843, 153202, 152297, 151736, 153380,
-          153502, 152702, 152115, 153181, 152735, 153277, 153457, 152393, 153112, 152595, 151670, 198, 19098, 155808,
-          151669, 152464, 153452, 152595, 153312, 151937, 151933, 153197, 152239, 153163, 152922, 153402, 152034,
-          152591, 153438, 152215, 151673, 152005, 151785, 152642, 151924, 153278, 151805, 151974, 153482, 152718,
-          152862, 153347, 151670, 198, 72, 155780, 151669, 151795, 152111, 152746, 152377, 153471, 152309, 151670, 198,
-          19016, 155788, 151669, 153181, 152271, 152190, 152842, 152224, 152701, 152939, 152536, 152091, 151815, 152733,
-          151672, 151670, 198, 14689, 155788, 151669, 152291, 152072, 152942, 151734, 153042, 153504, 152589, 153333,
-          151839, 151941, 153038, 153180, 151670, 198, 36996, 8303, 155832, 151669, 152231, 152256, 152835, 152801,
-          152985, 153400, 152393, 152818, 152765, 152249, 152600, 151699, 152302, 152752, 153018, 153009, 151992,
-          153054, 152847, 153354, 153228, 152662, 153355, 152532, 153393, 151782, 152458, 152048, 152757, 152428,
-          153195, 151906, 153006, 153178, 153250, 152331, 152284, 152780, 153138, 153319, 151980, 153142, 152418,
-          152228, 152733, 151670, 198, 9096, 155801, 151669, 151698, 153321, 152217, 153039, 152935, 153400, 152122,
-          152531, 153106, 152169, 152892, 152957, 151851, 152427, 152826, 152451, 151851, 152901, 152885, 152594,
-          153446, 153080, 151670, 198, 14689, 155795, 151669, 152658, 151700, 153321, 152450, 152530, 153191, 151673,
-          151690, 151698, 152714, 152846, 152981, 153171, 153384, 153364, 153188, 153246, 151670, 198, 1055, 155779,
-          151669, 151869, 152388, 152711, 153334, 151736, 151670, 198, 1782, 155780, 151669, 153483, 153240, 152241,
-          152558, 152697, 153046, 151670, 198, 5804, 1363, 155820, 151669, 152941, 152764, 152605, 153034, 153434,
-          153372, 153347, 151887, 152453, 152758, 152133, 152510, 152694, 152431, 152321, 153088, 152676, 152223,
-          152581, 152459, 152015, 152502, 153063, 152712, 153294, 153451, 153032, 152903, 152859, 152989, 151748,
-          152669, 152661, 152650, 152409, 151861, 151670, 198, 300, 7973, 155828, 151669, 153095, 152469, 152988,
-          152894, 151819, 152391, 153019, 152058, 153062, 153230, 151826, 152112, 152306, 152264, 152769, 153390,
-          152384, 152435, 152790, 153393, 152983, 152540, 152252, 152034, 153107, 152540, 151919, 151893, 152558,
-          152817, 152946, 152956, 152129, 152715, 153131, 153490, 151734, 152271, 152707, 151734, 153321, 152450,
-          151670, 198, 8088, 155792, 151669, 152452, 153497, 153353, 152679, 152533, 152382, 152374, 152611, 153341,
-          153163, 152285, 153411, 152495, 153141, 152320, 151670, 198, 1199, 155781, 151669, 151764, 152360, 153295,
-          152634, 153342, 152199, 152271, 151670, 198, 43366, 155799, 151669, 152308, 151682, 152889, 152016, 152385,
-          152629, 152495, 151826, 153321, 152958, 152180, 151886, 153432, 152922, 152128, 153024, 153040, 152593,
-          152287, 151677, 151670, 198, 53660, 155808, 151669, 151727, 152092, 152680, 153331, 151699, 152316, 152938,
-          152289, 152433, 153384, 151781, 153137, 153259, 152175, 153213, 152291, 151869, 152691, 152489, 151941,
-          152049, 152034, 153053, 152179, 153160, 151676, 153367, 151670, 198, 268, 4123, 480, 155821, 151669, 152350,
-          152173, 152536, 151991, 151960, 153144, 153013, 152358, 152234, 153135, 152291, 153235, 152143, 152583,
-          152402, 153483, 152678, 152192, 152533, 152946, 151797, 153103, 152310, 152293, 151825, 152548, 153442,
-          152109, 152659, 153325, 152781, 152570, 152957, 151752, 152265, 153381, 152515, 151670, 198, 437, 155787,
-          151669, 152957, 152659, 151975, 152709, 152402, 152836, 152174, 151792, 153409, 153327, 152990, 151670, 198,
-          275, 155781, 151669, 152520, 153038, 152067, 153273, 153185, 152265, 152974, 151670, 198, 94273, 155799,
-          151669, 152953, 152938, 153427, 152244, 151920, 153423, 152929, 152367, 153052, 152129, 152331, 152257,
-          152987, 152777, 153448, 152408, 151696, 152408, 152326, 152699, 151670, 198, 385, 16239, 155828, 151669,
-          152306, 152268, 153438, 153228, 152978, 152957, 153153, 153393, 152795, 152110, 152918, 152923, 152467,
-          152331, 153053, 153330, 151889, 153444, 152234, 152624, 151779, 152801, 152784, 152139, 152222, 152751,
-          152512, 153287, 153141, 153052, 151840, 152589, 152508, 153499, 152109, 152255, 151739, 152267, 152759,
-          153318, 153165, 153349, 151670, ]
-
-response = requests.post(
-    host_llm + "/completion",
-    json={
-        "prompt": [prefix + words, *suffix],
-        "n_predict": 1024,
-        "cache_prompt": True,
-        "return_tokens": True,
-        "samplers": ["top_k"],
-        "top_k": 16,
-        "seed": 1003,
-    }
-)
-
-response_json = response.json()
-
-#print(json.dumps(response_json, indent=4))
-#print(json.dumps(response_json["prompt"], indent=4).replace("\\n", "\n"))
-#print(json.dumps(response_json["timings"], indent=4))
-#print(json.dumps(response_json["tokens"], indent=4))
-
-codes = response_json["tokens"]
-
-codes = [t - 151672 for t in codes if t >= 151672 and t <= 155772]
-
-response = requests.post(
-    host_dec + "/embeddings",
-    json={
-        "input": [*codes],
-    }
-)
-
-response_json = response.json()
-
-#print(json.dumps(response_json, indent=4))
-
-# spectrogram
-embd = response_json[0]["embedding"]
-
-n_codes = len(embd)
-n_embd = len(embd[0])
-
-print('spectrogram generated: n_codes: %d, n_embd: %d' % (n_codes, n_embd))
-
-# post-process the spectrogram to convert to audio
-print('converting to audio ...')
-audio = embd_to_audio(embd, n_codes, n_embd)
-print('audio generated: %d samples' % len(audio))
-
-filename = "output.wav"
-sample_rate = 24000 # sampling rate
-
-# zero out first 0.25 seconds
-audio[:24000 // 4] = 0.0
-
-save_wav(filename, audio, sample_rate)
-print('audio written to file "%s"' % filename)

vendor/cpp-httplib/CMakeLists.txt

@@ -41,7 +41,7 @@ if (LLAMA_BUILD_BORINGSSL)
     set(FIPS OFF CACHE BOOL "Enable FIPS (BoringSSL)")
 
     set(BORINGSSL_GIT "https://boringssl.googlesource.com/boringssl" CACHE STRING "BoringSSL git repository")
-    set(BORINGSSL_VERSION "0.20260730.0" CACHE STRING "BoringSSL version")
+    set(BORINGSSL_VERSION "0.20260803.0" CACHE STRING "BoringSSL version")
 
     message(STATUS "Fetching BoringSSL version ${BORINGSSL_VERSION}")
 

vendor/cpp-httplib/httplib.cpp

@@ -1412,6 +1412,46 @@ bool stream_line_reader::getline() {
 #endif
 
   for (size_t i = 0;; i++) {
+    // Fast path: whatever the stream has already buffered can be scanned for
+    // the terminator in one pass. Asking for a byte at a time costs a virtual
+    // call, a bounds check and a one-byte copy per character of the request.
+    size_t buffered_size = 0;
+    if (auto buffered = strm_.buffered_data(buffered_size)) {
+      auto take = buffered_size;
+      auto terminated = false;
+
+      for (size_t at = 0; at < buffered_size;) {
+        auto nl = static_cast<const char *>(
+            memchr(buffered + at, '\n', buffered_size - at));
+        if (!nl) { break; }
+        auto pos = static_cast<size_t>(nl - buffered);
+#ifdef CPPHTTPLIB_ALLOW_LF_AS_LINE_TERMINATOR
+        take = pos + 1;
+        terminated = true;
+        break;
+#else
+        // A bare LF does not end the line; keep looking for CRLF. The CR may
+        // be the last byte of an earlier chunk, hence prev_byte.
+        if ((pos > 0 ? buffered[pos - 1] : prev_byte) == '\r') {
+          take = pos + 1;
+          terminated = true;
+          break;
+        }
+        at = pos + 1;
+#endif
+      }
+
+      if (size() + take > CPPHTTPLIB_MAX_LINE_LENGTH) { return false; }
+#ifndef CPPHTTPLIB_ALLOW_LF_AS_LINE_TERMINATOR
+      prev_byte = buffered[take - 1];
+#endif
+      append(buffered, take);
+      strm_.consume_buffered(take);
+      i += take;
+      if (terminated) { return true; }
+      continue;
+    }
+
     if (size() >= CPPHTTPLIB_MAX_LINE_LENGTH) {
       // Treat exceptionally long lines as an error to
       // prevent infinite loops/memory exhaustion
@@ -1443,16 +1483,26 @@ bool stream_line_reader::getline() {
   return true;
 }
 
-void stream_line_reader::append(char c) {
-  if (fixed_buffer_used_size_ < fixed_buffer_size_ - 1) {
-    fixed_buffer_[fixed_buffer_used_size_++] = c;
+void stream_line_reader::append(char c) { append(&c, 1); }
+
+void stream_line_reader::append(const char *data, size_t size) {
+  // Once the line has outgrown the fixed buffer everything must keep going to
+  // the growable one, even if a later chunk would have fit. Without the
+  // emptiness check a short append after a long one would land in the fixed
+  // buffer, which ptr() and size() no longer look at, and be lost.
+  if (growable_buffer_.empty() &&
+      fixed_buffer_used_size_ + size < fixed_buffer_size_) {
+    memcpy(fixed_buffer_ + fixed_buffer_used_size_, data, size);
+    fixed_buffer_used_size_ += size;
     fixed_buffer_[fixed_buffer_used_size_] = '\0';
   } else {
+    // Unlike the per-character overload, this can be the very first append of
+    // the line, so the fixed buffer may hold nothing and carry no terminator
+    // yet. assign() takes an explicit length and does not need one.
     if (growable_buffer_.empty()) {
-      assert(fixed_buffer_[fixed_buffer_used_size_] == '\0');
       growable_buffer_.assign(fixed_buffer_, fixed_buffer_used_size_);
     }
-    growable_buffer_ += c;
+    growable_buffer_.append(data, size);
   }
 }
 
@@ -1525,6 +1575,14 @@ bool mmap::open(const char *path) {
     is_open_empty_file = true;
     return false;
   }
+
+  if (addr_ == MAP_FAILED) {
+    // Clear the sentinel before `close()`, since `is_open()` only checks
+    // `addr_` against nullptr and `munmap()` must not be called with it.
+    addr_ = nullptr;
+    close();
+    return false;
+  }
 #endif
 
   return true;
@@ -1702,8 +1760,17 @@ public:
   socket_t socket() const override;
   time_t duration() const override;
   void set_read_timeout(time_t sec, time_t usec = 0) override;
+  const char *buffered_data(size_t &size) const override;
+  void consume_buffered(size_t size) override;
+
+  // The caller has just seen this socket become readable. Lets the next read
+  // skip its own readiness wait, which would otherwise ask the kernel a
+  // question that was answered a moment ago. Consumed by that read.
+  void set_readable_hint() { readable_hint_ = true; }
 
 private:
+  bool ensure_readable();
+
   socket_t sock_;
   time_t read_timeout_sec_;
   time_t read_timeout_usec_;
@@ -1715,6 +1782,7 @@ private:
   std::vector<char> read_buff_;
   size_t read_buff_off_ = 0;
   size_t read_buff_content_size_ = 0;
+  bool readable_hint_ = false;
 
   static const size_t read_buff_size_ = 1024l * 4;
 };
@@ -1782,6 +1850,9 @@ process_server_socket(const std::atomic<socket_t> &svr_sock, socket_t sock,
       [&](bool close_connection, bool &connection_closed) {
         SocketStream strm(sock, read_timeout_sec, read_timeout_usec,
                           write_timeout_sec, write_timeout_usec);
+        // process_server_socket_core() only gets here once keep_alive() has
+        // seen the socket go readable.
+        strm.set_readable_hint();
         return callback(strm, close_connection, connection_closed);
       });
 }
@@ -3071,19 +3142,49 @@ bool zstd_decompressor::decompress(const char *data, size_t data_length,
 }
 #endif
 
+bool contains_case_ignore(const std::string &s, const char *token) {
+  auto token_end = token + std::strlen(token);
+  return std::search(s.begin(), s.end(), token, token_end, [](char a, char b) {
+           return case_ignore::to_lower(a) == case_ignore::to_lower(b);
+         }) != s.end();
+}
+
+// Content codings are case-insensitive (RFC 9110 8.4.1). Matching them
+// case-sensitively would make a response labeled e.g. "GZIP" look like an
+// unknown coding, and its payload would be handed back still compressed.
+bool is_zlib_encoding(const std::string &encoding) {
+  return case_ignore::equal(encoding, "gzip") ||
+         case_ignore::equal(encoding, "deflate");
+}
+
+bool is_brotli_encoding(const std::string &encoding) {
+  return contains_case_ignore(encoding, "br");
+}
+
+bool is_zstd_encoding(const std::string &encoding) {
+  return contains_case_ignore(encoding, "zstd");
+}
+
+// Returns true if the content coding is one cpp-httplib is able to decompress
+// when the corresponding support is compiled in.
+bool is_known_content_encoding(const std::string &encoding) {
+  return is_zlib_encoding(encoding) || is_brotli_encoding(encoding) ||
+         is_zstd_encoding(encoding);
+}
+
 std::unique_ptr<decompressor>
 create_decompressor(const std::string &encoding) {
   std::unique_ptr<decompressor> decompressor;
 
-  if (encoding == "gzip" || encoding == "deflate") {
+  if (is_zlib_encoding(encoding)) {
 #ifdef CPPHTTPLIB_ZLIB_SUPPORT
     decompressor = detail::make_unique<gzip_decompressor>();
 #endif
-  } else if (encoding.find("br") != std::string::npos) {
+  } else if (is_brotli_encoding(encoding)) {
 #ifdef CPPHTTPLIB_BROTLI_SUPPORT
     decompressor = detail::make_unique<brotli_decompressor>();
 #endif
-  } else if (encoding == "zstd" || encoding.find("zstd") != std::string::npos) {
+  } else if (is_zstd_encoding(encoding)) {
 #ifdef CPPHTTPLIB_ZSTD_SUPPORT
     decompressor = detail::make_unique<zstd_decompressor>();
 #endif
@@ -3145,8 +3246,7 @@ const char *get_header_value(const Headers &headers,
 
 size_t get_header_value_count(const Headers &headers,
                                      const std::string &key) {
-  auto r = headers.equal_range(key);
-  return static_cast<size_t>(std::distance(r.first, r.second));
+  return headers.count(key);
 }
 
 template <typename Map>
@@ -3370,44 +3470,33 @@ ReadContentResult read_content_chunked(Stream &strm, T &x,
 bool is_chunked_transfer_encoding(const Headers &headers) {
   // RFC 9112 6.1: a message is framed with the chunked coding when "chunked"
   // is the final transfer coding. A single field value may list several
-  // codings ("gzip, chunked"), and the list may be split across multiple
-  // Transfer-Encoding header lines (RFC 9110 5.3). Match the last coding token
-  // case-insensitively rather than comparing the whole value against "chunked".
+  // codings ("gzip, chunked"), and RFC 9110 5.3 lets that list be split across
+  // several Transfer-Encoding lines, which combine into one comma-separated
+  // list in the order the lines were received. Headers preserves that order,
+  // so the final coding is the last token of the last line. Match it
+  // case-insensitively rather than comparing the whole value against
+  // "chunked".
   //
   // Security: reading a chunked message as unframed leaves its body in the
   // socket, where a keep-alive connection parses it as a smuggled request.
-  // Headers is an unordered_multimap whose iteration order for duplicate keys
-  // is not portable, so when there is more than one Transfer-Encoding line we
-  // cannot tell which coding is truly final. In that ambiguous case we fail
-  // safe by treating the message as chunked (a mis-parse just closes the
-  // connection, whereas the opposite error enables smuggling).
+  // Server::process_request() answers 400 and closes when the final coding is
+  // not chunked, so a request whose framing cannot be determined never
+  // reaches the "no body" path.
   auto rng = headers.equal_range("Transfer-Encoding");
+  if (rng.first == rng.second) { return false; }
 
-  size_t line_count = 0;
-  bool chunked_present = false;
-  bool last_line_ends_with_chunked = false;
+  // Cleared per line, so a trailing line carrying no coding at all leaves the
+  // combined list ending in nothing rather than inheriting the line before it.
+  std::string last_coding;
 
   for (auto it = rng.first; it != rng.second; ++it) {
-    line_count++;
     const auto &value = it->second;
-
-    std::string last_coding;
-    bool line_has_chunked = false;
+    last_coding.clear();
     split(value.data(), value.data() + value.size(), ',',
-          [&](const char *b, const char *e) {
-            last_coding.assign(b, e);
-            if (case_ignore::equal(last_coding, "chunked")) {
-              line_has_chunked = true;
-            }
-          });
-
-    if (line_has_chunked) { chunked_present = true; }
-    last_line_ends_with_chunked = case_ignore::equal(last_coding, "chunked");
+          [&](const char *b, const char *e) { last_coding.assign(b, e); });
   }
 
-  if (line_count == 0) { return false; }
-  if (line_count == 1) { return last_line_ends_with_chunked; }
-  return chunked_present;
+  return case_ignore::equal(last_coding, "chunked");
 }
 
 template <typename T, typename U>
@@ -3420,9 +3509,12 @@ bool prepare_content_receiver(T &x, int &status,
     std::unique_ptr<decompressor> decompressor;
 
     if (!encoding.empty()) {
+      // A coding we know about but were not built with is an error. An
+      // unrecognized coding (including "identity") is left alone and the
+      // payload is passed through as-is, since some servers misuse the header,
+      // e.g. by sending a character set such as "Content-Encoding: UTF-8".
       decompressor = detail::create_decompressor(encoding);
-      if (!decompressor) {
-        // Unsupported encoding or no support compiled in
+      if (!decompressor && detail::is_known_content_encoding(encoding)) {
         status = StatusCode::UnsupportedMediaType_415;
         return false;
       }
@@ -3845,6 +3937,19 @@ std::string params_to_query_str(const Params &params) {
   return query;
 }
 
+// Splits one "key=value" span of a query string at its first '='. A span with
+// no '=' at all lands entirely in key, leaving val empty, which is how a bare
+// "?flag" keeps its name.
+void divide_query_pair(const char *b, const char *e, std::string &key,
+                              std::string &val) {
+  divide(b, static_cast<std::size_t>(e - b), '=',
+         [&](const char *lhs_data, std::size_t lhs_size, const char *rhs_data,
+             std::size_t rhs_size) {
+           key.assign(lhs_data, lhs_size);
+           val.assign(rhs_data, rhs_size);
+         });
+}
+
 void parse_query_text(const char *data, std::size_t size,
                              Params &params) {
   std::set<std::string> cache;
@@ -3855,12 +3960,7 @@ void parse_query_text(const char *data, std::size_t size,
 
     std::string key;
     std::string val;
-    divide(b, static_cast<std::size_t>(e - b), '=',
-           [&](const char *lhs_data, std::size_t lhs_size, const char *rhs_data,
-               std::size_t rhs_size) {
-             key.assign(lhs_data, lhs_size);
-             val.assign(rhs_data, rhs_size);
-           });
+    divide_query_pair(b, e, key, val);
 
     if (!key.empty()) {
       params.emplace(decode_query_component(key), decode_query_component(val));
@@ -3874,20 +3974,18 @@ void parse_query_text(const std::string &s, Params &params) {
 
 // Normalize a query string by decoding and re-encoding each key/value pair
 // while preserving the original parameter order. This avoids double-encoding
-// and ensures consistent encoding without reordering (unlike Params which
-// uses std::multimap and sorts keys).
+// and ensures consistent encoding. It works on the raw string rather than
+// parsing into Params and re-serializing, because that round trip cannot
+// reproduce the input: params_to_query_str() always emits '=', so a bare
+// "flag" would come back as "flag=", and parse_query_text() drops exactly
+// duplicated pairs.
 std::string normalize_query_string(const std::string &query) {
   std::string result;
   split(query.data(), query.data() + query.size(), '&',
         [&](const char *b, const char *e) {
           std::string key;
           std::string val;
-          divide(b, static_cast<std::size_t>(e - b), '=',
-                 [&](const char *lhs_data, std::size_t lhs_size,
-                     const char *rhs_data, std::size_t rhs_size) {
-                   key.assign(lhs_data, lhs_size);
-                   val.assign(rhs_data, rhs_size);
-                 });
+          divide_query_pair(b, e, key, val);
 
           if (!key.empty()) {
             auto dec_key = decode_query_component(key);
@@ -3904,6 +4002,43 @@ std::string normalize_query_string(const std::string &query) {
   return result;
 }
 
+// Build the request target that goes on the wire from a caller-supplied path.
+// Shared by the buffered send path and the streaming API so that both put the
+// same bytes in the request line for the same input.
+std::string encode_request_target(const std::string &target,
+                                         bool path_encode) {
+  // `substr(0, npos)` yields the whole string, which is what the no-query
+  // case needs.
+  auto query_pos = target.find('?');
+  auto path_part = target.substr(0, query_pos);
+  std::string query_part;
+  if (query_pos != std::string::npos) {
+    query_part = target.substr(query_pos + 1);
+  }
+
+  auto result = path_encode ? encode_path(path_part) : std::move(path_part);
+
+  if (!query_part.empty()) {
+    // When path encoding is disabled the caller has supplied an already-encoded
+    // target and expects the exact bytes to be sent on the wire, so skip
+    // normalization for the query too. Normalizing would decode-then-re-encode
+    // it and corrupt pre-encoded binary payloads (e.g. turning `%20` into `+`,
+    // which a strict RFC 3986 server decodes back as `+`, not a space).
+    if (path_encode) {
+      auto normalized = normalize_query_string(query_part);
+      if (!normalized.empty()) {
+        result += '?';
+        result += normalized;
+      }
+    } else {
+      result += '?';
+      result += query_part;
+    }
+  }
+
+  return result;
+}
+
 bool parse_multipart_boundary(const std::string &content_type,
                                      std::string &boundary) {
   std::map<std::string, std::string> params;
@@ -4969,21 +5104,8 @@ bool is_field_valid(const std::string &name, const std::string &value) {
 
 } // namespace fields
 
-bool perform_websocket_handshake(Stream &strm, const std::string &host,
-                                        int port, bool is_ssl,
-                                        const std::string &path,
-                                        const Headers &headers,
+bool perform_websocket_handshake(Stream &strm, Request &req,
                                         std::string &selected_subprotocol) {
-  // Validate path and host
-  if (!fields::is_field_value(path) || !fields::is_field_value(host)) {
-    return false;
-  }
-
-  // Validate user-provided headers
-  for (const auto &h : headers) {
-    if (!fields::is_field_valid(h.first, h.second)) { return false; }
-  }
-
   // Generate random Sec-WebSocket-Key
   thread_local std::mt19937 rng(std::random_device{}());
   std::string key_bytes(16, '\0');
@@ -4993,19 +5115,30 @@ bool perform_websocket_handshake(Stream &strm, const std::string &host,
   }
   auto client_key = base64_encode(key_bytes);
 
-  // Build upgrade request
-  std::string req_str = "GET " + path + " HTTP/1.1\r\n";
-  req_str += "Host: " + make_host_and_port_string(host, port, is_ssl) + "\r\n";
-  req_str += "Upgrade: websocket\r\n";
-  req_str += "Connection: Upgrade\r\n";
-  req_str += "Sec-WebSocket-Key: " + client_key + "\r\n";
-  req_str += "Sec-WebSocket-Version: 13\r\n";
-  for (const auto &h : headers) {
-    req_str += h.first + ": " + h.second + "\r\n";
-  }
-  req_str += "\r\n";
+  req.headers.erase("Upgrade");
+  req.headers.erase("Connection");
+  req.headers.erase("Sec-WebSocket-Key");
+  req.headers.erase("Sec-WebSocket-Version");
+  req.headers.emplace("Upgrade", "websocket");
+  req.headers.emplace("Connection", "Upgrade");
+  req.headers.emplace("Sec-WebSocket-Key", client_key);
+  req.headers.emplace("Sec-WebSocket-Version", "13");
 
-  if (strm.write(req_str.data(), req_str.size()) < 0) { return false; }
+  // Build the request in memory first, like ClientImpl::write_request does.
+  // Writing straight to the socket would leak a request line onto the wire
+  // before check_and_write_headers gets a chance to reject an invalid header,
+  // and would emit one small write per header.
+  BufferStream bstrm;
+
+  if (write_request_line(bstrm, req.method, req.path) < 0) { return false; }
+
+  auto error = Error::Success;
+  if (!check_and_write_headers(bstrm, req.headers, write_headers, error)) {
+    return false;
+  }
+
+  const auto &data = bstrm.get_buffer();
+  if (!write_data(strm, data.data(), data.size())) { return false; }
 
   // Verify 101 response and Sec-WebSocket-Accept header
   auto expected_accept = websocket_accept_key(client_key);
@@ -5013,6 +5146,39 @@ bool perform_websocket_handshake(Stream &strm, const std::string &host,
                                          selected_subprotocol);
 }
 
+bool is_ip_address(const std::string &host) {
+  struct in_addr addr4;
+  struct in6_addr addr6;
+  return inet_pton(AF_INET, host.c_str(), &addr4) == 1 ||
+         inet_pton(AF_INET6, host.c_str(), &addr6) == 1;
+}
+
+// Resolve where a client should connect for `host`, honoring a user-supplied
+// hostname-to-address map. `host` itself is never rewritten, so it keeps
+// supplying the Host header and SNI; only the connection target changes.
+//
+// A mapped IP literal goes to `ip`, which keeps create_socket's AI_NUMERICHOST
+// path. Anything else goes to `connect_host`, which create_socket resolves as
+// a name, or uses as the socket path when the address family is AF_UNIX. An
+// absent or empty mapping leaves `host` as the connection target; without the
+// empty check the value would reach getaddrinfo as a null node and silently
+// resolve to loopback.
+void apply_addr_map(const std::map<std::string, std::string> &addr_map,
+                           const std::string &host, std::string &connect_host,
+                           std::string &ip) {
+  connect_host = host;
+  ip.clear();
+
+  auto it = addr_map.find(host);
+  if (it == addr_map.end() || it->second.empty()) { return; }
+
+  if (is_ip_address(it->second)) {
+    ip = it->second;
+  } else {
+    connect_host = it->second;
+  }
+}
+
 } // namespace detail
 
 /*
@@ -5044,7 +5210,12 @@ public:
   time_t duration() const override;
   void set_read_timeout(time_t sec, time_t usec = 0) override;
 
+  // See SocketStream::set_readable_hint().
+  void set_readable_hint() { readable_hint_ = true; }
+
 private:
+  bool ensure_readable();
+
   socket_t sock_;
   tls::session_t session_;
   time_t read_timeout_sec_;
@@ -5053,6 +5224,7 @@ private:
   time_t write_timeout_usec_;
   time_t max_timeout_msec_;
   const std::chrono::time_point<std::chrono::steady_clock> start_time_;
+  bool readable_hint_ = false;
 };
 
 #ifdef CPPHTTPLIB_OPENSSL_SUPPORT
@@ -5196,13 +5368,6 @@ std::string SHA_512(const std::string &s) {
 }
 #endif
 
-bool is_ip_address(const std::string &host) {
-  struct in_addr addr4;
-  struct in6_addr addr6;
-  return inet_pton(AF_INET, host.c_str(), &addr4) == 1 ||
-         inet_pton(AF_INET6, host.c_str(), &addr6) == 1;
-}
-
 template <typename T>
 bool process_server_socket_ssl(
     const std::atomic<socket_t> &svr_sock, tls::session_t session,
@@ -5214,6 +5379,8 @@ bool process_server_socket_ssl(
       [&](bool close_connection, bool &connection_closed) {
         SSLSocketStream strm(sock, session, read_timeout_sec, read_timeout_usec,
                              write_timeout_sec, write_timeout_usec);
+        // See the non-TLS path in process_server_socket().
+        strm.set_readable_hint();
         return callback(strm, close_connection, connection_closed);
       });
 }
@@ -5665,6 +5832,7 @@ std::string to_string(const Error error) {
   case Error::UnsupportedAddressFamily: return "Unsupported address family";
   case Error::HTTPParsing: return "HTTP parsing failed";
   case Error::InvalidRangeHeader: return "Invalid Range header";
+  case Error::UnsupportedContentEncoding: return "Unsupported Content-Encoding";
   default: break;
   }
 
@@ -6046,8 +6214,7 @@ std::string Request::get_trailer_value(const std::string &key,
 }
 
 size_t Request::get_trailer_value_count(const std::string &key) const {
-  auto r = trailers.equal_range(key);
-  return static_cast<size_t>(std::distance(r.first, r.second));
+  return trailers.count(key);
 }
 
 bool Request::has_param(const std::string &key) const {
@@ -6071,8 +6238,7 @@ Request::get_param_values(const std::string &key) const {
 }
 
 size_t Request::get_param_value_count(const std::string &key) const {
-  auto r = params.equal_range(key);
-  return static_cast<size_t>(std::distance(r.first, r.second));
+  return params.count(key);
 }
 
 bool Request::is_multipart_form_data() const {
@@ -6105,8 +6271,7 @@ bool MultipartFormData::has_field(const std::string &key) const {
 }
 
 size_t MultipartFormData::get_field_count(const std::string &key) const {
-  auto r = fields.equal_range(key);
-  return static_cast<size_t>(std::distance(r.first, r.second));
+  return fields.count(key);
 }
 
 FormData MultipartFormData::get_file(const std::string &key,
@@ -6129,8 +6294,7 @@ bool MultipartFormData::has_file(const std::string &key) const {
 }
 
 size_t MultipartFormData::get_file_count(const std::string &key) const {
-  auto r = files.equal_range(key);
-  return static_cast<size_t>(std::distance(r.first, r.second));
+  return files.count(key);
 }
 
 // Multipart FormData writer implementation
@@ -6209,8 +6373,7 @@ std::string Response::get_trailer_value(const std::string &key,
 }
 
 size_t Response::get_trailer_value_count(const std::string &key) const {
-  auto r = trailers.equal_range(key);
-  return static_cast<size_t>(std::distance(r.first, r.second));
+  return trailers.count(key);
 }
 
 void Response::set_redirect(const std::string &url, int stat) {
@@ -6306,8 +6469,7 @@ std::string Result::get_request_header_value(const std::string &key,
 
 size_t
 Result::get_request_header_value_count(const std::string &key) const {
-  auto r = request_headers_.equal_range(key);
-  return static_cast<size_t>(std::distance(r.first, r.second));
+  return request_headers_.count(key);
 }
 
 // Stream implementation
@@ -6595,6 +6757,24 @@ bool SocketStream::wait_writable() const {
   return select_write(sock_, write_timeout_sec_, write_timeout_usec_) > 0;
 }
 
+bool SocketStream::ensure_readable() {
+  if (readable_hint_) {
+    readable_hint_ = false;
+    return true;
+  }
+  return wait_readable();
+}
+
+const char *SocketStream::buffered_data(size_t &size) const {
+  size = read_buff_content_size_ - read_buff_off_;
+  return size ? read_buff_.data() + read_buff_off_ : nullptr;
+}
+
+void SocketStream::consume_buffered(size_t size) {
+  assert(size <= read_buff_content_size_ - read_buff_off_);
+  read_buff_off_ += size;
+}
+
 bool SocketStream::is_peer_alive() const {
   return detail::is_socket_alive(sock_);
 }
@@ -6621,7 +6801,7 @@ ssize_t SocketStream::read(char *ptr, size_t size) {
     }
   }
 
-  if (!wait_readable()) {
+  if (!ensure_readable()) {
     error_ = Error::Timeout;
     return -1;
   }
@@ -7099,6 +7279,14 @@ bool SSLSocketStream::wait_writable() const {
          !tls::is_peer_closed(session_, sock_);
 }
 
+bool SSLSocketStream::ensure_readable() {
+  if (readable_hint_) {
+    readable_hint_ = false;
+    return true;
+  }
+  return wait_readable();
+}
+
 bool SSLSocketStream::is_peer_alive() const {
   return !tls::is_peer_closed(session_, sock_);
 }
@@ -7111,7 +7299,7 @@ ssize_t SSLSocketStream::read(char *ptr, size_t size) {
       error_ = Error::ConnectionClosed;
     }
     return ret;
-  } else if (wait_readable()) {
+  } else if (ensure_readable()) {
     tls::TlsError err;
     auto ret = tls::read(session_, ptr, size, err);
     if (ret < 0) {
@@ -7533,9 +7721,11 @@ void Server::wait_until_ready() const {
 }
 
 void Server::stop() noexcept {
-  if (is_running_) {
-    assert(svr_sock_ != INVALID_SOCKET);
-    std::atomic<socket_t> sock(svr_sock_.exchange(INVALID_SOCKET));
+  // Release the listening socket whether or not the accept loop is running:
+  // bind_to_port() without listen_after_bind() still owns the descriptor. The
+  // exchange is what makes this safe to call concurrently with the accept loop.
+  socket_t sock = svr_sock_.exchange(INVALID_SOCKET);
+  if (sock != INVALID_SOCKET) {
     detail::shutdown_socket(sock);
     detail::close_socket(sock);
   }
@@ -7697,7 +7887,15 @@ Server::write_content_with_provider(Stream &strm, const Request &req,
   };
 
   if (res.content_length_ > 0) {
-    if (req.ranges.empty()) {
+    // Only a 206 response is served as a partial representation, matching the
+    // condition `apply_ranges()` used to decide the Content-Length and the
+    // multipart boundary. Since `detail::range_error()` validates `req.ranges`
+    // only for a 2xx status, slicing under any other status would write a body
+    // that disagrees with the header already sent, from an unchecked offset.
+    auto is_partial =
+        !req.ranges.empty() && res.status == StatusCode::PartialContent_206;
+
+    if (!is_partial) {
       return detail::write_content(strm, res.content_provider_, 0,
                                    res.content_length_, is_shutting_down);
     } else if (req.ranges.size() == 1) {
@@ -8096,7 +8294,14 @@ int Server::bind_internal(const std::string &host, int port,
 }
 
 bool Server::listen_internal() {
-  if (is_decommissioned) { return false; }
+  // A stop() between bind and listen leaves nothing to accept on. Report
+  // failure instead of returning success without ever serving, and mark the
+  // server decommissioned the way any failed listen does so that a concurrent
+  // wait_until_ready() wakes up instead of spinning forever.
+  if (is_decommissioned || svr_sock_ == INVALID_SOCKET) {
+    is_decommissioned = true;
+    return false;
+  }
 
   auto ret = true;
   is_running_ = true;
@@ -8492,11 +8697,17 @@ Server::process_request(Stream &strm, const std::string &remote_addr,
     return write_response(strm, close_connection, req, res);
   }
 
-  // RFC 9112 §6.3: Reject requests with both a non-zero Content-Length and
-  // any Transfer-Encoding to prevent request smuggling. Content-Length: 0 is
-  // tolerated for compatibility with existing clients.
-  if (req.get_header_value_u64("Content-Length") > 0 &&
-      req.has_header("Transfer-Encoding")) {
+  // RFC 9112 §6.3: Reject requests whose framing is ambiguous, which would
+  // otherwise let an intermediary and this parser disagree on where the body
+  // ends and enable request smuggling. Two cases: a non-zero Content-Length
+  // alongside any Transfer-Encoding (Content-Length: 0 is tolerated for
+  // compatibility with existing clients), and a Transfer-Encoding whose final
+  // coding is not chunked, which leaves the body length undeterminable. The
+  // latter must not fall through to the "no body" path, or the body bytes are
+  // parsed as the next request on a persistent connection.
+  if (req.has_header("Transfer-Encoding") &&
+      (req.get_header_value_u64("Content-Length") > 0 ||
+       !detail::is_chunked_transfer_encoding(req.headers))) {
     connection_closed = true;
     res.status = StatusCode::BadRequest_400;
     return write_response(strm, close_connection, req, res);
@@ -8908,13 +9119,13 @@ socket_t ClientImpl::create_client_socket(Error &error) const {
         write_timeout_sec_, write_timeout_usec_, interface_, error);
   }
 
-  // Check is custom IP specified for host_
+  // Check is custom IP or hostname specified for host_
+  std::string connect_host;
   std::string ip;
-  auto it = addr_map_.find(host_);
-  if (it != addr_map_.end()) { ip = it->second; }
+  detail::apply_addr_map(addr_map_, host_, connect_host, ip);
 
   return detail::create_client_socket(
-      host_, ip, port_, address_family_, tcp_nodelay_, ipv6_v6only_,
+      connect_host, ip, port_, address_family_, tcp_nodelay_, ipv6_v6only_,
       socket_options_, connection_timeout_sec_, connection_timeout_usec_,
       read_timeout_sec_, read_timeout_usec_, write_timeout_sec_,
       write_timeout_usec_, interface_, error);
@@ -9142,11 +9353,13 @@ void ClientImpl::prepare_default_headers(Request &r, bool for_stream,
     if (!r.has_header(header.first)) { r.headers.insert(header); }
   }
 
+  // RFC 9110 5.3 recommends sending control data such as Host first, so
+  // prepend it rather than appending it after the caller's own fields.
   if (!r.has_header("Host")) {
     if (address_family_ == AF_UNIX) {
-      r.headers.emplace("Host", "localhost");
+      r.headers.emplace_front("Host", "localhost");
     } else {
-      r.headers.emplace(
+      r.headers.emplace_front(
           "Host", detail::make_host_and_port_string(host_, port_, is_ssl()));
     }
   }
@@ -9197,7 +9410,12 @@ ClientImpl::open_stream(const std::string &method, const std::string &path,
   handle.response = detail::make_unique<Response>();
   handle.error = Error::Success;
 
-  auto query_path = params.empty() ? path : append_query_params(path, params);
+  // Encode the target exactly like the buffered send path does, so that the
+  // same `path` produces the same request line through either API.
+  auto raw_query_path =
+      params.empty() ? path : append_query_params(path, params);
+  auto query_path = detail::encode_request_target(raw_query_path, path_encode_);
+
   handle.connection_ = detail::make_unique<ClientConnection>();
 
   {
@@ -9311,7 +9529,20 @@ ClientImpl::open_stream(const std::string &method, const std::string &path,
 
   auto content_encoding = handle.response->get_header_value("Content-Encoding");
   if (!content_encoding.empty()) {
+    // Same policy as prepare_content_receiver(): reject a coding we know about
+    // but were not built with, pass an unrecognized one through as-is.
     handle.decompressor_ = detail::create_decompressor(content_encoding);
+    if (!handle.decompressor_) {
+      if (detail::is_known_content_encoding(content_encoding)) {
+        handle.error = Error::UnsupportedContentEncoding;
+        handle.response.reset();
+        return handle;
+      }
+    } else if (!handle.decompressor_->is_valid()) {
+      handle.error = Error::Compression;
+      handle.response.reset();
+      return handle;
+    }
   }
 
   return handle;
@@ -9842,52 +10073,26 @@ bool ClientImpl::write_request(Stream &strm, Request &req,
   {
     detail::BufferStream bstrm;
 
-    // Extract path and query from req.path
-    std::string path_part, query_part;
+    // Extract the query from req.path. The encoding itself is delegated to
+    // `encode_request_target`; the raw query is still needed here to decide
+    // between populating `req.params` from it and falling back to building a
+    // query out of caller-supplied `req.params`.
     auto query_pos = req.path.find('?');
-    if (query_pos != std::string::npos) {
-      path_part = req.path.substr(0, query_pos);
-      query_part = req.path.substr(query_pos + 1);
-    } else {
-      path_part = req.path;
-      query_part = "";
-    }
+    auto query_part = query_pos == std::string::npos
+                          ? std::string()
+                          : req.path.substr(query_pos + 1);
 
-    // Encode path part. If the original `req.path` already contained a
-    // query component, preserve its raw query string (including parameter
-    // order) instead of reparsing and reassembling it which may reorder
-    // parameters due to container ordering (e.g. `Params` uses
-    // `std::multimap`). When there is no query in `req.path`, fall back to
-    // building a query from `req.params` so existing callers that pass
-    // `Params` continue to work.
     auto path_with_query =
-        path_encode_ ? detail::encode_path(path_part) : path_part;
+        detail::encode_request_target(req.path, path_encode_);
 
     if (!query_part.empty()) {
-      // Normalize the query string (decode then re-encode) while preserving
-      // the original parameter order. When path encoding is disabled the
-      // caller has supplied an already-encoded target and expects the exact
-      // bytes to be sent on the wire, so skip normalization for the query
-      // too. Normalizing here would decode-then-re-encode the query and
-      // corrupt pre-encoded binary payloads (e.g. turning `%20` into `+`,
-      // which a strict RFC 3986 server decodes back as `+`, not a space).
-      if (path_encode_) {
-        auto normalized = detail::normalize_query_string(query_part);
-        if (!normalized.empty()) { path_with_query += '?' + normalized; }
-      } else {
-        path_with_query += '?' + query_part;
-      }
-
-      // Still populate req.params for handlers/users who read them.
+      // The query already came in through `req.path`; still populate
+      // `req.params` for handlers/users who read them.
       detail::parse_query_text(query_part, req.params);
-    } else {
-      // No query in path; parse any query_part (empty) and append params
-      // from `req.params` when present (preserves prior behavior for
-      // callers who provide Params separately).
-      detail::parse_query_text(query_part, req.params);
-      if (!req.params.empty()) {
-        path_with_query = append_query_params(path_with_query, req.params);
-      }
+    } else if (!req.params.empty()) {
+      // No query in `req.path`; build one from `req.params` so existing
+      // callers that pass `Params` separately continue to work.
+      path_with_query = append_query_params(path_with_query, req.params);
     }
 
     // Write request line and headers
@@ -10298,14 +10503,26 @@ bool ClientImpl::process_request(Stream &strm, Request &req,
     }
 
     if (res.status != StatusCode::NotModified_304) {
-      int dummy_status;
+      auto content_status = 0;
       auto max_length = (!has_payload_max_length_ && req.content_receiver)
                             ? (std::numeric_limits<size_t>::max)()
                             : payload_max_length_;
-      if (!detail::read_content(strm, res, max_length, dummy_status,
+      if (!detail::read_content(strm, res, max_length, content_status,
                                 std::move(progress), std::move(out),
                                 decompress_)) {
-        if (error != Error::Canceled) { error = Error::Read; }
+        if (error != Error::Canceled) {
+          // Tell the caller apart from a plain read failure when the body could
+          // not be decoded because of its Content-Encoding.
+          switch (content_status) {
+          case StatusCode::UnsupportedMediaType_415:
+            error = Error::UnsupportedContentEncoding;
+            break;
+          case StatusCode::InternalServerError_500:
+            error = Error::Compression;
+            break;
+          default: error = Error::Read; break;
+          }
+        }
         output_error_log(error, &req);
         return false;
       }
@@ -16769,18 +16986,42 @@ bool WebSocketClient::create_stream(std::unique_ptr<Stream> &strm) {
   return true;
 }
 
+void WebSocketClient::prepare_default_headers(Request &req) {
+#ifdef CPPHTTPLIB_SSL_ENABLED
+  auto is_ssl = is_ssl_;
+#else
+  auto is_ssl = false;
+#endif
+
+  if (!req.has_header("Host")) {
+    if (address_family_ == AF_UNIX) {
+      req.headers.emplace("Host", "localhost");
+    } else {
+      req.headers.emplace(
+          "Host", detail::make_host_and_port_string(host_, port_, is_ssl));
+    }
+  }
+
+#ifndef CPPHTTPLIB_NO_DEFAULT_USER_AGENT
+  if (!req.has_header("User-Agent")) {
+    auto agent = std::string("cpp-httplib/") + CPPHTTPLIB_VERSION;
+    req.set_header("User-Agent", agent);
+  }
+#endif
+}
+
 bool WebSocketClient::connect() {
   if (!is_valid_) { return false; }
   shutdown_and_close();
 
-  // Check is custom IP specified for host_
+  // Check is custom IP or hostname specified for host_
+  std::string connect_host;
   std::string ip;
-  auto it = addr_map_.find(host_);
-  if (it != addr_map_.end()) { ip = it->second; }
+  detail::apply_addr_map(addr_map_, host_, connect_host, ip);
 
   Error error;
   sock_ = detail::create_client_socket(
-      host_, ip, port_, address_family_, tcp_nodelay_, ipv6_v6only_,
+      connect_host, ip, port_, address_family_, tcp_nodelay_, ipv6_v6only_,
       socket_options_, connection_timeout_sec_, connection_timeout_usec_,
       read_timeout_sec_, read_timeout_usec_, write_timeout_sec_,
       write_timeout_usec_, interface_, error);
@@ -16793,23 +17034,19 @@ bool WebSocketClient::connect() {
     return false;
   }
 
-#ifdef CPPHTTPLIB_SSL_ENABLED
-  auto is_ssl = is_ssl_;
-#else
-  auto is_ssl = false;
-#endif
+  Request req;
+  req.method = "GET";
+  req.path = path_;
+  req.headers = headers_;
+  prepare_default_headers(req);
 
   std::string selected_subprotocol;
-  if (!detail::perform_websocket_handshake(*strm, host_, port_, is_ssl, path_,
-                                           headers_, selected_subprotocol)) {
+  if (!detail::perform_websocket_handshake(*strm, req, selected_subprotocol)) {
     shutdown_and_close();
     return false;
   }
   subprotocol_ = std::move(selected_subprotocol);
 
-  Request req;
-  req.method = "GET";
-  req.path = path_;
   ws_ = std::unique_ptr<WebSocket>(new WebSocket(std::move(strm), req, false,
                                                  websocket_ping_interval_sec_,
                                                  websocket_max_missed_pongs_));

vendor/cpp-httplib/httplib.h

@@ -8,8 +8,8 @@
 #ifndef CPPHTTPLIB_HTTPLIB_H
 #define CPPHTTPLIB_HTTPLIB_H
 
-#define CPPHTTPLIB_VERSION "0.51.0"
-#define CPPHTTPLIB_VERSION_NUM "0x003300"
+#define CPPHTTPLIB_VERSION "0.52.0"
+#define CPPHTTPLIB_VERSION_NUM "0x003400"
 
 #ifdef _WIN32
 #if defined(_WIN32_WINNT) && _WIN32_WINNT < 0x0A00
@@ -182,7 +182,7 @@
 #endif
 
 #ifndef CPPHTTPLIB_LISTEN_BACKLOG
-#define CPPHTTPLIB_LISTEN_BACKLOG 5
+#define CPPHTTPLIB_LISTEN_BACKLOG 128
 #endif
 
 #ifndef CPPHTTPLIB_MAX_LINE_LENGTH
@@ -321,6 +321,7 @@ using socket_t = int;
 #include <functional>
 #include <iomanip>
 #include <iostream>
+#include <iterator>
 #include <list>
 #include <map>
 #include <memory>
@@ -333,9 +334,11 @@ using socket_t = int;
 #include <sys/stat.h>
 #include <system_error>
 #include <thread>
+#include <type_traits>
 #include <unordered_map>
 #include <unordered_set>
 #include <utility>
+#include <vector>
 
 // On macOS with a TLS backend, enable Keychain root certificates by default
 // unless the user explicitly opts out. Not enabled on iOS/tvOS/watchOS since
@@ -968,11 +971,291 @@ enum StatusCode {
   NetworkAuthenticationRequired_511 = 511,
 };
 
-using Headers =
-    std::unordered_multimap<std::string, std::string, detail::case_ignore::hash,
-                            detail::case_ignore::equal_to>;
+namespace detail {
 
-using Params = std::multimap<std::string, std::string>;
+// A multimap that keeps its entries in the order they were inserted.
+//
+// HTTP needs that order in two places. RFC 9110 5.3 makes the order of header
+// fields sharing a field name significant and forbids a proxy from reordering
+// them, and a query string's parameters are meaningful in the order the caller
+// wrote them. Neither standard container expresses it: std::unordered_multimap
+// gives no ordering guarantee at all for equivalent keys (libstdc++ yields
+// reverse insertion order, libc++ insertion order), and std::multimap sorts by
+// key, which would drop control data such as Host behind whatever else the
+// message carries and alphabetise a query string.
+//
+// Entries are therefore kept in a flat vector, in order. Lookup is a linear
+// scan, which beats hashing for the handful of entries a message carries
+// (headers are capped at CPPHTTPLIB_HEADER_MAX_COUNT).
+//
+// KeyEqual compares keys; it is what makes Headers case-insensitive and
+// Params, whose parameter names are case-sensitive, not.
+template <typename Mapped, typename KeyEqual> class insertion_ordered_multimap {
+public:
+  using key_type = std::string;
+  using mapped_type = Mapped;
+  using value_type = std::pair<std::string, Mapped>;
+  using size_type = std::size_t;
+  using difference_type = std::ptrdiff_t;
+  using reference = value_type &;
+  using const_reference = const value_type &;
+
+private:
+  static size_type npos() { return static_cast<size_type>(-1); }
+
+  static bool keys_equal(const std::string &a, const std::string &b) {
+    return KeyEqual()(a, b);
+  }
+
+  // Iterating yields every entry in insertion order, but equal_range() and
+  // find() have to walk only the entries sharing one key, which are not
+  // adjacent. Both are the same iterator type: key_idx_ selects between the
+  // two traversals, and since equality compares only the position, an iterator
+  // restricted to one key still compares equal to end().
+  template <typename V> class iterator_t {
+  public:
+    using iterator_category = std::bidirectional_iterator_tag;
+    using value_type = insertion_ordered_multimap::value_type;
+    using difference_type = insertion_ordered_multimap::difference_type;
+    using pointer = V *;
+    using reference = V &;
+
+    iterator_t() : data_(nullptr), idx_(0), size_(0), key_idx_(npos()) {}
+
+    template <typename U,
+              typename std::enable_if<std::is_convertible<U *, V *>::value,
+                                      int>::type = 0>
+    iterator_t(const iterator_t<U> &rhs)
+        : data_(rhs.data_), idx_(rhs.idx_), size_(rhs.size_),
+          key_idx_(rhs.key_idx_) {}
+
+    reference operator*() const { return data_[idx_]; }
+    pointer operator->() const { return data_ + idx_; }
+
+    iterator_t &operator++() {
+      // Saturating, so that advancing past the last entry of a key (which
+      // get_multimap_value() does when asked for an out-of-range id) stays at
+      // end() instead of running off the container.
+      if (idx_ >= size_) { return *this; }
+      ++idx_;
+      if (key_idx_ != npos()) {
+        while (idx_ < size_ && !matches(idx_)) {
+          ++idx_;
+        }
+      }
+      return *this;
+    }
+
+    iterator_t operator++(int) {
+      auto tmp = *this;
+      ++*this;
+      return tmp;
+    }
+
+    iterator_t &operator--() {
+      if (idx_ == 0) { return *this; }
+      --idx_;
+      if (key_idx_ != npos()) {
+        while (idx_ > 0 && !matches(idx_)) {
+          --idx_;
+        }
+      }
+      return *this;
+    }
+
+    iterator_t operator--(int) {
+      auto tmp = *this;
+      --*this;
+      return tmp;
+    }
+
+    template <typename U> bool operator==(const iterator_t<U> &rhs) const {
+      return idx_ == rhs.idx_;
+    }
+
+    template <typename U> bool operator!=(const iterator_t<U> &rhs) const {
+      return idx_ != rhs.idx_;
+    }
+
+  private:
+    friend class insertion_ordered_multimap;
+    template <typename> friend class iterator_t;
+
+    iterator_t(V *data, size_type idx, size_type size, size_type key_idx)
+        : data_(data), idx_(idx), size_(size), key_idx_(key_idx) {}
+
+    bool matches(size_type i) const {
+      return keys_equal(data_[i].first, data_[key_idx_].first);
+    }
+
+    V *data_;
+    size_type idx_;
+    size_type size_;
+    size_type key_idx_;
+  };
+
+public:
+  using iterator = iterator_t<value_type>;
+  using const_iterator = iterator_t<const value_type>;
+
+  insertion_ordered_multimap() = default;
+  insertion_ordered_multimap(std::initializer_list<value_type> il)
+      : entries_(il) {}
+  template <typename InputIt>
+  insertion_ordered_multimap(InputIt first, InputIt last)
+      : entries_(first, last) {}
+
+  iterator begin() { return make_iter(0, npos()); }
+  iterator end() { return make_iter(entries_.size(), npos()); }
+  const_iterator begin() const { return make_citer(0, npos()); }
+  const_iterator end() const { return make_citer(entries_.size(), npos()); }
+  const_iterator cbegin() const { return begin(); }
+  const_iterator cend() const { return end(); }
+
+  bool empty() const { return entries_.empty(); }
+  size_type size() const { return entries_.size(); }
+  void clear() { entries_.clear(); }
+  void swap(insertion_ordered_multimap &rhs) { entries_.swap(rhs.entries_); }
+
+  iterator insert(const value_type &val) {
+    entries_.push_back(val);
+    return make_iter(entries_.size() - 1, npos());
+  }
+
+  iterator insert(value_type &&val) {
+    entries_.push_back(std::move(val));
+    return make_iter(entries_.size() - 1, npos());
+  }
+
+  template <typename... Args> iterator emplace(Args &&...args) {
+    entries_.emplace_back(std::forward<Args>(args)...);
+    return make_iter(entries_.size() - 1, npos());
+  }
+
+  // For entries that have to lead the message, such as the Host header field
+  // (RFC 9110 5.3 recommends sending control data first).
+  template <typename... Args> iterator emplace_front(Args &&...args) {
+    entries_.emplace(entries_.begin(), std::forward<Args>(args)...);
+    return make_iter(0, npos());
+  }
+
+  iterator find(const std::string &key) {
+    auto i = index_of(key);
+    return i == npos() ? end() : make_iter(i, i);
+  }
+
+  const_iterator find(const std::string &key) const {
+    auto i = index_of(key);
+    return i == npos() ? end() : make_citer(i, i);
+  }
+
+  size_type count(const std::string &key) const {
+    size_type n = 0;
+    for (const auto &entry : entries_) {
+      if (keys_equal(entry.first, key)) { n++; }
+    }
+    return n;
+  }
+
+  std::pair<iterator, iterator> equal_range(const std::string &key) {
+    auto i = index_of(key);
+    return i == npos() ? std::make_pair(end(), end())
+                       : std::make_pair(make_iter(i, i), end());
+  }
+
+  std::pair<const_iterator, const_iterator>
+  equal_range(const std::string &key) const {
+    auto i = index_of(key);
+    return i == npos() ? std::make_pair(end(), end())
+                       : std::make_pair(make_citer(i, i), end());
+  }
+
+  size_type erase(const std::string &key) {
+    auto before = entries_.size();
+    entries_.erase(std::remove_if(entries_.begin(), entries_.end(),
+                                  [&](const value_type &entry) {
+                                    return keys_equal(entry.first, key);
+                                  }),
+                   entries_.end());
+    return before - entries_.size();
+  }
+
+  iterator erase(const_iterator pos) {
+    entries_.erase(entries_.begin() + static_cast<difference_type>(pos.idx_));
+    return make_iter(pos.idx_, npos());
+  }
+
+  // Erases what iterating [first, last) would actually visit, so erasing an
+  // equal_range() removes only the entries with that key, not everything
+  // positioned between them.
+  iterator erase(const_iterator first, const_iterator last) {
+    auto from = first.idx_;
+    auto to = last.idx_;
+    if (from >= to) { return make_iter(from, npos()); }
+
+    auto begin_it = entries_.begin();
+    auto from_it = begin_it + static_cast<difference_type>(from);
+    auto to_it = begin_it + static_cast<difference_type>(to);
+
+    if (first.key_idx_ == npos()) {
+      entries_.erase(from_it, to_it);
+    } else {
+      auto key = entries_[first.key_idx_].first;
+      auto keep = from_it;
+      for (auto it = from_it; it != to_it; ++it) {
+        if (!keys_equal(it->first, key)) {
+          if (keep != it) { *keep = std::move(*it); }
+          ++keep;
+        }
+      }
+      if (keep != to_it) {
+        keep = std::move(to_it, entries_.end(), keep);
+      } else {
+        keep = entries_.end();
+      }
+      entries_.erase(keep, entries_.end());
+    }
+    return make_iter(from, npos());
+  }
+
+  friend bool operator==(const insertion_ordered_multimap &lhs,
+                         const insertion_ordered_multimap &rhs) {
+    return lhs.entries_ == rhs.entries_;
+  }
+
+  friend bool operator!=(const insertion_ordered_multimap &lhs,
+                         const insertion_ordered_multimap &rhs) {
+    return !(lhs == rhs);
+  }
+
+private:
+  size_type index_of(const std::string &key) const {
+    for (size_type i = 0; i < entries_.size(); i++) {
+      if (keys_equal(entries_[i].first, key)) { return i; }
+    }
+    return npos();
+  }
+
+  iterator make_iter(size_type idx, size_type key_idx) {
+    return iterator(entries_.data(), idx, entries_.size(), key_idx);
+  }
+
+  const_iterator make_citer(size_type idx, size_type key_idx) const {
+    return const_iterator(entries_.data(), idx, entries_.size(), key_idx);
+  }
+
+  std::vector<value_type> entries_;
+};
+
+} // namespace detail
+
+using Headers =
+    detail::insertion_ordered_multimap<std::string,
+                                       detail::case_ignore::equal_to>;
+
+// Query parameter names are case-sensitive, unlike header field names.
+using Params =
+    detail::insertion_ordered_multimap<std::string, std::equal_to<std::string>>;
 using Match = std::smatch;
 
 using DownloadProgress = std::function<bool(size_t current, size_t total)>;
@@ -1079,9 +1362,16 @@ struct FormField {
   std::string content;
   Headers headers;
 };
-using FormFields = std::multimap<std::string, FormField>;
+// RFC 7578 5.2: a form processor "SHOULD send back results in order" and
+// "Intermediaries MUST NOT reorder the results", so a handler walking these
+// should see the parts as they were sent. A std::multimap sorts by field name
+// and loses that. Field names are case-sensitive, hence std::equal_to rather
+// than the case-insensitive predicate Headers uses.
+using FormFields =
+    detail::insertion_ordered_multimap<FormField, std::equal_to<std::string>>;
 
-using FormFiles = std::multimap<std::string, FormData>;
+using FormFiles =
+    detail::insertion_ordered_multimap<FormData, std::equal_to<std::string>>;
 
 struct MultipartFormData {
   FormFields fields; // Text fields from multipart
@@ -1514,6 +1804,7 @@ enum class Error {
   UnsupportedAddressFamily,
   HTTPParsing,
   InvalidRangeHeader,
+  UnsupportedContentEncoding,
 
   // For internal use only
   SSLPeerCouldBeClosed_,
@@ -1545,6 +1836,18 @@ public:
     (void)usec;
   }
 
+  // Bytes already pulled off the socket and sitting in this stream's own
+  // buffer. Exposing them lets a line reader scan for a terminator in one
+  // pass instead of asking for a byte at a time. A stream that does no
+  // buffering of its own reports none, and readers fall back to read().
+  virtual const char *buffered_data(size_t &size) const {
+    size = 0;
+    return nullptr;
+  }
+
+  // Discards `size` bytes previously returned by buffered_data().
+  virtual void consume_buffered(size_t size) { (void)size; }
+
   ssize_t write(const char *ptr);
   ssize_t write(const std::string &s);
 
@@ -2452,7 +2755,8 @@ protected:
   std::thread::id socket_requests_are_from_thread_ = std::thread::id();
   bool socket_should_be_closed_when_request_is_done_ = false;
 
-  // Hostname-IP map
+  // Hostname to connection target map. The value is an IP literal or another
+  // hostname; only the connection target changes, never the identity.
   std::map<std::string, std::string> addr_map_;
 
   // Default headers
@@ -3154,6 +3458,10 @@ private:
 std::string make_host_and_port_string(const std::string &host, int port,
                                       bool is_ssl);
 
+template <typename T>
+bool check_and_write_headers(Stream &strm, Headers &headers, T header_writer,
+                             Error &error);
+
 std::string trim_copy(const std::string &s);
 
 void divide(
@@ -3364,6 +3672,7 @@ public:
 
 private:
   void append(char c);
+  void append(const char *data, size_t size);
 
   Stream &strm_;
   char *fixed_buffer_;
@@ -3992,6 +4301,7 @@ public:
 private:
   void shutdown_and_close();
   bool create_stream(std::unique_ptr<Stream> &strm);
+  void prepare_default_headers(Request &req);
 
   std::string host_;
   int port_;
@@ -4016,7 +4326,8 @@ private:
   time_t connection_timeout_usec_ = CPPHTTPLIB_CONNECTION_TIMEOUT_USECOND;
   std::string interface_;
 
-  // Hostname-IP map
+  // Hostname to connection target map. The value is an IP literal or another
+  // hostname; only the connection target changes, never the identity.
   std::map<std::string, std::string> addr_map_;
 
 #ifdef CPPHTTPLIB_SSL_ENABLED