ggml webgpu: actually add softmax, fix rms_norm offset (#16400)

* implement soft_max

* Fix soft_max data race

* Temporary fix, wait on each submit

common/arg.cpp

@@ -1615,18 +1615,14 @@ static void add_rpc_devices(const std::string & servers) {
     if (!rpc_reg) {
         throw std::invalid_argument("failed to find RPC backend");
     }
-    typedef ggml_backend_dev_t (*ggml_backend_rpc_add_device_t)(const char * endpoint);
-    ggml_backend_rpc_add_device_t ggml_backend_rpc_add_device_fn = (ggml_backend_rpc_add_device_t) ggml_backend_reg_get_proc_address(rpc_reg, "ggml_backend_rpc_add_device");
-    if (!ggml_backend_rpc_add_device_fn) {
-        throw std::invalid_argument("failed to find RPC device add function");
+    typedef ggml_backend_reg_t (*ggml_backend_rpc_add_server_t)(const char * endpoint);
+    ggml_backend_rpc_add_server_t ggml_backend_rpc_add_server_fn = (ggml_backend_rpc_add_server_t) ggml_backend_reg_get_proc_address(rpc_reg, "ggml_backend_rpc_add_server");
+    if (!ggml_backend_rpc_add_server_fn) {
+        throw std::invalid_argument("failed to find RPC add server function");
     }
     for (const auto & server : rpc_servers) {
-        ggml_backend_dev_t dev = ggml_backend_rpc_add_device_fn(server.c_str());
-        if (dev) {
-            ggml_backend_device_register(dev);
-        } else {
-            throw std::invalid_argument("failed to register RPC device");
-        }
+        auto reg = ggml_backend_rpc_add_server_fn(server.c_str());
+        ggml_backend_register(reg);
     }
 }
 
@@ -1932,13 +1928,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         }
     ).set_env("LLAMA_ARG_SWA_FULL"));
     add_opt(common_arg(
-        {"--swa-checkpoints"}, "N",
-        string_format("max number of SWA checkpoints per slot to create (default: %d)\n"
-            "[(more info)](https://github.com/ggml-org/llama.cpp/pull/15293)", params.n_swa_checkpoints),
+        {"--ctx-checkpoints", "--swa-checkpoints"}, "N",
+        string_format("max number of context checkpoints to create per slot (default: %d)\n"
+            "[(more info)](https://github.com/ggml-org/llama.cpp/pull/15293)", params.n_ctx_checkpoints),
         [](common_params & params, int value) {
-            params.n_swa_checkpoints = value;
+            params.n_ctx_checkpoints = value;
         }
-    ).set_env("LLAMA_ARG_SWA_CHECKPOINTS").set_examples({LLAMA_EXAMPLE_SERVER}));
+    ).set_env("LLAMA_ARG_CTX_CHECKPOINTS").set_examples({LLAMA_EXAMPLE_SERVER}));
     add_opt(common_arg(
         {"--kv-unified", "-kvu"},
         string_format("use single unified KV buffer for the KV cache of all sequences (default: %s)\n"

common/chat.cpp

@@ -625,6 +625,7 @@ const char * common_chat_format_name(common_chat_format format) {
         case COMMON_CHAT_FORMAT_CONTENT_ONLY: return "Content-only";
         case COMMON_CHAT_FORMAT_GENERIC: return "Generic";
         case COMMON_CHAT_FORMAT_MISTRAL_NEMO: return "Mistral Nemo";
+        case COMMON_CHAT_FORMAT_MAGISTRAL: return "Magistral";
         case COMMON_CHAT_FORMAT_LLAMA_3_X: return "Llama 3.x";
         case COMMON_CHAT_FORMAT_LLAMA_3_X_WITH_BUILTIN_TOOLS: return "Llama 3.x with builtin tools";
         case COMMON_CHAT_FORMAT_DEEPSEEK_R1: return "DeepSeek R1";
@@ -984,6 +985,65 @@ static common_chat_params common_chat_params_init_mistral_nemo(const common_chat
     data.format = COMMON_CHAT_FORMAT_MISTRAL_NEMO;
     return data;
 }
+
+static common_chat_params common_chat_params_init_magistral(const common_chat_template & tmpl, const struct templates_params & inputs) {
+    common_chat_params data;
+    data.prompt = apply(tmpl, inputs);
+    data.format = COMMON_CHAT_FORMAT_MAGISTRAL;
+    data.preserved_tokens = {
+        "[THINK]",
+        "[/THINK]",
+    };
+
+    if (inputs.tools.is_array() && !inputs.tools.empty()) {
+        data.grammar_lazy = inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_REQUIRED;
+        data.grammar = build_grammar([&](const common_grammar_builder & builder) {
+            auto schemas = json::array();
+            foreach_function(inputs.tools, [&](const json & tool) {
+                const auto & function = tool.at("function");
+                schemas.push_back({
+                    {"type", "object"},
+                    {"properties", {
+                        {"name", {
+                            {"type", "string"},
+                            {"const", function.at("name")},
+                        }},
+                        {"arguments", function.at("parameters")},
+                        {"id", {
+                            {"type", "string"},
+                            {"pattern", "^[a-zA-Z0-9]{9}$"},
+                        }},
+                    }},
+                    {"required", json::array({"name", "arguments", "id"})},
+                });
+            });
+            auto schema = json {
+                {"type", "array"},
+                {"items", schemas.size() == 1 ? schemas[0] : json {{"anyOf", schemas}}},
+                {"minItems", 1},
+            };
+            if (!inputs.parallel_tool_calls) {
+                schema["maxItems"] = 1;
+            }
+            builder.add_rule("root", "\"[TOOL_CALLS]\" " + builder.add_schema("tool_calls", schema));
+        });
+        data.grammar_triggers.push_back({COMMON_GRAMMAR_TRIGGER_TYPE_WORD, "[TOOL_CALLS]"});
+        data.preserved_tokens.push_back("[TOOL_CALLS]");
+    } else {
+        data.grammar_lazy = false;
+        if (!inputs.json_schema.is_null()) {
+            if (!inputs.grammar.empty()) {
+                throw std::runtime_error("Either \"json_schema\" or \"grammar\" can be specified, but not both");
+            }
+            data.grammar = json_schema_to_grammar(inputs.json_schema);
+        } else {
+            data.grammar = inputs.grammar;
+        }
+    }
+
+    return data;
+}
+
 static void common_chat_parse_mistral_nemo(common_chat_msg_parser & builder) {
     if (!builder.syntax().parse_tool_calls) {
         builder.add_content(builder.consume_rest());
@@ -994,6 +1054,18 @@ static void common_chat_parse_mistral_nemo(common_chat_msg_parser & builder) {
     parse_prefixed_json_tool_call_array(builder, prefix);
 }
 
+static void common_chat_parse_magistral(common_chat_msg_parser & builder) {
+    builder.try_parse_reasoning("[THINK]", "[/THINK]");
+
+    if (!builder.syntax().parse_tool_calls) {
+        builder.add_content(builder.consume_rest());
+        return;
+    }
+
+    static const common_regex prefix(regex_escape("[TOOL_CALLS]"));
+    parse_prefixed_json_tool_call_array(builder, prefix);
+}
+
 static common_chat_params common_chat_params_init_command_r7b(const common_chat_template & tmpl, const struct templates_params & inputs) {
     common_chat_params data;
 
@@ -2702,6 +2774,10 @@ static common_chat_params common_chat_templates_apply_jinja(
         return common_chat_params_init_llama_3_x(tmpl, params, allow_python_tag_builtin_tools);
     }
 
+    if (src.find("[THINK]") != std::string::npos && src.find("[/THINK]") != std::string::npos) {
+        return common_chat_params_init_magistral(tmpl, params);
+    }
+
     // Plain handler (no tools)
     if (params.tools.is_null() || inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_NONE) {
         return common_chat_params_init_without_tools(tmpl, params);
@@ -2802,6 +2878,9 @@ static void common_chat_parse(common_chat_msg_parser & builder) {
         case COMMON_CHAT_FORMAT_MISTRAL_NEMO:
             common_chat_parse_mistral_nemo(builder);
             break;
+        case COMMON_CHAT_FORMAT_MAGISTRAL:
+            common_chat_parse_magistral(builder);
+            break;
         case COMMON_CHAT_FORMAT_LLAMA_3_X:
             common_chat_parse_llama_3_1(builder);
             break;

common/chat.h

@@ -101,6 +101,7 @@ enum common_chat_format {
     COMMON_CHAT_FORMAT_CONTENT_ONLY,
     COMMON_CHAT_FORMAT_GENERIC,
     COMMON_CHAT_FORMAT_MISTRAL_NEMO,
+    COMMON_CHAT_FORMAT_MAGISTRAL,
     COMMON_CHAT_FORMAT_LLAMA_3_X,
     COMMON_CHAT_FORMAT_LLAMA_3_X_WITH_BUILTIN_TOOLS,
     COMMON_CHAT_FORMAT_DEEPSEEK_R1,

common/common.h

@@ -424,7 +424,7 @@ struct common_params {
     int32_t timeout_write     = timeout_read; // http write timeout in seconds
     int32_t n_threads_http    = -1;           // number of threads to process HTTP requests (TODO: support threadpool)
     int32_t n_cache_reuse     = 0;            // min chunk size to reuse from the cache via KV shifting
-    int32_t n_swa_checkpoints = 3;            // max number of SWA checkpoints per slot
+    int32_t n_ctx_checkpoints = 3;            // max number of context checkpoints per slot
 
     std::string hostname      = "127.0.0.1";
     std::string public_path   = "";                                                                         // NOLINT

ggml/include/ggml-backend.h

@@ -215,6 +215,8 @@ extern "C" {
     // Backend registry
     //
 
+    GGML_API void ggml_backend_register(ggml_backend_reg_t reg);
+
     GGML_API void ggml_backend_device_register(ggml_backend_dev_t device);
 
     // Backend (reg) enumeration

ggml/include/ggml-rpc.h

@@ -7,26 +7,25 @@
 extern "C" {
 #endif
 
-#define RPC_PROTO_MAJOR_VERSION    2
+#define RPC_PROTO_MAJOR_VERSION    3
 #define RPC_PROTO_MINOR_VERSION    0
 #define RPC_PROTO_PATCH_VERSION    0
 #define GGML_RPC_MAX_SERVERS       16
 
 // backend API
-GGML_BACKEND_API ggml_backend_t ggml_backend_rpc_init(const char * endpoint);
+GGML_BACKEND_API ggml_backend_t ggml_backend_rpc_init(const char * endpoint, uint32_t device);
 GGML_BACKEND_API bool ggml_backend_is_rpc(ggml_backend_t backend);
 
-GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_rpc_buffer_type(const char * endpoint);
+GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_rpc_buffer_type(const char * endpoint, uint32_t device);
 
-GGML_BACKEND_API void ggml_backend_rpc_get_device_memory(const char * endpoint, size_t * free, size_t * total);
+GGML_BACKEND_API void ggml_backend_rpc_get_device_memory(const char * endpoint, uint32_t device, size_t * free, size_t * total);
 
-GGML_BACKEND_API void ggml_backend_rpc_start_server(ggml_backend_t backend, const char * endpoint,
-                                                    const char * cache_dir,
-                                                    size_t free_mem, size_t total_mem);
+GGML_BACKEND_API void ggml_backend_rpc_start_server(const char * endpoint, const char * cache_dir,
+                                                    size_t n_threads, size_t n_devices,
+                                                    ggml_backend_dev_t * devices, size_t * free_mem, size_t * total_mem);
 
 GGML_BACKEND_API ggml_backend_reg_t ggml_backend_rpc_reg(void);
-
-GGML_BACKEND_API ggml_backend_dev_t ggml_backend_rpc_add_device(const char * endpoint);
+GGML_BACKEND_API ggml_backend_reg_t ggml_backend_rpc_add_server(const char * endpoint);
 
 #ifdef  __cplusplus
 }

ggml/src/ggml-backend-impl.h

@@ -209,9 +209,6 @@ extern "C" {
         void * context;
     };
 
-    // Internal backend registry API
-    GGML_API void ggml_backend_register(ggml_backend_reg_t reg);
-
     // Add backend dynamic loading support to the backend
 
     // Initialize the backend

ggml/src/ggml-rpc/ggml-rpc.cpp

@@ -105,9 +105,12 @@ enum rpc_cmd {
     RPC_CMD_INIT_TENSOR,
     RPC_CMD_GET_ALLOC_SIZE,
     RPC_CMD_HELLO,
+    RPC_CMD_DEVICE_COUNT,
     RPC_CMD_COUNT,
 };
 
+static_assert(RPC_CMD_HELLO == 14, "RPC_CMD_HELLO must be always 14");
+
 // Try RPC_CMD_SET_TENSOR_HASH first when data size is larger than this threshold
 const size_t HASH_THRESHOLD = 10 * 1024 * 1024;
 
@@ -117,7 +120,12 @@ struct rpc_msg_hello_rsp {
     uint8_t patch;
 };
 
+struct rpc_msg_device_count_rsp {
+    uint32_t device_count;
+};
+
 struct rpc_msg_get_alloc_size_req {
+    uint32_t   device;
     rpc_tensor tensor;
 };
 
@@ -130,6 +138,7 @@ struct rpc_msg_init_tensor_req {
 };
 
 struct rpc_msg_alloc_buffer_req {
+    uint32_t device;
     uint64_t size;
 };
 
@@ -138,10 +147,18 @@ struct rpc_msg_alloc_buffer_rsp {
     uint64_t remote_size;
 };
 
+struct rpc_msg_get_alignment_req {
+    uint32_t device;
+};
+
 struct rpc_msg_get_alignment_rsp {
     uint64_t alignment;
 };
 
+struct rpc_msg_get_max_size_req {
+    uint32_t device;
+};
+
 struct rpc_msg_get_max_size_rsp {
     uint64_t max_size;
 };
@@ -192,6 +209,10 @@ struct rpc_msg_graph_compute_rsp {
     uint8_t result;
 };
 
+struct rpc_msg_get_device_memory_req {
+    uint32_t device;
+};
+
 struct rpc_msg_get_device_memory_rsp {
     uint64_t free_mem;
     uint64_t total_mem;
@@ -207,13 +228,15 @@ static ggml_guid_t ggml_backend_rpc_guid() {
 
 struct ggml_backend_rpc_buffer_type_context {
     std::string endpoint;
+    uint32_t    device;
     std::string name;
-    size_t alignment;
-    size_t max_size;
+    size_t      alignment;
+    size_t      max_size;
 };
 
 struct ggml_backend_rpc_context {
     std::string endpoint;
+    uint32_t    device;
     std::string name;
 };
 
@@ -608,23 +631,30 @@ static void ggml_backend_rpc_buffer_get_tensor(ggml_backend_buffer_t buffer, con
     RPC_STATUS_ASSERT(status);
 }
 
+static bool ggml_backend_buffer_is_rpc(ggml_backend_buffer_t buffer) {
+    return buffer->iface.free_buffer == ggml_backend_rpc_buffer_free_buffer;
+}
+
 static bool ggml_backend_rpc_buffer_cpy_tensor(ggml_backend_buffer_t buffer, const ggml_tensor * src, ggml_tensor * dst) {
-    // check if src and dst are on the same server
-    ggml_backend_buffer_t src_buffer = src->buffer;
-    ggml_backend_rpc_buffer_context * src_ctx = (ggml_backend_rpc_buffer_context *)src_buffer->context;
-    ggml_backend_buffer_t dst_buffer = dst->buffer;
-    ggml_backend_rpc_buffer_context * dst_ctx = (ggml_backend_rpc_buffer_context *)dst_buffer->context;
-    if (src_ctx->sock != dst_ctx->sock) {
-        return false;
+    if (ggml_backend_buffer_is_rpc(src->buffer)) {
+        // check if src and dst are on the same server
+        ggml_backend_buffer_t src_buffer = src->buffer;
+        ggml_backend_rpc_buffer_context * src_ctx = (ggml_backend_rpc_buffer_context *)src_buffer->context;
+        ggml_backend_buffer_t dst_buffer = dst->buffer;
+        ggml_backend_rpc_buffer_context * dst_ctx = (ggml_backend_rpc_buffer_context *)dst_buffer->context;
+        if (src_ctx->sock != dst_ctx->sock) {
+            return false;
+        }
+        ggml_backend_rpc_buffer_context * ctx = (ggml_backend_rpc_buffer_context *)buffer->context;
+        rpc_msg_copy_tensor_req request;
+        request.src = serialize_tensor(src);
+        request.dst = serialize_tensor(dst);
+        rpc_msg_copy_tensor_rsp response;
+        bool status = send_rpc_cmd(ctx->sock, RPC_CMD_COPY_TENSOR, &request, sizeof(request), &response, sizeof(response));
+        RPC_STATUS_ASSERT(status);
+        return response.result;
     }
-    ggml_backend_rpc_buffer_context * ctx = (ggml_backend_rpc_buffer_context *)buffer->context;
-    rpc_msg_copy_tensor_req request;
-    request.src = serialize_tensor(src);
-    request.dst = serialize_tensor(dst);
-    rpc_msg_copy_tensor_rsp response;
-    bool status = send_rpc_cmd(ctx->sock, RPC_CMD_COPY_TENSOR, &request, sizeof(request), &response, sizeof(response));
-    RPC_STATUS_ASSERT(status);
-    return response.result;
+    return false;
 }
 
 static void ggml_backend_rpc_buffer_clear(ggml_backend_buffer_t buffer, uint8_t value) {
@@ -653,7 +683,7 @@ static const char * ggml_backend_rpc_buffer_type_name(ggml_backend_buffer_type_t
 
 static ggml_backend_buffer_t ggml_backend_rpc_buffer_type_alloc_buffer(ggml_backend_buffer_type_t buft, size_t size) {
     ggml_backend_rpc_buffer_type_context * buft_ctx = (ggml_backend_rpc_buffer_type_context *)buft->context;
-    rpc_msg_alloc_buffer_req request = {size};
+    rpc_msg_alloc_buffer_req request = {buft_ctx->device, size};
     rpc_msg_alloc_buffer_rsp response;
     auto sock = get_socket(buft_ctx->endpoint);
     bool status = send_rpc_cmd(sock, RPC_CMD_ALLOC_BUFFER, &request, sizeof(request), &response, sizeof(response));
@@ -669,9 +699,10 @@ static ggml_backend_buffer_t ggml_backend_rpc_buffer_type_alloc_buffer(ggml_back
     }
 }
 
-static size_t get_alignment(const std::shared_ptr<socket_t> & sock) {
+static size_t get_alignment(const std::shared_ptr<socket_t> & sock, uint32_t device) {
+    rpc_msg_get_alignment_req request = {device};
     rpc_msg_get_alignment_rsp response;
-    bool status = send_rpc_cmd(sock, RPC_CMD_GET_ALIGNMENT, nullptr, 0, &response, sizeof(response));
+    bool status = send_rpc_cmd(sock, RPC_CMD_GET_ALIGNMENT, &request, sizeof(request), &response, sizeof(response));
     RPC_STATUS_ASSERT(status);
     return response.alignment;
 }
@@ -681,9 +712,10 @@ static size_t ggml_backend_rpc_buffer_type_get_alignment(ggml_backend_buffer_typ
     return buft_ctx->alignment;
 }
 
-static size_t get_max_size(const std::shared_ptr<socket_t> & sock) {
+static size_t get_max_size(const std::shared_ptr<socket_t> & sock, uint32_t device) {
+    rpc_msg_get_max_size_req request = {device};
     rpc_msg_get_max_size_rsp response;
-    bool status = send_rpc_cmd(sock, RPC_CMD_GET_MAX_SIZE, nullptr, 0, &response, sizeof(response));
+    bool status = send_rpc_cmd(sock, RPC_CMD_GET_MAX_SIZE, &request, sizeof(request), &response, sizeof(response));
     RPC_STATUS_ASSERT(status);
     return response.max_size;
 }
@@ -700,7 +732,7 @@ static size_t ggml_backend_rpc_buffer_type_get_alloc_size(ggml_backend_buffer_ty
         auto sock = get_socket(buft_ctx->endpoint);
 
         rpc_msg_get_alloc_size_req request;
-
+        request.device = buft_ctx->device;
         request.tensor = serialize_tensor(tensor);
 
         rpc_msg_get_alloc_size_rsp response;
@@ -754,7 +786,7 @@ static void add_tensor(ggml_tensor * tensor, std::vector<rpc_tensor> & tensors,
     tensors.push_back(serialize_tensor(tensor));
 }
 
-static void serialize_graph(const ggml_cgraph * cgraph, std::vector<uint8_t> & output) {
+static void serialize_graph(uint32_t device, const ggml_cgraph * cgraph, std::vector<uint8_t> & output) {
     uint32_t n_nodes = cgraph->n_nodes;
     std::vector<rpc_tensor> tensors;
     std::unordered_set<ggml_tensor*> visited;
@@ -762,24 +794,29 @@ static void serialize_graph(const ggml_cgraph * cgraph, std::vector<uint8_t> & o
         add_tensor(cgraph->nodes[i], tensors, visited);
     }
     // serialization format:
-    // | n_nodes (4 bytes) | nodes (n_nodes * sizeof(uint64_t) | n_tensors (4 bytes) | tensors (n_tensors * sizeof(rpc_tensor)) |
+    // | device (4 bytes) | n_nodes (4 bytes) | nodes (n_nodes * sizeof(uint64_t) | n_tensors (4 bytes) | tensors (n_tensors * sizeof(rpc_tensor)) |
     uint32_t n_tensors = tensors.size();
-    int output_size = sizeof(uint32_t) + n_nodes * sizeof(uint64_t) + sizeof(uint32_t) + n_tensors * sizeof(rpc_tensor);
+    int output_size = 2*sizeof(uint32_t) + n_nodes * sizeof(uint64_t) + sizeof(uint32_t) + n_tensors * sizeof(rpc_tensor);
     output.resize(output_size, 0);
-    memcpy(output.data(), &n_nodes, sizeof(n_nodes));
+    uint8_t * dest = output.data();
+    memcpy(dest, &device, sizeof(device));
+    dest += sizeof(device);
+    memcpy(dest, &n_nodes, sizeof(n_nodes));
+    dest += sizeof(n_nodes);
     for (uint32_t i = 0; i < n_nodes; i++) {
-        memcpy(output.data() + sizeof(n_nodes) + i * sizeof(uint64_t), &cgraph->nodes[i], sizeof(uint64_t));
+        memcpy(dest + i * sizeof(uint64_t), &cgraph->nodes[i], sizeof(uint64_t));
     }
-    uint32_t * out_ntensors = (uint32_t *)(output.data() + sizeof(n_nodes) + n_nodes * sizeof(uint64_t));
-    *out_ntensors = n_tensors;
-    rpc_tensor * out_tensors = (rpc_tensor *)(output.data() + sizeof(n_nodes) + n_nodes * sizeof(uint64_t) + sizeof(uint32_t));
+    dest += n_nodes * sizeof(uint64_t);
+    memcpy(dest, &n_tensors, sizeof(n_tensors));
+    dest += sizeof(n_tensors);
+    rpc_tensor * out_tensors = (rpc_tensor *)dest;
     memcpy(out_tensors, tensors.data(), n_tensors * sizeof(rpc_tensor));
 }
 
 static enum ggml_status ggml_backend_rpc_graph_compute(ggml_backend_t backend, ggml_cgraph * cgraph) {
     ggml_backend_rpc_context * rpc_ctx = (ggml_backend_rpc_context *)backend->context;
     std::vector<uint8_t> input;
-    serialize_graph(cgraph, input);
+    serialize_graph(rpc_ctx->device, cgraph, input);
     rpc_msg_graph_compute_rsp response;
     auto sock = get_socket(rpc_ctx->endpoint);
     bool status = send_rpc_cmd(sock, RPC_CMD_GRAPH_COMPUTE, input.data(), input.size(), &response, sizeof(response));
@@ -804,12 +841,13 @@ static ggml_backend_i ggml_backend_rpc_interface = {
     /* .graph_optimize          = */ NULL,
 };
 
-ggml_backend_buffer_type_t ggml_backend_rpc_buffer_type(const char * endpoint) {
+ggml_backend_buffer_type_t ggml_backend_rpc_buffer_type(const char * endpoint, uint32_t device) {
     static std::mutex mutex;
     std::lock_guard<std::mutex> lock(mutex);
+    std::string buft_name = "RPC" + std::to_string(device) + "[" + std::string(endpoint) + "]";
     // NOTE: buffer types are allocated and never freed; this is by design
     static std::unordered_map<std::string, ggml_backend_buffer_type_t> buft_map;
-    auto it = buft_map.find(endpoint);
+    auto it = buft_map.find(buft_name);
     if (it != buft_map.end()) {
         return it->second;
     }
@@ -818,34 +856,37 @@ ggml_backend_buffer_type_t ggml_backend_rpc_buffer_type(const char * endpoint) {
         GGML_LOG_ERROR("Failed to connect to %s\n", endpoint);
         return nullptr;
     }
-    size_t alignment = get_alignment(sock);
-    size_t max_size = get_max_size(sock);
+    size_t alignment = get_alignment(sock, device);
+    size_t max_size = get_max_size(sock, device);
     ggml_backend_rpc_buffer_type_context * buft_ctx = new ggml_backend_rpc_buffer_type_context {
         /* .endpoint  = */ endpoint,
-        /* .name      = */ "RPC[" + std::string(endpoint) + "]",
+        /* .device    = */ device,
+        /* .name      = */ buft_name,
         /* .alignment = */ alignment,
         /* .max_size  = */ max_size
     };
-
+    auto reg = ggml_backend_rpc_add_server(endpoint);
     ggml_backend_buffer_type_t buft = new ggml_backend_buffer_type {
         /* .iface   = */ ggml_backend_rpc_buffer_type_interface,
-        /* .device  = */ ggml_backend_rpc_add_device(endpoint),
+        /* .device  = */ ggml_backend_reg_dev_get(reg, device),
         /* .context = */ buft_ctx
     };
-    buft_map[endpoint] = buft;
+    buft_map[buft_name] = buft;
     return buft;
 }
 
-ggml_backend_t ggml_backend_rpc_init(const char * endpoint) {
+ggml_backend_t ggml_backend_rpc_init(const char * endpoint, uint32_t device) {
+    std::string dev_name = "RPC" + std::to_string(device) + "[" + std::string(endpoint) + "]";
     ggml_backend_rpc_context * ctx = new ggml_backend_rpc_context {
-        /* .endpoint  = */ endpoint,
-        /* .name      = */ "RPC[" + std::string(endpoint) + "]",
+        /* .endpoint = */ endpoint,
+        /* .device   = */ device,
+        /* .name     = */ dev_name
     };
-
+    auto reg = ggml_backend_rpc_add_server(endpoint);
     ggml_backend_t backend = new ggml_backend {
         /* .guid    = */ ggml_backend_rpc_guid(),
         /* .iface   = */ ggml_backend_rpc_interface,
-        /* .device  = */ ggml_backend_rpc_add_device(endpoint),
+        /* .device  = */ ggml_backend_reg_dev_get(reg, device),
         /* .context = */ ctx
     };
     return backend;
@@ -855,37 +896,39 @@ bool ggml_backend_is_rpc(ggml_backend_t backend) {
     return backend != NULL && ggml_guid_matches(backend->guid, ggml_backend_rpc_guid());
 }
 
-static void get_device_memory(const std::shared_ptr<socket_t> & sock, size_t * free, size_t * total) {
+static void get_device_memory(const std::shared_ptr<socket_t> & sock, uint32_t device, size_t * free, size_t * total) {
+    rpc_msg_get_device_memory_req request;
+    request.device = device;
     rpc_msg_get_device_memory_rsp response;
-    bool status = send_rpc_cmd(sock, RPC_CMD_GET_DEVICE_MEMORY, nullptr, 0, &response, sizeof(response));
+    bool status = send_rpc_cmd(sock, RPC_CMD_GET_DEVICE_MEMORY, &request, sizeof(request), &response, sizeof(response));
     RPC_STATUS_ASSERT(status);
     *free = response.free_mem;
     *total = response.total_mem;
 }
 
-void ggml_backend_rpc_get_device_memory(const char * endpoint, size_t * free, size_t * total) {
+void ggml_backend_rpc_get_device_memory(const char * endpoint, uint32_t device, size_t * free, size_t * total) {
     auto sock = get_socket(endpoint);
     if (sock == nullptr) {
         *free = 0;
         *total = 0;
         return;
     }
-    get_device_memory(sock, free, total);
+    get_device_memory(sock, device, free, total);
 }
 
 // RPC server-side implementation
 
 class rpc_server {
 public:
-    rpc_server(ggml_backend_t backend, const char * cache_dir)
-        : backend(backend), cache_dir(cache_dir) {
+    rpc_server(std::vector<ggml_backend_t> backends, const char * cache_dir)
+        : backends(std::move(backends)), cache_dir(cache_dir) {
     }
     ~rpc_server();
 
     void hello(rpc_msg_hello_rsp & response);
-    void alloc_buffer(const rpc_msg_alloc_buffer_req & request, rpc_msg_alloc_buffer_rsp & response);
-    void get_alignment(rpc_msg_get_alignment_rsp & response);
-    void get_max_size(rpc_msg_get_max_size_rsp & response);
+    bool alloc_buffer(const rpc_msg_alloc_buffer_req & request, rpc_msg_alloc_buffer_rsp & response);
+    bool get_alignment(const rpc_msg_get_alignment_req & request, rpc_msg_get_alignment_rsp & response);
+    bool get_max_size(const rpc_msg_get_max_size_req & request, rpc_msg_get_max_size_rsp & response);
     bool buffer_get_base(const rpc_msg_buffer_get_base_req & request, rpc_msg_buffer_get_base_rsp & response);
     bool free_buffer(const rpc_msg_free_buffer_req & request);
     bool buffer_clear(const rpc_msg_buffer_clear_req & request);
@@ -906,7 +949,7 @@ private:
                               std::unordered_map<uint64_t, struct ggml_tensor*> & tensor_map);
 
 
-    ggml_backend_t backend;
+    std::vector<ggml_backend_t> backends;
     const char * cache_dir;
     std::unordered_set<ggml_backend_buffer_t> buffers;
 };
@@ -919,6 +962,10 @@ void rpc_server::hello(rpc_msg_hello_rsp & response) {
 }
 
 bool rpc_server::get_alloc_size(const rpc_msg_get_alloc_size_req & request, rpc_msg_get_alloc_size_rsp & response) {
+    uint32_t dev_id = request.device;
+    if (dev_id >= backends.size()) {
+        return false;
+    }
     ggml_backend_buffer_type_t buft;
     struct ggml_init_params params {
         /*.mem_size   =*/ ggml_tensor_overhead(),
@@ -935,10 +982,10 @@ bool rpc_server::get_alloc_size(const rpc_msg_get_alloc_size_req & request, rpc_
         GGML_LOG_ERROR("Null tensor pointer passed to server get_alloc_size function.\n");
         return false;
     }
-    LOG_DBG("[%s] buffer: %p, data: %p\n", __func__, (void*)tensor->buffer, tensor->data);
+    LOG_DBG("[%s] device: %d, buffer: %p, data: %p\n", __func__, dev_id, (void*)tensor->buffer, tensor->data);
     if (tensor->buffer == nullptr) {
         //No buffer allocated.
-        buft = ggml_backend_get_default_buffer_type(backend);
+        buft = ggml_backend_get_default_buffer_type(backends[dev_id]);
     } else {
         buft = tensor->buffer->buft;
     }
@@ -948,33 +995,49 @@ bool rpc_server::get_alloc_size(const rpc_msg_get_alloc_size_req & request, rpc_
     return true;
 }
 
-void rpc_server::alloc_buffer(const rpc_msg_alloc_buffer_req & request, rpc_msg_alloc_buffer_rsp & response) {
-    ggml_backend_buffer_type_t buft = ggml_backend_get_default_buffer_type(backend);
+bool rpc_server::alloc_buffer(const rpc_msg_alloc_buffer_req & request, rpc_msg_alloc_buffer_rsp & response) {
+    uint32_t dev_id = request.device;
+    if (dev_id >= backends.size()) {
+        return false;
+    }
+    ggml_backend_buffer_type_t buft = ggml_backend_get_default_buffer_type(backends[dev_id]);
     ggml_backend_buffer_t buffer = ggml_backend_buft_alloc_buffer(buft, request.size);
     response.remote_ptr = 0;
     response.remote_size = 0;
     if (buffer != nullptr) {
         response.remote_ptr = reinterpret_cast<uint64_t>(buffer);
         response.remote_size = buffer->size;
-        LOG_DBG("[%s] size: %" PRIu64 " -> remote_ptr: %" PRIx64 ", remote_size: %" PRIu64 "\n", __func__, request.size, response.remote_ptr, response.remote_size);
+        LOG_DBG("[%s] device: %d, size: %" PRIu64 " -> remote_ptr: %" PRIx64 ", remote_size: %" PRIu64 "\n",
+            __func__, dev_id, request.size, response.remote_ptr, response.remote_size);
         buffers.insert(buffer);
     } else {
-        LOG_DBG("[%s] size: %" PRIu64 " -> failed\n", __func__, request.size);
+        LOG_DBG("[%s] device: %d, size: %" PRIu64 " -> failed\n", __func__, dev_id, request.size);
     }
+    return true;
 }
 
-void rpc_server::get_alignment(rpc_msg_get_alignment_rsp & response) {
-    ggml_backend_buffer_type_t buft = ggml_backend_get_default_buffer_type(backend);
+bool rpc_server::get_alignment(const rpc_msg_get_alignment_req & request, rpc_msg_get_alignment_rsp & response) {
+    uint32_t dev_id = request.device;
+    if (dev_id >= backends.size()) {
+        return false;
+    }
+    ggml_backend_buffer_type_t buft = ggml_backend_get_default_buffer_type(backends[dev_id]);
     size_t alignment = ggml_backend_buft_get_alignment(buft);
-    LOG_DBG("[%s] alignment: %lu\n", __func__, alignment);
+    LOG_DBG("[%s] device: %d, alignment: %lu\n", __func__, dev_id, alignment);
     response.alignment = alignment;
+    return true;
 }
 
-void rpc_server::get_max_size(rpc_msg_get_max_size_rsp & response) {
-    ggml_backend_buffer_type_t buft = ggml_backend_get_default_buffer_type(backend);
+bool rpc_server::get_max_size(const rpc_msg_get_max_size_req & request, rpc_msg_get_max_size_rsp & response) {
+    uint32_t dev_id = request.device;
+    if (dev_id >= backends.size()) {
+        return false;
+    }
+    ggml_backend_buffer_type_t buft = ggml_backend_get_default_buffer_type(backends[dev_id]);
     size_t max_size = ggml_backend_buft_get_max_size(buft);
-    LOG_DBG("[%s] max_size: %lu\n", __func__, max_size);
+    LOG_DBG("[%s] device: %d, max_size: %lu\n", __func__, dev_id, max_size);
     response.max_size = max_size;
+    return true;
 }
 
 bool rpc_server::buffer_get_base(const rpc_msg_buffer_get_base_req & request, rpc_msg_buffer_get_base_rsp & response) {
@@ -1332,23 +1395,33 @@ ggml_tensor * rpc_server::create_node(uint64_t id,
 
 bool rpc_server::graph_compute(const std::vector<uint8_t> & input, rpc_msg_graph_compute_rsp & response) {
     // serialization format:
-    // | n_nodes (4 bytes) | nodes (n_nodes * sizeof(uint64_t) | n_tensors (4 bytes) | tensors (n_tensors * sizeof(rpc_tensor)) |
-    if (input.size() < sizeof(uint32_t)) {
+    // | device (4 bytes) | n_nodes (4 bytes) | nodes (n_nodes * sizeof(uint64_t) | n_tensors (4 bytes) | tensors (n_tensors * sizeof(rpc_tensor)) |
+    if (input.size() < 2*sizeof(uint32_t)) {
+        return false;
+    }
+    const uint8_t * src = input.data();
+    uint32_t device;
+    memcpy(&device, src, sizeof(device));
+    src += sizeof(device);
+    if (device >= backends.size()) {
         return false;
     }
     uint32_t n_nodes;
-    memcpy(&n_nodes, input.data(), sizeof(n_nodes));
-    if (input.size() < sizeof(uint32_t) + n_nodes*sizeof(uint64_t) + sizeof(uint32_t)) {
+    memcpy(&n_nodes, src, sizeof(n_nodes));
+    src += sizeof(n_nodes);
+    if (input.size() < 2*sizeof(uint32_t) + n_nodes*sizeof(uint64_t) + sizeof(uint32_t)) {
         return false;
     }
-    const uint64_t * nodes = (const uint64_t *)(input.data() + sizeof(n_nodes));
+    const uint64_t * nodes = (const uint64_t *)src;
+    src += n_nodes*sizeof(uint64_t);
     uint32_t n_tensors;
-    memcpy(&n_tensors, input.data() + sizeof(n_nodes) + n_nodes*sizeof(uint64_t), sizeof(n_tensors));
-    if (input.size() < sizeof(uint32_t) + n_nodes*sizeof(uint64_t) + sizeof(uint32_t) + n_tensors*sizeof(rpc_tensor)) {
+    memcpy(&n_tensors, src, sizeof(n_tensors));
+    src += sizeof(n_tensors);
+    if (input.size() < 2*sizeof(uint32_t) + n_nodes*sizeof(uint64_t) + sizeof(uint32_t) + n_tensors*sizeof(rpc_tensor)) {
         return false;
     }
-    const rpc_tensor * tensors = (const rpc_tensor *)(input.data() + sizeof(n_nodes) + n_nodes*sizeof(uint64_t) + sizeof(n_tensors));
-    LOG_DBG("[%s] n_nodes: %u, n_tensors: %u\n", __func__, n_nodes, n_tensors);
+    const rpc_tensor * tensors = (const rpc_tensor *)src;
+    LOG_DBG("[%s] device: %u, n_nodes: %u, n_tensors: %u\n", __func__, device, n_nodes, n_tensors);
 
     size_t buf_size = ggml_tensor_overhead()*(n_nodes + n_tensors) + ggml_graph_overhead_custom(n_nodes, false);
 
@@ -1380,7 +1453,7 @@ bool rpc_server::graph_compute(const std::vector<uint8_t> & input, rpc_msg_graph
             return false;
         }
     }
-    ggml_status status = ggml_backend_graph_compute(backend, graph);
+    ggml_status status = ggml_backend_graph_compute(backends[device], graph);
     response.result = status;
     return true;
 }
@@ -1391,9 +1464,9 @@ rpc_server::~rpc_server() {
     }
 }
 
-static void rpc_serve_client(ggml_backend_t backend, const char * cache_dir,
-                             sockfd_t sockfd, size_t free_mem, size_t total_mem) {
-    rpc_server server(backend, cache_dir);
+static void rpc_serve_client(const std::vector<ggml_backend_t> & backends, const char * cache_dir,
+                             sockfd_t sockfd, const std::vector<size_t> & free_mem, const std::vector<size_t> & total_mem) {
+    rpc_server server(backends, cache_dir);
     uint8_t cmd;
     if (!recv_data(sockfd, &cmd, 1)) {
         return;
@@ -1425,13 +1498,26 @@ static void rpc_serve_client(ggml_backend_t backend, const char * cache_dir,
                 // HELLO command is handled above
                 return;
             }
+            case RPC_CMD_DEVICE_COUNT: {
+                if (!recv_msg(sockfd, nullptr, 0)) {
+                    return;
+                }
+                rpc_msg_device_count_rsp response;
+                response.device_count = backends.size();
+                if (!send_msg(sockfd, &response, sizeof(response))) {
+                    return;
+                }
+                break;
+            }
             case RPC_CMD_ALLOC_BUFFER: {
                 rpc_msg_alloc_buffer_req request;
                 if (!recv_msg(sockfd, &request, sizeof(request))) {
                     return;
                 }
                 rpc_msg_alloc_buffer_rsp response;
-                server.alloc_buffer(request, response);
+                if (!server.alloc_buffer(request, response)) {
+                    return;
+                }
                 if (!send_msg(sockfd, &response, sizeof(response))) {
                     return;
                 }
@@ -1452,22 +1538,28 @@ static void rpc_serve_client(ggml_backend_t backend, const char * cache_dir,
                 break;
             }
             case RPC_CMD_GET_ALIGNMENT: {
-                if (!recv_msg(sockfd, nullptr, 0)) {
+                rpc_msg_get_alignment_req request;
+                if (!recv_msg(sockfd, &request, sizeof(request))) {
                     return;
                 }
                 rpc_msg_get_alignment_rsp response;
-                server.get_alignment(response);
+                if (!server.get_alignment(request, response)) {
+                    return;
+                }
                 if (!send_msg(sockfd, &response, sizeof(response))) {
                     return;
                 }
                 break;
             }
             case RPC_CMD_GET_MAX_SIZE: {
-                if (!recv_msg(sockfd, nullptr, 0)) {
+                rpc_msg_get_max_size_req request;
+                if (!recv_msg(sockfd, &request, sizeof(request))) {
                     return;
                 }
                 rpc_msg_get_max_size_rsp response;
-                server.get_max_size(response);
+                if (!server.get_max_size(request, response)) {
+                    return;
+                }
                 if (!send_msg(sockfd, &response, sizeof(response))) {
                     return;
                 }
@@ -1593,12 +1685,19 @@ static void rpc_serve_client(ggml_backend_t backend, const char * cache_dir,
                 break;
             }
             case RPC_CMD_GET_DEVICE_MEMORY: {
-                if (!recv_msg(sockfd, nullptr, 0)) {
+                rpc_msg_get_device_memory_req request;
+                if (!recv_msg(sockfd, &request, sizeof(request))) {
+                    return;
+                }
+                auto dev_id = request.device;
+                if (dev_id >= backends.size()) {
                     return;
                 }
                 rpc_msg_get_device_memory_rsp response;
-                response.free_mem = free_mem;
-                response.total_mem = total_mem;
+                response.free_mem = free_mem[dev_id];
+                response.total_mem = total_mem[dev_id];
+                LOG_DBG("[get_device_mem] device: %u, free_mem: %" PRIu64 ", total_mem: %" PRIu64 "\n", dev_id,
+                    response.free_mem, response.total_mem);
                 if (!send_msg(sockfd, &response, sizeof(response))) {
                     return;
                 }
@@ -1612,16 +1711,41 @@ static void rpc_serve_client(ggml_backend_t backend, const char * cache_dir,
     }
 }
 
-void ggml_backend_rpc_start_server(ggml_backend_t backend, const char * endpoint,
-                                   const char * cache_dir,
-                                   size_t free_mem, size_t total_mem) {
+void ggml_backend_rpc_start_server(const char * endpoint, const char * cache_dir,
+                                   size_t n_threads, size_t n_devices,
+                                   ggml_backend_dev_t * devices, size_t * free_mem, size_t * total_mem) {
+    if (n_devices == 0 || devices == nullptr || free_mem == nullptr || total_mem == nullptr) {
+        fprintf(stderr, "Invalid arguments to ggml_backend_rpc_start_server\n");
+        return;
+    }
+    std::vector<ggml_backend_t> backends;
+    std::vector<size_t> free_mem_vec(free_mem, free_mem + n_devices);
+    std::vector<size_t> total_mem_vec(total_mem, total_mem + n_devices);
     printf("Starting RPC server v%d.%d.%d\n",
         RPC_PROTO_MAJOR_VERSION,
         RPC_PROTO_MINOR_VERSION,
         RPC_PROTO_PATCH_VERSION);
     printf("  endpoint       : %s\n", endpoint);
     printf("  local cache    : %s\n", cache_dir ? cache_dir : "n/a");
-    printf("  backend memory : %zu MB\n", free_mem / (1024 * 1024));
+    printf("Devices:\n");
+    for (size_t i = 0; i < n_devices; i++) {
+        auto dev = devices[i];
+        printf("  %s: %s (%zu MiB, %zu MiB free)\n", ggml_backend_dev_name(dev), ggml_backend_dev_description(dev),
+               total_mem[i] / 1024 / 1024, free_mem[i] / 1024 / 1024);
+        auto backend = ggml_backend_dev_init(dev, nullptr);
+        if (!backend) {
+            fprintf(stderr, "Failed to create backend for device %s\n", dev->iface.get_name(dev));
+            return;
+        }
+        backends.push_back(backend);
+        ggml_backend_reg_t reg = dev ? ggml_backend_dev_backend_reg(dev) : nullptr;
+        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(backend, n_threads);
+            }
+        }
+    }
 
     std::string host;
     int port;
@@ -1649,22 +1773,27 @@ void ggml_backend_rpc_start_server(ggml_backend_t backend, const char * endpoint
             fprintf(stderr, "Failed to accept client connection\n");
             return;
         }
-        printf("Accepted client connection, free_mem=%zu, total_mem=%zu\n", free_mem, total_mem);
+        printf("Accepted client connection\n");
         fflush(stdout);
-        rpc_serve_client(backend, cache_dir, client_socket->fd, free_mem, total_mem);
+        rpc_serve_client(backends, cache_dir, client_socket->fd, free_mem_vec, total_mem_vec);
         printf("Client connection closed\n");
         fflush(stdout);
     }
 #ifdef _WIN32
     WSACleanup();
 #endif
+    for (auto backend : backends) {
+        ggml_backend_free(backend);
+    }
 }
 
 // device interface
 
 struct ggml_backend_rpc_device_context {
     std::string endpoint;
+    uint32_t    device;
     std::string name;
+    std::string description;
 };
 
 static const char * ggml_backend_rpc_device_get_name(ggml_backend_dev_t dev) {
@@ -1676,15 +1805,13 @@ static const char * ggml_backend_rpc_device_get_name(ggml_backend_dev_t dev) {
 static const char * ggml_backend_rpc_device_get_description(ggml_backend_dev_t dev) {
     ggml_backend_rpc_device_context * ctx = (ggml_backend_rpc_device_context *)dev->context;
 
-    return ctx->name.c_str();
+    return ctx->description.c_str();
 }
 
 static void ggml_backend_rpc_device_get_memory(ggml_backend_dev_t dev, size_t * free, size_t * total) {
     ggml_backend_rpc_device_context * ctx = (ggml_backend_rpc_device_context *)dev->context;
 
-    ggml_backend_rpc_get_device_memory(ctx->endpoint.c_str(), free, total);
-
-    GGML_UNUSED(dev);
+    ggml_backend_rpc_get_device_memory(ctx->endpoint.c_str(), ctx->device, free, total);
 }
 
 static enum ggml_backend_dev_type ggml_backend_rpc_device_get_type(ggml_backend_dev_t dev) {
@@ -1710,7 +1837,7 @@ static void ggml_backend_rpc_device_get_props(ggml_backend_dev_t dev, struct ggm
 static ggml_backend_t ggml_backend_rpc_device_init(ggml_backend_dev_t dev, const char * params) {
     ggml_backend_rpc_device_context * ctx = (ggml_backend_rpc_device_context *)dev->context;
 
-    return ggml_backend_rpc_init(ctx->endpoint.c_str());
+    return ggml_backend_rpc_init(ctx->endpoint.c_str(), ctx->device);
 
     GGML_UNUSED(params);
 }
@@ -1718,7 +1845,7 @@ static ggml_backend_t ggml_backend_rpc_device_init(ggml_backend_dev_t dev, const
 static ggml_backend_buffer_type_t ggml_backend_rpc_device_get_buffer_type(ggml_backend_dev_t dev) {
     ggml_backend_rpc_device_context * ctx = (ggml_backend_rpc_device_context *)dev->context;
 
-    return ggml_backend_rpc_buffer_type(ctx->endpoint.c_str());
+    return ggml_backend_rpc_buffer_type(ctx->endpoint.c_str(), ctx->device);
 
     GGML_UNUSED(dev);
 }
@@ -1736,7 +1863,7 @@ static bool ggml_backend_rpc_device_supports_buft(ggml_backend_dev_t dev, ggml_b
     }
     ggml_backend_rpc_buffer_type_context * buft_ctx = (ggml_backend_rpc_buffer_type_context *)buft->context;
     ggml_backend_rpc_device_context * dev_ctx = (ggml_backend_rpc_device_context *)dev->context;
-    return buft_ctx->endpoint == dev_ctx->endpoint;
+    return buft_ctx->endpoint == dev_ctx->endpoint && buft_ctx->device == dev_ctx->device;
 }
 
 static const struct ggml_backend_device_i ggml_backend_rpc_device_i = {
@@ -1759,28 +1886,34 @@ static const struct ggml_backend_device_i ggml_backend_rpc_device_i = {
 
 // backend reg interface
 
-static const char * ggml_backend_rpc_reg_get_name(ggml_backend_reg_t reg) {
-    return "RPC";
+struct ggml_backend_rpc_reg_context {
+    std::string                     name;
+    std::vector<ggml_backend_dev_t> devices;
+};
 
-    GGML_UNUSED(reg);
+static const char * ggml_backend_rpc_reg_get_name(ggml_backend_reg_t reg) {
+    ggml_backend_rpc_reg_context * ctx = (ggml_backend_rpc_reg_context *)reg->context;
+    return ctx ? ctx->name.c_str() : "RPC";
 }
 
 static size_t ggml_backend_rpc_reg_get_device_count(ggml_backend_reg_t reg) {
-    return 0;
-
-    GGML_UNUSED(reg);
+    ggml_backend_rpc_reg_context * ctx = (ggml_backend_rpc_reg_context *)reg->context;
+    return ctx ? ctx->devices.size() : 0;
 }
 
 static ggml_backend_dev_t ggml_backend_rpc_reg_get_device(ggml_backend_reg_t reg, size_t index) {
-    GGML_ABORT("The RPC backend does not have enumerated devices - use ggml_backend_add_device instead");
-
-    GGML_UNUSED(reg);
-    GGML_UNUSED(index);
+    ggml_backend_rpc_reg_context * ctx = (ggml_backend_rpc_reg_context *)reg->context;
+    if (ctx == nullptr) {
+        GGML_ABORT("The RPC backend does not have enumerated devices - use ggml_backend_rpc_add_server instead");
+    } else {
+        GGML_ASSERT(index < ctx->devices.size());
+        return ctx->devices[index];
+    }
 }
 
 static void * ggml_backend_rpc_get_proc_address(ggml_backend_reg_t reg, const char * name) {
-    if (std::strcmp(name, "ggml_backend_rpc_add_device") == 0) {
-        return (void *)ggml_backend_rpc_add_device;
+    if (std::strcmp(name, "ggml_backend_rpc_add_server") == 0) {
+        return (void *)ggml_backend_rpc_add_server;
     }
     if (std::strcmp(name, "ggml_backend_rpc_start_server") == 0) {
         return (void *)ggml_backend_rpc_start_server;
@@ -1807,30 +1940,61 @@ ggml_backend_reg_t ggml_backend_rpc_reg(void) {
     return &ggml_backend_rpc_reg;
 }
 
-ggml_backend_dev_t ggml_backend_rpc_add_device(const char * endpoint) {
-    static std::unordered_map<std::string, ggml_backend_dev_t> dev_map;
-
-    static std::mutex mutex;
-    std::lock_guard<std::mutex> lock(mutex);
-
-    if (dev_map.find(endpoint) != dev_map.end()) {
-        return dev_map[endpoint];
-    }
-
-    ggml_backend_rpc_device_context * ctx = new ggml_backend_rpc_device_context {
-        /* .endpoint = */ endpoint,
-        /* .name     = */ "RPC[" + std::string(endpoint) + "]",
-    };
-
-    ggml_backend_dev_t dev = new ggml_backend_device {
-        /* .iface   = */ ggml_backend_rpc_device_i,
-        /* .reg     = */ ggml_backend_rpc_reg(),
-        /* .context = */ ctx,
-    };
-
-    dev_map[endpoint] = dev;
-
-    return dev;
+static uint32_t ggml_backend_rpc_get_device_count(const char * endpoint) {
+    auto sock = get_socket(endpoint);
+    rpc_msg_device_count_rsp response;
+    bool status = send_rpc_cmd(sock, RPC_CMD_DEVICE_COUNT, nullptr, 0, &response, sizeof(response));
+    RPC_STATUS_ASSERT(status);
+    return response.device_count;
 }
 
+static const ggml_backend_reg_i ggml_backend_rpc_reg_interface = {
+    /* .get_name          = */ ggml_backend_rpc_reg_get_name,
+    /* .get_device_count  = */ ggml_backend_rpc_reg_get_device_count,
+    /* .get_device        = */ ggml_backend_rpc_reg_get_device,
+    /* .get_proc_address  = */ ggml_backend_rpc_get_proc_address,
+};
+
+ggml_backend_reg_t ggml_backend_rpc_add_server(const char * endpoint) {
+    static std::unordered_map<std::string, ggml_backend_reg_t> reg_map;
+    static std::mutex mutex;
+    static uint32_t dev_id = 0;
+    std::lock_guard<std::mutex> lock(mutex);
+    if (reg_map.find(endpoint) != reg_map.end()) {
+        return reg_map[endpoint];
+    }
+    uint32_t dev_count = ggml_backend_rpc_get_device_count(endpoint);
+    if (dev_count == 0) {
+        return nullptr;
+    }
+    ggml_backend_rpc_reg_context * ctx = new ggml_backend_rpc_reg_context;
+    ctx->name = "RPC[" + std::string(endpoint) + "]";
+    for (uint32_t ind = 0; ind < dev_count; ind++) {
+        std::string dev_name = "RPC" + std::to_string(dev_id);
+        std::string dev_desc = std::string(endpoint);
+        ggml_backend_rpc_device_context * dev_ctx = new ggml_backend_rpc_device_context {
+            /* .endpoint    = */ endpoint,
+            /* .device      = */ ind,
+            /* .name        = */ dev_name,
+            /* .description = */ dev_desc
+        };
+
+        ggml_backend_dev_t dev = new ggml_backend_device {
+            /* .iface   = */ ggml_backend_rpc_device_i,
+            /* .reg     = */ ggml_backend_rpc_reg(),
+            /* .context = */ dev_ctx,
+        };
+        ctx->devices.push_back(dev);
+        dev_id++;
+    }
+    ggml_backend_reg_t reg = new ggml_backend_reg {
+        /* .api_version = */ GGML_BACKEND_API_VERSION,
+        /* .iface       = */ ggml_backend_rpc_reg_interface,
+        /* .context     = */ ctx
+    };
+    reg_map[endpoint] = reg;
+    return reg;
+}
+
+
 GGML_BACKEND_DL_IMPL(ggml_backend_rpc_reg)

ggml/src/ggml-vulkan/CMakeLists.txt

@@ -1,5 +1,6 @@
 cmake_minimum_required(VERSION 3.19)
 cmake_policy(SET CMP0114 NEW)
+cmake_policy(SET CMP0116 NEW)
 
 find_package(Vulkan COMPONENTS glslc REQUIRED)
 
@@ -54,25 +55,25 @@ if (Vulkan_FOUND)
     # Test all shader extensions
     test_shader_extension_support(
         "GL_KHR_cooperative_matrix"
-        "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders/test_coopmat_support.comp"
+        "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders/feature-tests/coopmat.comp"
         "GGML_VULKAN_COOPMAT_GLSLC_SUPPORT"
     )
 
     test_shader_extension_support(
         "GL_NV_cooperative_matrix2"
-        "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders/test_coopmat2_support.comp"
+        "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders/feature-tests/coopmat2.comp"
         "GGML_VULKAN_COOPMAT2_GLSLC_SUPPORT"
     )
 
     test_shader_extension_support(
         "GL_EXT_integer_dot_product"
-        "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders/test_integer_dot_support.comp"
+        "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders/feature-tests/integer_dot.comp"
         "GGML_VULKAN_INTEGER_DOT_GLSLC_SUPPORT"
     )
 
     test_shader_extension_support(
         "GL_EXT_bfloat16"
-        "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders/test_bfloat16_support.comp"
+        "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders/feature-tests/bfloat16.comp"
         "GGML_VULKAN_BFLOAT16_GLSLC_SUPPORT"
     )
 
@@ -160,7 +161,6 @@ if (Vulkan_FOUND)
     set (_ggml_vk_genshaders_dir "${CMAKE_BINARY_DIR}/$<CONFIG>")
     set (_ggml_vk_genshaders_cmd "${_ggml_vk_genshaders_dir}/vulkan-shaders-gen${_ggml_vk_host_suffix}")
     set (_ggml_vk_header     "${CMAKE_CURRENT_BINARY_DIR}/ggml-vulkan-shaders.hpp")
-    set (_ggml_vk_source     "${CMAKE_CURRENT_BINARY_DIR}/ggml-vulkan-shaders.cpp")
     set (_ggml_vk_input_dir  "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders")
     set (_ggml_vk_output_dir "${CMAKE_CURRENT_BINARY_DIR}/vulkan-shaders.spv")
 
@@ -176,24 +176,35 @@ if (Vulkan_FOUND)
 
     add_custom_command(
         OUTPUT ${_ggml_vk_header}
-               ${_ggml_vk_source}
-
         COMMAND ${_ggml_vk_genshaders_cmd}
-            --glslc      ${Vulkan_GLSLC_EXECUTABLE}
-            --input-dir  ${_ggml_vk_input_dir}
             --output-dir ${_ggml_vk_output_dir}
             --target-hpp ${_ggml_vk_header}
-            --target-cpp ${_ggml_vk_source}
-            --no-clean
-
-        DEPENDS ${_ggml_vk_shader_files}
-                ${_ggml_vk_shaders_gen_sources}
+        DEPENDS ${_ggml_vk_shaders_gen_sources}
                 vulkan-shaders-gen
-
-        COMMENT "Generate vulkan shaders"
+        COMMENT "Generate vulkan shaders header"
     )
+    target_sources(ggml-vulkan PRIVATE ${_ggml_vk_header})
 
-    target_sources(ggml-vulkan PRIVATE ${_ggml_vk_source} ${_ggml_vk_header})
+    foreach (file_full ${_ggml_vk_shader_files})
+        get_filename_component(file ${file_full} NAME)
+        set (_ggml_vk_target_cpp "${CMAKE_CURRENT_BINARY_DIR}/${file}.cpp")
+
+        add_custom_command(
+            OUTPUT  ${_ggml_vk_target_cpp}
+            DEPFILE ${_ggml_vk_target_cpp}.d
+            COMMAND ${_ggml_vk_genshaders_cmd}
+                --glslc      ${Vulkan_GLSLC_EXECUTABLE}
+                --source     ${file_full}
+                --output-dir ${_ggml_vk_output_dir}
+                --target-hpp ${_ggml_vk_header}
+                --target-cpp ${_ggml_vk_target_cpp}
+            DEPENDS ${file_full}
+                    ${_ggml_vk_shaders_gen_sources}
+                    vulkan-shaders-gen
+            COMMENT "Generate vulkan shaders for ${file}"
+        )
+        target_sources(ggml-vulkan PRIVATE ${_ggml_vk_target_cpp})
+    endforeach()
 
 else()
     message(WARNING "Vulkan not found")

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_binary_head.comp"
+#include "types.glsl"
+#include "generic_binary_head.glsl"
 
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 

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

@@ -6,8 +6,8 @@
 #extension GL_KHR_shader_subgroup_basic : enable
 #endif
 
-#include "types.comp"
-#include "generic_binary_head.comp"
+#include "types.glsl"
+#include "generic_binary_head.glsl"
 
 const uint num_threads = 256;
 

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

@@ -2,7 +2,7 @@
 
 #extension GL_EXT_control_flow_attributes : require
 
-#include "types.comp"
+#include "types.glsl"
 
 layout (push_constant) uniform parameter
 {

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 

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

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_control_flow_attributes : enable
 
-#include "types.comp"
+#include "types.glsl"
 
 layout(constant_id = 0) const int BLOCK_SIZE = 1024;
 layout(constant_id = 1) const int BLOCK_SIZE_LOG2 = 10;

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_unary_head.comp"
+#include "types.glsl"
+#include "generic_unary_head.glsl"
 
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_binary_head.comp"
+#include "types.glsl"
+#include "generic_binary_head.glsl"
 
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_unary_head.comp"
+#include "types.glsl"
+#include "generic_unary_head.glsl"
 
 #extension GL_EXT_control_flow_attributes : require
 

ggml/src/ggml-vulkan/vulkan-shaders/conv2d_dw.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "types.comp"
+#include "types.glsl"
 
 layout (push_constant) uniform parameter
 {

ggml/src/ggml-vulkan/vulkan-shaders/conv2d_mm.comp

@@ -11,7 +11,7 @@
 #    extension GL_KHR_shader_subgroup_shuffle : enable
 #endif
 
-#include "types.comp"
+#include "types.glsl"
 
 // shape notation: [dim(N), ..., dim(0)] -- stride(dim(j)) >= stride(dim(i)) if i > j
 layout(binding = 0) readonly buffer A {

ggml/src/ggml-vulkan/vulkan-shaders/conv_transpose_1d.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "types.comp"
+#include "types.glsl"
 
 layout (binding = 0) readonly buffer A {A_TYPE data_a[];};   // src0 - kernel:    [K, Cout, Cin]
 layout (binding = 1) readonly buffer B {B_TYPE data_b[];};   // src1 - input:     [L, Cin]

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_unary_head.comp"
+#include "types.glsl"
+#include "generic_unary_head.glsl"
 
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 

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

@@ -1,8 +1,8 @@
 #version 450
 
-#include "types.comp"
-#include "generic_unary_head.comp"
-#include "dequant_funcs.comp"
+#include "types.glsl"
+#include "generic_unary_head.glsl"
+#include "dequant_funcs.glsl"
 
 #if defined(DATA_A_IQ4_NL) || defined(DATA_A_MXFP4)
 // 16 invocations needed for init_iq_shmem

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "rte.comp"
-#include "types.comp"
+#include "rte.glsl"
+#include "types.glsl"
 
 #if defined(SET_ROWS) && QUANT_K == 1
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
@@ -14,7 +14,7 @@ const uint BLOCK_SIZE = 32;
 layout (binding = 0) readonly buffer S {float data_s[];};
 
 #if defined(SET_ROWS)
-#include "generic_binary_head.comp"
+#include "generic_binary_head.glsl"
 layout (binding = 1) readonly buffer C {B_TYPE data_i[];};
 layout (binding = 2) writeonly buffer Q {A_TYPE data_q[];};
 
@@ -25,7 +25,7 @@ layout (binding = 2) writeonly buffer Q {A_TYPE data_q[];};
 #endif
 
 #else
-#include "generic_unary_head.comp"
+#include "generic_unary_head.glsl"
 layout (binding = 1) writeonly buffer Q {A_TYPE data_q[];};
 #endif
 

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_unary_head.comp"
+#include "types.glsl"
+#include "generic_unary_head.glsl"
 
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 

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

@@ -2,8 +2,8 @@
 
 #extension GL_EXT_control_flow_attributes : enable
 
-#include "types.comp"
-#include "generic_head.comp"
+#include "types.glsl"
+#include "generic_head.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_f32.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs.glsl

@@ -2,7 +2,7 @@
 #extension GL_EXT_shader_explicit_arithmetic_types_int8 : require
 #endif
 
-#include "types.comp"
+#include "types.glsl"
 
 #if defined(A_TYPE_PACKED16)
 layout (binding = 0) readonly buffer A_PACKED16 {A_TYPE_PACKED16 data_a_packed16[];};

ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs_cm2.glsl

@@ -1,5 +1,5 @@
 
-#include "types.comp"
+#include "types.glsl"
 
 layout(buffer_reference, std430, buffer_reference_align = 2) buffer decodeBufQ4_0 {
    block_q4_0_packed16 block;

ggml/src/ggml-vulkan/vulkan-shaders/dequant_head.glsl

@@ -10,4 +10,4 @@ layout (push_constant) uniform parameter
     uint nel;
 } p;
 
-#include "types.comp"
+#include "types.glsl"

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq1_m.comp

@@ -2,7 +2,7 @@
 
 #extension GL_EXT_shader_explicit_arithmetic_types_int16 : require
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq1_s.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq2_s.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq2_xs.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq2_xxs.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq3_s.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq3_xxs.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq4_nl.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq4_xs.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_mxfp4.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q2_k.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 64, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q3_k.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 64, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q4_0.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q4_1.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q4_k.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 32, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q5_0.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q5_1.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q5_k.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 64, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q6_k.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 64, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q8_0.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

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

@@ -10,7 +10,7 @@ layout (push_constant) uniform parameter
     uint n_past;
 } p;
 
-#include "types.comp"
+#include "types.glsl"
 
 layout(local_size_x = 1, local_size_y = 512, local_size_z = 1) in;
 

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_binary_head.comp"
+#include "types.glsl"
+#include "generic_binary_head.glsl"
 
 const uint num_threads = 256;
 

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

@@ -1,8 +1,8 @@
 #version 450
 
-#include "rte.comp"
-#include "generic_head.comp"
-#include "types.comp"
+#include "rte.glsl"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 

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

@@ -8,8 +8,8 @@
 
 #extension GL_KHR_shader_subgroup_shuffle : enable
 
-#include "types.comp"
-#include "flash_attn_base.comp"
+#include "types.glsl"
+#include "flash_attn_base.glsl"
 
 const uint32_t HSK_per_thread = HSK / D_split;
 const uint32_t HSV_per_thread = HSV / D_split;

ggml/src/ggml-vulkan/vulkan-shaders/flash_attn_cm1.comp

@@ -10,8 +10,8 @@
 #extension GL_KHR_memory_scope_semantics : enable
 #extension GL_KHR_cooperative_matrix : enable
 
-#include "types.comp"
-#include "flash_attn_base.comp"
+#include "types.glsl"
+#include "flash_attn_base.glsl"
 
 const uint32_t HSK_per_thread = HSK / D_split;
 const uint32_t HSV_per_thread = HSV / D_split;

ggml/src/ggml-vulkan/vulkan-shaders/flash_attn_cm2.comp

@@ -16,9 +16,9 @@
 #extension GL_KHR_shader_subgroup_vote : enable
 #extension GL_EXT_null_initializer : enable
 
-#include "types.comp"
-#include "dequant_funcs_cm2.comp"
-#include "flash_attn_base.comp"
+#include "types.glsl"
+#include "dequant_funcs_cm2.glsl"
+#include "flash_attn_base.glsl"
 
 layout (binding = 0) readonly buffer Q {uint8_t data_q[];};
 layout (binding = 1) readonly buffer K {uint8_t data_k[];};

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

@@ -1,6 +1,6 @@
 #version 450
 
-#include "glu_head.comp"
+#include "glu_head.glsl"
 
 const float GELU_COEF_A    = 0.044715f;
 const float SQRT_2_OVER_PI = 0.79788456080286535587989211986876f;
@@ -10,4 +10,4 @@ float op(float a, float b) {
     return 0.5f*a*(2.0f - 2.0f / (exp(2 * val) + 1)) * b;
 }
 
-#include "glu_main.comp"
+#include "glu_main.glsl"

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

@@ -1,6 +1,6 @@
 #version 450
 
-#include "glu_head.comp"
+#include "glu_head.glsl"
 
 // based on Abramowitz and Stegun formula 7.1.26 or similar Hastings' approximation
 // ref: https://www.johndcook.com/blog/python_erf/
@@ -24,4 +24,4 @@ float op(float a, float b) {
     return 0.5f * a * (1.0f + erf_approx) * b;
 }
 
-#include "glu_main.comp"
+#include "glu_main.glsl"

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

@@ -1,6 +1,6 @@
 #version 450
 
-#include "glu_head.comp"
+#include "glu_head.glsl"
 
 const float GELU_QUICK_COEF = -1.702f;
 
@@ -8,4 +8,4 @@ float op(float a, float b) {
     return a * (1.0f / (1.0f + exp(GELU_QUICK_COEF * a))) * b;
 }
 
-#include "glu_main.comp"
+#include "glu_main.glsl"

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 

ggml/src/ggml-vulkan/vulkan-shaders/generic_binary_head.glsl

@@ -1,8 +1,8 @@
 #extension GL_EXT_shader_16bit_storage : require
 #extension GL_EXT_control_flow_attributes : require
 
-#include "rte.comp"
-#include "utils.comp"
+#include "rte.glsl"
+#include "utils.glsl"
 
 layout (push_constant) uniform parameter
 {

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_binary_head.comp"
+#include "types.glsl"
+#include "generic_binary_head.glsl"
 
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 

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

@@ -2,9 +2,9 @@
 
 #extension GL_EXT_control_flow_attributes : enable
 
-#include "types.comp"
-#include "generic_binary_head.comp"
-#include "dequant_funcs.comp"
+#include "types.glsl"
+#include "generic_binary_head.glsl"
+#include "dequant_funcs.glsl"
 
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/glu_head.glsl

@@ -1,6 +1,6 @@
 #extension GL_EXT_shader_16bit_storage : require
 
-#include "rte.comp"
+#include "rte.glsl"
 
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 #define BLOCK_SIZE 512

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 

ggml/src/ggml-vulkan/vulkan-shaders/im2col.comp

@@ -3,9 +3,8 @@
 #extension GL_EXT_shader_16bit_storage : require
 #extension GL_EXT_control_flow_attributes : require
 
-#include "rte.comp"
-
-#include "types.comp"
+#include "rte.glsl"
+#include "types.glsl"
 
 layout (push_constant) uniform parameter
 {

ggml/src/ggml-vulkan/vulkan-shaders/im2col_3d.comp

@@ -4,9 +4,8 @@
 #extension GL_EXT_control_flow_attributes : require
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "rte.comp"
-
-#include "types.comp"
+#include "rte.glsl"
+#include "types.glsl"
 
 layout (push_constant) uniform parameter
 {

ggml/src/ggml-vulkan/vulkan-shaders/l2_norm.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 #define BLOCK_SIZE 512

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 

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

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_binary_head.comp"
+#include "types.glsl"
+#include "generic_binary_head.glsl"
 
 const uint num_threads = 256;
 

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

@@ -2,7 +2,7 @@
 
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_base.glsl

@@ -11,7 +11,7 @@
 #define EXPERT_COUNT 8
 #endif
 
-#include "types.comp"
+#include "types.glsl"
 
 #ifndef MMQ
 layout (binding = 0) readonly buffer A {A_TYPE data_a[];};
@@ -32,7 +32,7 @@ layout (binding = 2) writeonly buffer D {D_TYPE data_d[];};
 layout (binding = 3) readonly buffer IDS {int data_ids[];};
 #endif
 
-#include "dequant_funcs.comp"
+#include "dequant_funcs.glsl"
 
 layout (push_constant) uniform parameter
 {

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_iq1_m.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_iq1_s.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_iq2_s.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_iq2_xs.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_iq2_xxs.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_iq3_s.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_iq3_xxs.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q2_k.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q3_k.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q4_k.comp

@@ -2,7 +2,7 @@
 
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q5_k.comp

@@ -2,7 +2,7 @@
 
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q6_k.comp

@@ -2,7 +2,7 @@
 
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

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

@@ -6,13 +6,13 @@
 #define MMQ
 #define B_TYPE block_q8_1_x4
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 
 #define K_PER_ITER 8
 
-#include "mul_mmq_funcs.comp"
+#include "mul_mmq_funcs.glsl"
 
 uint a_offset, b_offset, d_offset;
 

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

@@ -28,7 +28,7 @@
 #extension GL_EXT_shader_explicit_arithmetic_types_int16 : require
 #endif
 
-#include "types.comp"
+#include "types.glsl"
 
 #ifndef LOAD_VEC_A
 #define LOAD_VEC_A 1
@@ -195,7 +195,7 @@ void load_row_ids(uint expert_idx, bool nei0_is_pow2, uint ic) {
 shared ACC_TYPE coopmat_stage[TM * TN * NUM_WARPS];
 #endif
 
-#include "mul_mm_funcs.comp"
+#include "mul_mm_funcs.glsl"
 
 void main() {
 #ifdef NEEDS_INIT_IQ_SHMEM

ggml/src/ggml-vulkan/vulkan-shaders/mul_mm_cm2.comp

@@ -18,8 +18,8 @@
 #extension GL_EXT_bfloat16 : enable
 #endif
 
-#include "types.comp"
-#include "utils.comp"
+#include "types.glsl"
+#include "utils.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 
@@ -71,7 +71,7 @@ layout (binding = 2) writeonly buffer D {D_TYPE data_d[];};
 #if QUANT_K > 1
 #define DECODEFUNCA , dequantFuncA
 
-#include "dequant_funcs_cm2.comp"
+#include "dequant_funcs_cm2.glsl"
 
 #else
 #define DECODEFUNCA

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

@@ -20,7 +20,7 @@
 #extension GL_EXT_shader_explicit_arithmetic_types_int16 : require
 #endif
 
-#include "types.comp"
+#include "types.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 
@@ -110,7 +110,7 @@ shared u16vec2 row_ids[4096];
 shared ACC_TYPE coopmat_stage[TM * TN * NUM_WARPS];
 #endif
 
-#include "mul_mmq_funcs.comp"
+#include "mul_mmq_funcs.glsl"
 
 void main() {
 #ifdef NEEDS_INIT_IQ_SHMEM