ggml : remove old quantization functions (#5942 )

* ggml : remove old quantization functions ggml-ci * ggml : simplify ggml_quantize_chunk ggml-ci * ggml : restrict correctness ggml-ci * ggml : remove hist data from the quantization API ggml-ci * tests : remove hist usage in test-backend-ops ggml-ci * vulkan : remove hist and fix typo
server : clarify some items in the readme (#5957 )
2026-07-14 08:25:55 +02:00 · 2024-03-09 15:53:59 +02:00 · 2024-03-09 15:47:47 +02:00 · 2024-03-09 14:27:58 +02:00 · 2024-03-09 14:17:11 +02:00 · 2024-03-09 13:16:53 +02:00
41 changed files with 3021 additions and 3715 deletions
@@ -199,7 +199,8 @@ if (LLAMA_METAL)
    # get full path to the file
    #add_compile_definitions(GGML_METAL_DIR_KERNELS="${CMAKE_CURRENT_SOURCE_DIR}/")

-    # copy ggml-metal.metal to bin directory
+    # copy ggml-common.h and ggml-metal.metal to bin directory
+    configure_file(ggml-common.h    ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-common.h    COPYONLY)
    configure_file(ggml-metal.metal ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-metal.metal COPYONLY)

    if (LLAMA_METAL_EMBED_LIBRARY)
@@ -201,6 +201,10 @@ ifdef LLAMA_SERVER_VERBOSE
 	MK_CPPFLAGS += -DSERVER_VERBOSE=$(LLAMA_SERVER_VERBOSE)
 endif

+ifdef LLAMA_SERVER_SSL
+	MK_CPPFLAGS += -DCPPHTTPLIB_OPENSSL_SUPPORT
+	MK_LDFLAGS += -lssl -lcrypto
+endif

 ifdef LLAMA_CODE_COVERAGE
 	MK_CXXFLAGS += -fprofile-arcs -ftest-coverage -dumpbase ''
@@ -449,7 +453,7 @@ endif # LLAMA_CUDA_PEER_MAX_BATCH_SIZE
 ifdef LLAMA_CUDA_CCBIN
 	MK_NVCCFLAGS += -ccbin $(LLAMA_CUDA_CCBIN)
 endif
-ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
+ggml-cuda.o: ggml-cuda.cu ggml-cuda.h ggml-common.h
 ifdef JETSON_EOL_MODULE_DETECT
 	$(NVCC) -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I/usr/local/cuda/targets/aarch64-linux/include -std=c++11 -O3 $(NVCCFLAGS) $(CPPFLAGS) -Xcompiler "$(CUDA_CXXFLAGS)" -c $< -o $@
 else
@@ -626,7 +630,7 @@ ggml-alloc.o: ggml-alloc.c ggml.h ggml-alloc.h
 ggml-backend.o: ggml-backend.c ggml.h ggml-backend.h
 	$(CC)  $(CFLAGS)   -c $< -o $@

-ggml-quants.o: ggml-quants.c ggml.h ggml-quants.h
+ggml-quants.o: ggml-quants.c ggml.h ggml-quants.h ggml-common.h
 	$(CC) $(CFLAGS)    -c $< -o $@

 OBJS += ggml-alloc.o ggml-backend.o ggml-quants.o
@@ -10,6 +10,7 @@ Inference of Meta's [LLaMA](https://arxiv.org/abs/2302.13971) model (and others)

 ### Recent API changes

+- [2024 Mar 8] `llama_kv_cache_seq_rm()` returns a `bool` instead of `void`, and new `llama_n_max_seq()` returns the upper limit of acceptable `seq_id` in batches (relevant when dealing with multiple sequences) https://github.com/ggerganov/llama.cpp/pull/5328
 - [2024 Mar 4] Embeddings API updated https://github.com/ggerganov/llama.cpp/pull/5796
 - [2024 Mar 3] `struct llama_context_params` https://github.com/ggerganov/llama.cpp/pull/5849

@@ -110,6 +111,7 @@ Typically finetunes of the base models below are supported as well.
 - [x] [InternLM2](https://huggingface.co/models?search=internlm2)
 - [x] [CodeShell](https://github.com/WisdomShell/codeshell)
 - [x] [Gemma](https://ai.google.dev/gemma)
+- [x] [Mamba](https://github.com/state-spaces/mamba)

 **Multimodal models:**

@@ -1288,6 +1288,7 @@ struct llama_context_params llama_context_params_from_gpt_params(const gpt_param

    cparams.n_ctx             = params.n_ctx;
    cparams.n_batch           = params.n_batch;
+    cparams.n_parallel        = params.n_parallel;
    cparams.n_threads         = params.n_threads;
    cparams.n_threads_batch   = params.n_threads_batch == -1 ? params.n_threads : params.n_threads_batch;
    cparams.seed              = params.seed;
@@ -1851,3 +1852,18 @@ void dump_kv_cache_view_seqs(const llama_kv_cache_view & view, int row_size) {

    printf("\n=== Done dumping\n");
 }
+
+void llama_embd_normalize(const float * inp, float * out, int n) {
+    double sum = 0.0;
+    for (int i = 0; i < n; i++) {
+        sum += inp[i] * inp[i];
+    }
+    sum = sqrt(sum);
+
+    const float norm = sum > 0.0 ? 1.0f / sum : 0.0f;
+
+    for (int i = 0; i < n; i++) {
+        out[i] = inp[i] * norm;
+    }
+}
+
@@ -260,3 +260,10 @@ void dump_kv_cache_view(const llama_kv_cache_view & view, int row_size = 80);

 // Dump the KV cache view showing individual sequences in each cell (long output).
 void dump_kv_cache_view_seqs(const llama_kv_cache_view & view, int row_size = 40);
+
+//
+// Embedding utils
+//
+
+void llama_embd_normalize(const float * inp, float * out, int n);
+
@@ -297,7 +297,7 @@ inline std::string log_filename_generator_impl(LogTriState multilog, const std::
 #ifndef _MSC_VER
    #define LOG(...) LOG_IMPL(__VA_ARGS__, "")
 #else
-    #define LOG(str, ...) LOG_IMPL("%s" str, "", __VA_ARGS__, "")
+    #define LOG(str, ...) LOG_IMPL("%s" str, "", ##__VA_ARGS__, "")
 #endif

 // Main TEE macro.
@@ -311,7 +311,7 @@ inline std::string log_filename_generator_impl(LogTriState multilog, const std::
 #ifndef _MSC_VER
    #define LOG_TEE(...) LOG_TEE_IMPL(__VA_ARGS__, "")
 #else
-    #define LOG_TEE(str, ...) LOG_TEE_IMPL("%s" str, "", __VA_ARGS__, "")
+    #define LOG_TEE(str, ...) LOG_TEE_IMPL("%s" str, "", ##__VA_ARGS__, "")
 #endif

 // LOG macro variants with auto endline.
@@ -319,8 +319,8 @@ inline std::string log_filename_generator_impl(LogTriState multilog, const std::
    #define LOGLN(...) LOG_IMPL(__VA_ARGS__, "\n")
    #define LOG_TEELN(...) LOG_TEE_IMPL(__VA_ARGS__, "\n")
 #else
-    #define LOGLN(str, ...) LOG_IMPL("%s" str, "", __VA_ARGS__, "\n")
-    #define LOG_TEELN(str, ...) LOG_TEE_IMPL("%s" str, "", __VA_ARGS__, "\n")
+    #define LOGLN(str, ...) LOG_IMPL("%s" str, "", ##__VA_ARGS__, "\n")
+    #define LOG_TEELN(str, ...) LOG_TEE_IMPL("%s" str, "", ##__VA_ARGS__, "\n")
 #endif

 // INTERNAL, DO NOT USE
@@ -1847,6 +1847,124 @@ class StarCoder2Model(Model):
    model_arch = gguf.MODEL_ARCH.STARCODER2


+@Model.register("MambaForCausalLM", "MambaLMHeadModel")
+class MambaModel(Model):
+    model_arch = gguf.MODEL_ARCH.MAMBA
+
+    def set_vocab(self):
+        vocab_size = self.hparams["vocab_size"]
+        # Round vocab size to next multiple of 8
+        pad_vocab = self.hparams.get("pad_vocab_size_multiple", 8)
+        # pad using ceiling division
+        # ref: https://stackoverflow.com/a/17511341/22827863
+        vocab_size = -(vocab_size // -pad_vocab) * pad_vocab
+        self.hparams["vocab_size"] = vocab_size
+
+        if (self.dir_model / "tokenizer.json").is_file():
+            self._set_vocab_gpt2()
+        else:
+            # Use the GPT-NeoX tokenizer when no tokenizer files are present
+            tokenizer_path = Path(sys.path[0]) / "models" / "ggml-vocab-gpt-neox.gguf"
+            print(f"Using tokenizer from '{os.path.relpath(tokenizer_path, os.getcwd())}'")
+            neox_reader = gguf.GGUFReader(tokenizer_path, "r")
+
+            field = neox_reader.get_field(gguf.Keys.Tokenizer.MODEL)
+            self.gguf_writer.add_tokenizer_model(bytes(field.parts[-1]))
+            field = neox_reader.get_field(gguf.Keys.Tokenizer.LIST)
+            self.gguf_writer.add_token_list([bytes(field.parts[i]) for i in field.data][:vocab_size])
+            field = neox_reader.get_field(gguf.Keys.Tokenizer.TOKEN_TYPE)
+            self.gguf_writer.add_token_types([field.parts[i].tolist()[0] for i in field.data][:vocab_size])
+            field = neox_reader.get_field(gguf.Keys.Tokenizer.MERGES)
+            self.gguf_writer.add_token_merges([bytes(field.parts[i]) for i in field.data])
+            field = neox_reader.get_field(gguf.Keys.Tokenizer.BOS_ID)
+            self.gguf_writer.add_bos_token_id(field.parts[-1].tolist()[0])
+            field = neox_reader.get_field(gguf.Keys.Tokenizer.EOS_ID)
+            self.gguf_writer.add_eos_token_id(field.parts[-1].tolist()[0])
+            field = neox_reader.get_field(gguf.Keys.Tokenizer.UNK_ID)
+            self.gguf_writer.add_unk_token_id(field.parts[-1].tolist()[0])
+
+    def set_gguf_parameters(self):
+        d_model = self.find_hparam(["hidden_size", "d_model"])
+        d_conv  = self.find_hparam(["conv_kernel", "d_conv"], optional=True) or 4
+        d_inner = self.find_hparam(["intermediate_size", "d_inner"], optional=True) or 2 * d_model
+        d_state = self.find_hparam(["state_size", "d_state"], optional=True) or 16
+        # ceiling division
+        # ref: https://stackoverflow.com/a/17511341/22827863
+        # ref: https://github.com/state-spaces/mamba/blob/ce59daea3a090d011d6476c6e5b97f6d58ddad8b/mamba_ssm/modules/mamba_simple.py#L58
+        dt_rank = self.find_hparam(["time_step_rank", "dt_rank"], optional=True) or -(d_model // -16)
+        rms_norm_eps = self.find_hparam(["layer_norm_epsilon", "rms_norm_eps"], optional=True) or 1e-5
+
+        # Fail early for models which don't have a block expansion factor of 2
+        assert d_inner == 2 * d_model
+
+        self.gguf_writer.add_name(self.dir_model.name)
+        self.gguf_writer.add_context_length(2**20) # arbitrary value; for those who use the default
+        self.gguf_writer.add_embedding_length(d_model)
+        self.gguf_writer.add_feed_forward_length(0) # unused, but seemingly required when loading
+        self.gguf_writer.add_head_count(0) # unused, but seemingly required when loading
+        self.gguf_writer.add_block_count(self.hparams["n_layer"])
+        self.gguf_writer.add_ssm_conv_kernel(d_conv)
+        self.gguf_writer.add_ssm_inner_size(d_inner)
+        self.gguf_writer.add_ssm_state_size(d_state)
+        self.gguf_writer.add_ssm_time_step_rank(dt_rank)
+        self.gguf_writer.add_layer_norm_rms_eps(rms_norm_eps)
+        self.gguf_writer.add_file_type(self.ftype)
+
+    def write_tensors(self):
+        block_count = self.hparams["n_layer"]
+        tensor_map = gguf.get_tensor_name_map(self.model_arch, block_count)
+
+        tok_embd = None
+        tok_embd_name = gguf.TENSOR_NAMES[gguf.MODEL_TENSOR.TOKEN_EMBD] + ".weight"
+        output_name   = gguf.TENSOR_NAMES[gguf.MODEL_TENSOR.OUTPUT]     + ".weight"
+
+        for name, data_torch in self.get_tensors():
+            old_dtype = data_torch.dtype
+
+            # convert any unsupported data types to float32
+            if data_torch.dtype not in (torch.float16, torch.float32):
+                data_torch = data_torch.to(torch.float32)
+
+            # map tensor names
+            new_name = tensor_map.get_name(name, try_suffixes=(".weight", ".bias"))
+            if new_name is None:
+                print(f"Can not map tensor {name!r}")
+                sys.exit()
+
+            if name.endswith(".A_log"):
+                print("A_log --> A ==> " + new_name)
+                data_torch = -torch.exp(data_torch)
+
+            # assuming token_embd.weight is seen before output.weight
+            if tok_embd is not None and new_name == output_name:
+                if torch.equal(tok_embd, data_torch):
+                    print(f"{output_name} is equivalent to {tok_embd_name}, omitting")
+                    continue
+            if new_name == tok_embd_name:
+                tok_embd = data_torch
+
+            data = data_torch.squeeze().numpy()
+
+            n_dims = len(data.shape)
+            data_dtype = data.dtype
+
+            # if f32 desired, convert any float16 to float32
+            if self.ftype == 0 and data_dtype == np.float16:
+                data = data.astype(np.float32)
+
+            # TODO: Why cant we use these float16 as-is? There should be not reason to store float16 as float32
+            if self.ftype == 1 and data_dtype == np.float16 and n_dims == 1:
+                data = data.astype(np.float32)
+
+            # if f16 desired, convert big float32 2-dim weight tensors to float16
+            if self.ftype == 1 and data_dtype == np.float32 and new_name.removesuffix(".weight").endswith((".ssm_in", ".ssm_out", "token_embd", "output")) and n_dims == 2:
+                data = data.astype(np.float16)
+
+            print(f"{new_name}, n_dims = {n_dims}, {old_dtype} --> {data.dtype}")
+
+            self.gguf_writer.add_tensor(new_name, data)
+
+
 ###### CONVERSION LOGIC ######


@@ -105,6 +105,9 @@ int main(int argc, char ** argv) {
    ctx_params.n_threads       = params.n_threads;
    ctx_params.n_threads_batch = params.n_threads_batch == -1 ? params.n_threads : params.n_threads_batch;

+    // ensure enough sequences are available
+    ctx_params.n_parallel = *std::max_element(n_pl.begin(), n_pl.end());
+
    llama_context * ctx = llama_new_context_with_model(model, ctx_params);

    if (ctx == NULL) {
@@ -174,10 +177,10 @@ int main(int argc, char ** argv) {

                llama_batch_clear(batch);

-                const int n_tokens = is_pp_shared ? pp : pl*pp;
-
-                for (int i = 0; i < n_tokens; ++i) {
-                    llama_batch_add(batch, 0, i, { 0 }, false);
+                for (int i = 0; i < pp; ++i) {
+                    for (int j = 0; j < (is_pp_shared ? 1 : pl); ++j) {
+                        llama_batch_add(batch, 0, i, { j }, false);
+                    }
                }
                batch.logits[batch.n_tokens - 1] = true;

@@ -192,7 +195,7 @@ int main(int argc, char ** argv) {

                if (is_pp_shared) {
                    for (int32_t i = 1; i < pl; ++i) {
-                        llama_kv_cache_seq_cp(ctx, 0, i, 0, pp);
+                        llama_kv_cache_seq_cp(ctx, 0, i, -1, -1);
                    }
                }

@@ -80,6 +80,7 @@ int main(int argc, char ** argv) {
    ctx_params.seed  = 1234;
    ctx_params.n_ctx = n_kv_req;
    ctx_params.n_batch = std::max(n_len, n_parallel);
+    ctx_params.n_parallel      = n_parallel;
    ctx_params.n_threads       = params.n_threads;
    ctx_params.n_threads_batch = params.n_threads_batch == -1 ? params.n_threads : params.n_threads_batch;

@@ -132,7 +133,7 @@ int main(int argc, char ** argv) {
    // assign the system KV cache to all parallel sequences
    // this way, the parallel sequences will "reuse" the prompt tokens without having to copy them
    for (int32_t i = 1; i < n_parallel; ++i) {
-        llama_kv_cache_seq_cp(ctx, 0, i, 0, batch.n_tokens);
+        llama_kv_cache_seq_cp(ctx, 0, i, -1, -1);
    }

    if (n_parallel > 1) {
@@ -189,12 +189,10 @@ int main(int argc, char ** argv)  {

    int32_t nelements = sizex*sizey;

-    std::vector<int64_t> hist_cur(1 << 4, 0);
-
    // Set up a the benchmark matrices
    // printf("Creating new tensor q11 & Running quantize\n");
    struct ggml_tensor * q11 = ggml_new_tensor_2d(ctx, qtype, sizex, sizey);
-    ggml_quantize_chunk(qtype, (const float *) m11->data, q11->data, 0, nelements/m11->ne[0], m11->ne[0], hist_cur.data(), nullptr);
+    ggml_quantize_chunk(qtype, (const float *) m11->data, q11->data, 0, nelements/m11->ne[0], m11->ne[0], nullptr);

    // Set up a the compute graph
    // printf("Creating new tensor q31\n");
@@ -207,7 +205,7 @@ int main(int argc, char ** argv)  {
    // Set up a second graph computation to make sure we override the CPU cache lines
    // printf("Creating new tensor q12 & Running quantize\n");
    struct ggml_tensor * q12 = ggml_new_tensor_2d(ctx, qtype, sizex, sizey);
-    ggml_quantize_chunk(qtype, (const float *) m12->data, q12->data, 0, nelements/m12->ne[0], m12->ne[0], hist_cur.data(), nullptr);
+    ggml_quantize_chunk(qtype, (const float *) m12->data, q12->data, 0, nelements/m12->ne[0], m12->ne[0], nullptr);

    // printf("Creating new tensor q32\n");
    struct ggml_tensor * q32 = ggml_mul_mat(ctx, q12, m2);
@@ -23,17 +23,6 @@ static void batch_add_seq(llama_batch & batch, const std::vector<int32_t> & toke
    }
 }

-static void normalize(const float * vec, float * out, int n) {
-    float norm = 0;
-    for (int i = 0; i < n; i++) {
-        norm += vec[i] * vec[i];
-    }
-    norm = sqrt(norm);
-    for (int i = 0; i < n; i++) {
-        out[i] = vec[i] / norm;
-    }
-}
-
 static void batch_decode(llama_context * ctx, llama_batch & batch, float * output, int n_seq, int n_embd) {
    // clear previous kv_cache values (irrelevant for embeddings)
    llama_kv_cache_clear(ctx);
@@ -44,7 +33,6 @@ static void batch_decode(llama_context * ctx, llama_batch & batch, float * outpu
        fprintf(stderr, "%s : failed to decode\n", __func__);
    }

-    // normalize on copy
    for (int i = 0; i < batch.n_tokens; i++) {
        if (!batch.logits[i]) {
            continue;
@@ -61,7 +49,7 @@ static void batch_decode(llama_context * ctx, llama_batch & batch, float * outpu
        }

        float * out = output + batch.seq_id[i][0] * n_embd;
-        normalize(embd, out, n_embd);
+        llama_embd_normalize(embd, out, n_embd);
    }
 }

@@ -173,6 +173,7 @@ struct cmd_params {
    std::vector<bool> no_kv_offload;
    std::vector<std::vector<float>> tensor_split;
    std::vector<bool> use_mmap;
+    std::vector<bool> embeddings;
    int reps;
    bool verbose;
    output_formats output_format;
@@ -192,6 +193,7 @@ static const cmd_params cmd_params_defaults = {
    /* no_kv_offload */ {false},
    /* tensor_split  */ {std::vector<float>(llama_max_devices(), 0.0f)},
    /* use_mmap      */ {true},
+    /* embeddings    */ {false},
    /* reps          */ 5,
    /* verbose       */ false,
    /* output_format */ MARKDOWN
@@ -214,6 +216,7 @@ static void print_usage(int /* argc */, char ** argv) {
    printf("  -mg, --main-gpu <i>                 (default: %s)\n", join(cmd_params_defaults.main_gpu, ",").c_str());
    printf("  -nkvo, --no-kv-offload <0|1>        (default: %s)\n", join(cmd_params_defaults.no_kv_offload, ",").c_str());
    printf("  -mmp, --mmap <0|1>                  (default: %s)\n", join(cmd_params_defaults.use_mmap, ",").c_str());
+    printf("  -embd, --embeddings <0|1>           (default: %s)\n", join(cmd_params_defaults.embeddings, ",").c_str());
    printf("  -ts, --tensor_split <ts0/ts1/..>    (default: 0)\n");
    printf("  -r, --repetitions <n>               (default: %d)\n", cmd_params_defaults.reps);
    printf("  -o, --output <csv|json|md|sql>      (default: %s)\n", output_format_str(cmd_params_defaults.output_format));
@@ -382,6 +385,13 @@ static cmd_params parse_cmd_params(int argc, char ** argv) {
            }
            auto p = split<bool>(argv[i], split_delim);
            params.use_mmap.insert(params.use_mmap.end(), p.begin(), p.end());
+        } else if (arg == "-embd" || arg == "--embeddings") {
+            if (++i >= argc) {
+                invalid_param = true;
+                break;
+            }
+            auto p = split<bool>(argv[i], split_delim);
+            params.embeddings.insert(params.embeddings.end(), p.begin(), p.end());
        } else if (arg == "-ts" || arg == "--tensor-split") {
            if (++i >= argc) {
                invalid_param = true;
@@ -453,6 +463,7 @@ static cmd_params parse_cmd_params(int argc, char ** argv) {
    if (params.no_kv_offload.empty()){ params.no_kv_offload = cmd_params_defaults.no_kv_offload; }
    if (params.tensor_split.empty()) { params.tensor_split = cmd_params_defaults.tensor_split; }
    if (params.use_mmap.empty())     { params.use_mmap = cmd_params_defaults.use_mmap; }
+    if (params.embeddings.empty())   { params.embeddings = cmd_params_defaults.embeddings; }
    if (params.n_threads.empty())    { params.n_threads = cmd_params_defaults.n_threads; }

    return params;
@@ -472,6 +483,7 @@ struct cmd_params_instance {
    bool no_kv_offload;
    std::vector<float> tensor_split;
    bool use_mmap;
+    bool embeddings;

    llama_model_params to_llama_mparams() const {
        llama_model_params mparams = llama_model_default_params();
@@ -502,6 +514,7 @@ struct cmd_params_instance {
        cparams.type_k = type_k;
        cparams.type_v = type_v;
        cparams.offload_kqv = !no_kv_offload;
+        cparams.embeddings = embeddings;

        return cparams;
    }
@@ -517,6 +530,7 @@ static std::vector<cmd_params_instance> get_cmd_params_instances(const cmd_param
    for (const auto & mg : params.main_gpu)
    for (const auto & ts : params.tensor_split)
    for (const auto & mmp : params.use_mmap)
+    for (const auto & embd : params.embeddings)
    for (const auto & nb : params.n_batch)
    for (const auto & tk : params.type_k)
    for (const auto & tv : params.type_v)
@@ -540,6 +554,7 @@ static std::vector<cmd_params_instance> get_cmd_params_instances(const cmd_param
                /* .no_kv_offload= */ nkvo,
                /* .tensor_split = */ ts,
                /* .use_mmap     = */ mmp,
+                /* .embeddings   = */ embd,
            };
            instances.push_back(instance);
        }
@@ -562,6 +577,7 @@ static std::vector<cmd_params_instance> get_cmd_params_instances(const cmd_param
                /* .no_kv_offload= */ nkvo,
                /* .tensor_split = */ ts,
                /* .use_mmap     = */ mmp,
+                /* .embeddings   = */ embd,
            };
            instances.push_back(instance);
        }
@@ -597,6 +613,7 @@ struct test {
    bool no_kv_offload;
    std::vector<float> tensor_split;
    bool use_mmap;
+    bool embeddings;
    int n_prompt;
    int n_gen;
    std::string test_time;
@@ -619,6 +636,7 @@ struct test {
        no_kv_offload = inst.no_kv_offload;
        tensor_split = inst.tensor_split;
        use_mmap = inst.use_mmap;
+        embeddings = inst.embeddings;
        n_prompt = inst.n_prompt;
        n_gen = inst.n_gen;
        // RFC 3339 date-time format
@@ -690,7 +708,7 @@ struct test {
            "n_batch", "n_threads", "type_k", "type_v",
            "n_gpu_layers", "split_mode",
            "main_gpu", "no_kv_offload",
-            "tensor_split", "use_mmap",
+            "tensor_split", "use_mmap", "embeddings",
            "n_prompt", "n_gen", "test_time",
            "avg_ns", "stddev_ns",
            "avg_ts", "stddev_ts"
@@ -710,7 +728,7 @@ struct test {
        }
        if (field == "cuda" || field == "opencl"  || field == "vulkan" || field == "kompute" || field == "metal" ||
            field == "gpu_blas" || field == "blas" || field == "sycl" ||field == "f16_kv" || field == "no_kv_offload" ||
-            field == "use_mmap") {
+            field == "use_mmap" || field == "embeddings") {
            return BOOL;
        }
        if (field == "avg_ts" || field == "stddev_ts") {
@@ -744,7 +762,7 @@ struct test {
            std::to_string(n_batch), std::to_string(n_threads), ggml_type_name(type_k), ggml_type_name(type_v),
            std::to_string(n_gpu_layers), split_mode_str(split_mode),
            std::to_string(main_gpu), std::to_string(no_kv_offload),
-            tensor_split_str, std::to_string(use_mmap),
+            tensor_split_str, std::to_string(use_mmap), std::to_string(embeddings),
            std::to_string(n_prompt), std::to_string(n_gen), test_time,
            std::to_string(avg_ns()), std::to_string(stdev_ns()),
            std::to_string(avg_ts()), std::to_string(stdev_ts())
@@ -914,6 +932,9 @@ struct markdown_printer : public printer {
        if (field == "use_mmap") {
            return "mmap";
        }
+        if (field == "embeddings") {
+            return "embd";
+        }
        if (field == "tensor_split") {
            return "ts";
        }
@@ -957,6 +978,9 @@ struct markdown_printer : public printer {
        if (params.use_mmap.size() > 1 || params.use_mmap != cmd_params_defaults.use_mmap) {
            fields.emplace_back("use_mmap");
        }
+        if (params.embeddings.size() > 1 || params.embeddings != cmd_params_defaults.embeddings) {
+            fields.emplace_back("embeddings");
+        }
        fields.emplace_back("test");
        fields.emplace_back("t/s");

@@ -1862,7 +1862,6 @@ bool clip_model_quantize(const char * fname_inp, const char * fname_out, const i

    std::vector<uint8_t> work(512);
    std::vector<float> conv_buf(512);
-    std::vector<int64_t> hist_all(1 << 4, 0);
    size_t total_size_org = 0;
    size_t total_size_new = 0;

@@ -1917,48 +1916,7 @@ bool clip_model_quantize(const char * fname_inp, const char * fname_out, const i
            }
            new_data = work.data();

-            std::vector<int64_t> hist_cur(1 << 4, 0);
-
-            switch (new_type) {
-                case GGML_TYPE_Q4_0: {
-                    new_size = ggml_quantize_q4_0(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q4_1: {
-                    new_size = ggml_quantize_q4_1(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q5_0: {
-                    new_size = ggml_quantize_q5_0(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q5_1: {
-                    new_size = ggml_quantize_q5_1(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q8_0: {
-                    new_size = ggml_quantize_q8_0(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q2_K: {
-                    new_size = ggml_quantize_q2_K(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q3_K: {
-                    new_size = ggml_quantize_q3_K(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q4_K: {
-                    new_size = ggml_quantize_q4_K(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q5_K: {
-                    new_size = ggml_quantize_q5_K(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q6_K: {
-                    new_size = ggml_quantize_q6_K(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                default: {
-                    fprintf(stderr, "%s: unsupported quantization type %d\n", __func__, new_type);
-                    return false;
-                }
-            }
-
-            for (size_t j = 0; j < hist_cur.size(); ++j) {
-                hist_all[j] += hist_cur[j];
-            }
+            new_size = ggml_quantize_chunk(new_type, f32_data, new_data, 0, n_elms/cur->ne[0], cur->ne[0], nullptr);
        } else {
            new_type = cur->type;
            new_data = cur->data;
@@ -1993,17 +1951,6 @@ bool clip_model_quantize(const char * fname_inp, const char * fname_out, const i
    {
        printf("%s: original  size = %8.2f MB\n", __func__, total_size_org / 1024.0 / 1024.0);
        printf("%s: quantized size = %8.2f MB\n", __func__, total_size_new / 1024.0 / 1024.0);
-
-        int64_t sum_all = 0;
-        for (size_t i = 0; i < hist_all.size(); ++i) {
-            sum_all += hist_all[i];
-        }
-
-        printf("%s: hist: ", __func__);
-        for (size_t i = 0; i < hist_all.size(); ++i) {
-            printf("%5.3f ", hist_all[i] / (float)sum_all);
-        }
-        printf("\n");
    }

    return true;
@@ -107,6 +107,9 @@ int main(int argc, char ** argv) {
    // number of simultaneous "clients" to simulate
    const int32_t n_clients = params.n_parallel;

+    // dedicate one sequence to the system prompt
+    params.n_parallel += 1;
+
    // requests to simulate
    const int32_t n_seq = params.n_sequences;

@@ -196,8 +199,8 @@ int main(int argc, char ** argv) {
        }

        // assign the system KV cache to all parallel sequences
-        for (int32_t i = 1; i < n_clients; ++i) {
-            llama_kv_cache_seq_cp(ctx, 0, i, 0, n_tokens_system);
+        for (int32_t i = 1; i <= n_clients; ++i) {
+            llama_kv_cache_seq_cp(ctx, 0, i, -1, -1);
        }

        LOG_TEE("\n");
@@ -221,15 +224,17 @@ int main(int argc, char ** argv) {

            client.i_batch = batch.n_tokens;

-            llama_batch_add(batch, client.sampled, n_tokens_system + client.n_prompt + client.n_decoded, { client.id }, true);
+            llama_batch_add(batch, client.sampled, n_tokens_system + client.n_prompt + client.n_decoded, { client.id + 1 }, true);

            client.n_decoded += 1;
        }

        if (batch.n_tokens == 0) {
            // all sequences have ended - clear the entire KV cache
-            for (int i = 0; i < n_clients; ++i) {
-                llama_kv_cache_seq_rm(ctx, i, n_tokens_system, -1);
+            for (int i = 1; i <= n_clients; ++i) {
+                llama_kv_cache_seq_rm(ctx, i, -1, -1);
+                // but keep the system prompt
+                llama_kv_cache_seq_cp(ctx, 0, i, -1, -1);
            }

            LOG_TEE("%s: clearing the KV cache\n", __func__);
@@ -255,7 +260,7 @@ int main(int argc, char ** argv) {
                    tokens_prompt = ::llama_tokenize(ctx, client.prompt, false);

                    for (size_t i = 0; i < tokens_prompt.size(); ++i) {
-                        llama_batch_add(batch, tokens_prompt[i], i + n_tokens_system, { client.id }, false);
+                        llama_batch_add(batch, tokens_prompt[i], i + n_tokens_system, { client.id + 1 }, false);
                    }

                    // extract the logits only for the last token
@@ -366,7 +371,8 @@ int main(int argc, char ** argv) {
                    }

                    // delete only the generated part of the sequence, i.e. keep the system prompt in the cache
-                    llama_kv_cache_seq_rm(ctx, client.id, n_tokens_system, -1);
+                    llama_kv_cache_seq_rm(ctx, client.id + 1, -1, -1);
+                    llama_kv_cache_seq_cp(ctx, 0, client.id + 1, -1, -1);

                    const auto t_main_end = ggml_time_us();

@@ -809,7 +809,7 @@ static void hellaswag_score(llama_context * ctx, const gpt_params & params) {
    const int n_batch = params.n_batch;

    const int max_tasks_per_batch = 32;
-    const int max_seq = 4*max_tasks_per_batch;
+    const int max_seq = std::min(4*max_tasks_per_batch, (int) llama_n_max_seq(ctx));

    llama_batch batch = llama_batch_init(n_ctx, 0, max_seq);

@@ -1086,7 +1086,7 @@ static void winogrande_score(llama_context * ctx, const gpt_params & params) {
    const int n_batch = params.n_batch;

    const int max_tasks_per_batch = 128;
-    const int max_seq = 2*max_tasks_per_batch;
+    const int max_seq = std::min(2*max_tasks_per_batch, (int) llama_n_max_seq(ctx));

    llama_batch batch = llama_batch_init(n_ctx, 0, max_seq);

@@ -1438,7 +1438,7 @@ static void multiple_choice_score(llama_context * ctx, const gpt_params & params
    const int n_batch = params.n_batch;

    const int max_tasks_per_batch = 32;
-    const int max_seq = 4*max_tasks_per_batch;
+    const int max_seq = std::min(4*max_tasks_per_batch, (int) llama_n_max_seq(ctx));

    llama_batch batch = llama_batch_init(n_ctx, 0, max_seq);

@@ -1815,6 +1815,9 @@ int main(int argc, char ** argv) {
    llama_model * model;
    llama_context * ctx;

+    // ensure there's at least enough seq_ids for HellaSwag
+    params.n_parallel = std::max(4, params.n_parallel);
+
    // load the model and apply lora adapter, if any
    std::tie(model, ctx) = llama_init_from_gpt_params(params);
    if (model == NULL) {
@@ -1,5 +1,6 @@
 set(TARGET server)
 option(LLAMA_SERVER_VERBOSE "Build verbose logging option for Server" ON)
+option(LLAMA_SERVER_SSL "Build SSL support for the server" OFF)
 include_directories(${CMAKE_CURRENT_SOURCE_DIR})
 add_executable(${TARGET} server.cpp utils.hpp json.hpp httplib.h)
 install(TARGETS ${TARGET} RUNTIME)
@@ -7,6 +8,11 @@ target_compile_definitions(${TARGET} PRIVATE
    SERVER_VERBOSE=$<BOOL:${LLAMA_SERVER_VERBOSE}>
 )
 target_link_libraries(${TARGET} PRIVATE common ${CMAKE_THREAD_LIBS_INIT})
+if (LLAMA_SERVER_SSL)
+    find_package(OpenSSL REQUIRED)
+    target_link_libraries(${TARGET} PRIVATE OpenSSL::SSL OpenSSL::Crypto)
+    target_compile_definitions(${TARGET} PRIVATE CPPHTTPLIB_OPENSSL_SUPPORT)
+endif()
 if (WIN32)
    TARGET_LINK_LIBRARIES(${TARGET} PRIVATE ws2_32)
 endif()
@@ -42,7 +42,7 @@ see https://github.com/ggerganov/llama.cpp/issues/1437
 - `-to N`, `--timeout N`: Server read/write timeout in seconds. Default `600`.
 - `--host`: Set the hostname or ip address to listen. Default `127.0.0.1`.
 - `--port`: Set the port to listen. Default: `8080`.
- `--path`: path from which to serve static files (default examples/server/public)
+- `--path`: path from which to serve static files (default: disabled)
 - `--api-key`: Set an api key for request authorization. By default the server responds to every request. With an api key set, the requests must have the Authorization header set with the api key as Bearer token. May be used multiple times to enable multiple valid keys.
 - `--api-key-file`: path to file containing api keys delimited by new lines. If set, requests must include one of the keys for access. May be used in conjunction with `--api-key`'s.
 - `--embedding`: Enable embedding extraction, Default: disabled.
@@ -59,6 +59,10 @@ see https://github.com/ggerganov/llama.cpp/issues/1437
 - `--log-disable`: Output logs to stdout only, default: enabled.
 - `--log-format FORMAT`: Define the log output to FORMAT: json or text (default: json)

+**If compiled with `LLAMA_SERVER_SSL=ON`**
+- `--ssl-key-file FNAME`: path to file a PEM-encoded SSL private key
+- `--ssl-cert-file FNAME`: path to file a PEM-encoded SSL certificate
+
 ## Build

 server is build alongside everything else from the root of the project
@@ -75,6 +79,28 @@ server is build alongside everything else from the root of the project
  cmake --build . --config Release
  ```

+## Build with SSL
+
+server can also be built with SSL support using OpenSSL 3
+
+- Using `make`:
+
+  ```bash
+  # NOTE: For non-system openssl, use the following:
+  #   CXXFLAGS="-I /path/to/openssl/include"
+  #   LDFLAGS="-L /path/to/openssl/lib"
+  make LLAMA_SERVER_SSL=true server
+  ```
+
+- Using `CMake`:
+
+  ```bash
+  mkdir build
+  cd build
+  cmake .. -DLLAMA_SERVER_SSL=ON
+  make server
+  ```
+
 ## Quick Start

 To get started right away, run the following command, making sure to use the correct path for the model you have:
@@ -169,7 +195,11 @@ node index.js

    *Options:*

-    `prompt`: Provide the prompt for this completion as a string or as an array of strings or numbers representing tokens. Internally, the prompt is compared to the previous completion and only the "unseen" suffix is evaluated. If the prompt is a string or an array with the first element given as a string, a `bos` token is inserted in the front like `main` does.
+    `prompt`: Provide the prompt for this completion as a string or as an array of strings or numbers representing tokens. Internally, if `cache_prompt` is `true`, the prompt is compared to the previous completion and only the "unseen" suffix is evaluated. A `BOS` token is inserted at the start, if all of the following conditions are true:
+
+      - The prompt is a string or an array with the first element given as a string
+      - The model's `tokenizer.ggml.add_bos_token` metadata is `true`
+      - The system prompt is empty

    `temperature`: Adjust the randomness of the generated text (default: 0.8).

@@ -282,7 +312,7 @@ Notice that each `probs` is an array of length `n_probs`.

    `content`: Set the text to tokenize.

-    Note that the special `BOS` token is not added in front of the text and also a space character is not inserted automatically as it is for `/completion`.
+    Note that a special `BOS` token is never inserted.

 - **POST** `/detokenize`: Convert tokens to text.

@@ -532,7 +562,7 @@ The HTTP server supports OAI-like API

 ### Extending or building alternative Web Front End

-The default location for the static files is `examples/server/public`. You can extend the front end by running the server binary with `--path` set to `./your-directory` and importing `/completion.js` to get access to the llamaComplete() method.
+You can extend the front end by running the server binary with `--path` set to `./your-directory` and importing `/completion.js` to get access to the llamaComplete() method.

 Read the documentation in `/completion.js` to see convenient ways to access llama.

@@ -6,8 +6,8 @@ Feature: Parallel
    Given a server listening on localhost:8080
    And   a model file tinyllamas/stories260K.gguf from HF repo ggml-org/models
    And   42 as server seed
-    And   512 as batch size
-    And   64 KV cache size
+    And   128 as batch size
+    And   256 KV cache size
    And   2 slots
    And   continuous batching
    Then  the server is starting
@@ -76,6 +76,7 @@ Feature: Parallel
      | disabled  | 128       |
      | enabled   | 64        |

+
  Scenario:  Multi users with total number of tokens to predict exceeds the KV Cache size #3969
    Given a prompt:
      """
@@ -39,8 +39,9 @@ Feature: Security


  Scenario Outline: CORS Options
-    When an OPTIONS request is sent from <origin>
-    Then CORS header <cors_header> is set to <cors_header_value>
+    Given a user api key llama.cpp
+    When  an OPTIONS request is sent from <origin>
+    Then  CORS header <cors_header> is set to <cors_header_value>

    Examples: Headers
      | origin          | cors_header                      | cors_header_value |
@@ -10,11 +10,10 @@ Feature: llama.cpp server
      # KV Cache corresponds to the total amount of tokens
      # that can be stored across all independent sequences: #4130
      # see --ctx-size and #5568
-    And   32 KV cache size
-    And   512 as batch size
-    And   1 slots
-    And   embeddings extraction
-    And   32 server max tokens to predict
+    And   256 KV cache size
+    And   32 as batch size
+    And   2 slots
+    And   64 server max tokens to predict
    And   prometheus compatible metrics exposed
    Then  the server is starting
    Then  the server is healthy
@@ -23,17 +22,35 @@ Feature: llama.cpp server
    Then the server is ready
    And  all slots are idle

+
  Scenario Outline: Completion
    Given a prompt <prompt>
    And   <n_predict> max tokens to predict
    And   a completion request with no api error
    Then  <n_predicted> tokens are predicted matching <re_content>
+    And   the completion is <truncated> truncated
+    And   <n_prompt> prompt tokens are processed
    And   prometheus metrics are exposed
+    And   metric llamacpp:tokens_predicted is <n_predicted>

    Examples: Prompts
-      | prompt                           | n_predict | re_content                       | n_predicted |
-      | I believe the meaning of life is | 8         | (read\|going)+                   | 8           |
-      | Write a joke about AI            | 64        | (park\|friends\|scared\|always)+ | 32          |
+      | prompt                                                                    | n_predict | re_content                    | n_prompt | n_predicted | truncated |
+      | I believe the meaning of life is                                          | 8         | (read\|going)+                | 18       | 8           | not       |
+      | Write a joke about AI from a very long prompt which will not be truncated | 256       | (princesses\|everyone\|kids)+ | 46       | 64          | not       |
+
+  Scenario: Completion prompt truncated
+    Given a prompt:
+    """
+    Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
+    Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat.
+    Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.
+    Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
+    """
+    And   a completion request with no api error
+    Then  64 tokens are predicted matching fun|Annaks|popcorns
+    And   the completion is  truncated
+    And   109 prompt tokens are processed
+

  Scenario Outline: OAI Compatibility
    Given a model <model>
@@ -43,11 +60,14 @@ Feature: llama.cpp server
    And   streaming is <enable_streaming>
    Given an OAI compatible chat completions request with no api error
    Then  <n_predicted> tokens are predicted matching <re_content>
+    And   <n_prompt> prompt tokens are processed
+    And   the completion is <truncated> truncated

    Examples: Prompts
-      | model        | system_prompt               | user_prompt                          | max_tokens | re_content             | n_predicted | enable_streaming |
-      | llama-2      | Book                        | What is the best book                | 8          | (Mom\|what)+           | 8           | disabled         |
-      | codellama70b | You are a coding assistant. | Write the fibonacci function in c++. | 64         | (thanks\|happy\|bird)+ | 32          | enabled          |
+      | model        | system_prompt               | user_prompt                          | max_tokens | re_content             | n_prompt | n_predicted | enable_streaming | truncated |
+      | llama-2      | Book                        | What is the best book                | 8          | (Here\|what)+          | 77       | 8           | disabled         | not       |
+      | codellama70b | You are a coding assistant. | Write the fibonacci function in c++. | 128        | (thanks\|happy\|bird)+ | -1       | 64          | enabled          |           |
+

  Scenario: Tokenize / Detokenize
    When tokenizing:
@@ -196,12 +196,30 @@ async def step_request_completion(context, api_error):

@step(u'{predicted_n:d} tokens are predicted matching {re_content}')
 def step_n_tokens_predicted_with_content(context, predicted_n, re_content):
-    assert_n_tokens_predicted(context.tasks_result.pop(), predicted_n, re_content)
+    context.completion = context.tasks_result.pop()
+    assert_n_tokens_predicted(context.completion, predicted_n, re_content)


@step(u'{predicted_n:d} tokens are predicted')
 def step_n_tokens_predicted(context, predicted_n):
-    assert_n_tokens_predicted(context.tasks_result.pop(), predicted_n)
+    context.completion = context.tasks_result.pop()
+    assert_n_tokens_predicted(context.completion, predicted_n)
+
+
+@step(u'the completion is  truncated')
+def step_assert_completion_truncated(context):
+    step_assert_completion_truncated(context, '')
+
+
+@step(u'the completion is {truncated} truncated')
+def step_assert_completion_truncated(context, truncated):
+    truncated = truncated != "not"
+    assert context.completion['truncated'] == truncated, f'{context.completion}'
+
+
+@step(u'{n_prompt:d} prompt tokens are processed')
+def step_impl(context, n_prompt):
+    assert n_prompt < 0 or n_prompt == context.completion['timings']['prompt_n'], f"n_prompt={context.completion['timings']['prompt_n']}"


@step(u'a user prompt {user_prompt}')
@@ -564,8 +582,9 @@ async def step_detokenize(context):
@async_run_until_complete
 async def step_options_request(context, origin):
    async with aiohttp.ClientSession() as session:
+        headers = {'Authorization': f'Bearer {context.user_api_key}', 'Origin': origin}
        async with session.options(f'{context.base_url}/v1/chat/completions',
-                                   headers={"Origin": origin}) as response:
+                                    headers=headers) as response:
            assert response.status == 200
            context.options_response = response

@@ -586,14 +605,24 @@ async def step_prometheus_metrics_exported(context):
            metric_exported = False
            if context.debug:
                print(f"/metrics answer:\n{metrics_raw}\n")
+            context.metrics = {}
            for metric in parser.text_string_to_metric_families(metrics_raw):
                match metric.name:
                    case "llamacpp:kv_cache_usage_ratio":
                        assert len(metric.samples) > 0
                        metric_exported = True
+                context.metrics[metric.name] = metric
+            assert int(metrics_response.headers["Process-Start-Time-Unix"]) > 0, "no header process start time"
            assert metric_exported, "No metrics exported"


+@step(u'metric {metric_name} is {metric_value:d}')
+def step_assert_metric_value(context, metric_name, metric_value):
+    if metric_name not in context.metrics:
+        assert False, f"no metric {metric_name} in {context.metrics.keys()}"
+    assert context.metrics[metric_name].samples[0].value == metric_value, f"metric: {context.metrics[metric_name]}"
+
+
@step(u'available models')
 def step_available_models(context):
    # openai client always expects an api_key
@@ -712,7 +741,8 @@ async def oai_chat_completions(user_prompt,
    completion_response = {
        'content': '',
        'timings': {
-            'predicted_n': 0
+            'predicted_n': 0,
+            'prompt_n': 0
        }
    }
    if async_client:
@@ -753,7 +783,8 @@ async def oai_chat_completions(user_prompt,
                        completion_response = {
                            'content': chat_completion_raw['choices'][0]['message'],
                            'timings': {
-                                'predicted_n': chat_completion_raw['usage']['completion_tokens']
+                                'predicted_n': chat_completion_raw['usage']['completion_tokens'],
+                                'prompt_n': chat_completion_raw['usage']['prompt_tokens']
                            }
                        }
                    else:
@@ -782,13 +813,16 @@ async def oai_chat_completions(user_prompt,
                if 'content' in delta:
                    completion_response['content'] += delta['content']
                    completion_response['timings']['predicted_n'] += 1
+                completion_response['truncated'] = chunk.choices[0].finish_reason != 'stop'
        else:
            assert len(chat_completion.choices) == 1
            completion_response = {
                'content': chat_completion.choices[0].message.content,
                'timings': {
-                    'predicted_n': chat_completion.usage.completion_tokens
-                }
+                    'predicted_n': chat_completion.usage.completion_tokens,
+                    'prompt_n': chat_completion.usage.prompt_tokens
+                    },
+                'truncated': chat_completion.choices[0].finish_reason != 'stop'
            }
    if debug:
        print("OAI response formatted to llama.cpp:", completion_response)
@@ -879,7 +913,6 @@ def assert_n_tokens_predicted(completion_response, expected_predicted_n=None, re
                                                     f' {n_predicted} <> {expected_predicted_n}')


-
 async def gather_tasks_results(context):
    n_tasks = len(context.concurrent_tasks)
    if context.debug:
@@ -0,0 +1,779 @@
+#pragma once
+
+#if defined(GGML_COMMON_IMPL_C)
+#include <stdint.h>
+
+#define GGML_TABLE_BEGIN(type, name, size) static const type name[size] = {
+#define GGML_TABLE_END() };
+
+#define GGML_COMMON_IMPL
+#elif defined(GGML_COMMON_IMPL_METAL)
+#include <metal_stdlib>
+
+#define GGML_TABLE_BEGIN(type, name, size) static const constant type name[size] = {
+#define GGML_TABLE_END() };
+
+#define GGML_COMMON_IMPL
+#elif defined(GGML_COMMON_IMPL_CUDA)
+#include <cstdint>
+
+#define GGML_TABLE_BEGIN(type, name, size) static const __device__ __constant__ type name[size] = {
+#define GGML_TABLE_END() };
+
+#define GGML_COMMON_IMPL
+#elif defined(GGML_COMMON_IMPL_SYCL)
+#include <cstdint>
+
+#define GGML_TABLE_BEGIN(type, name, size) static dpct::global_memory<const type, 1> name(sycl::range<1>(size), {
+#define GGML_TABLE_END() });
+
+#define GGML_COMMON_IMPL
+#endif
+
+#if defined(GGML_COMMON_IMPL)
+
+GGML_TABLE_BEGIN(uint8_t, kmask_iq2xs, 8)
+    1, 2, 4, 8, 16, 32, 64, 128
+GGML_TABLE_END()
+
+GGML_TABLE_BEGIN(uint8_t, ksigns_iq2xs, 128)
+      0, 129, 130,   3, 132,   5,   6, 135, 136,   9,  10, 139,  12, 141, 142,  15,
+    144,  17,  18, 147,  20, 149, 150,  23,  24, 153, 154,  27, 156,  29,  30, 159,
+    160,  33,  34, 163,  36, 165, 166,  39,  40, 169, 170,  43, 172,  45,  46, 175,
+     48, 177, 178,  51, 180,  53,  54, 183, 184,  57,  58, 187,  60, 189, 190,  63,
+    192,  65,  66, 195,  68, 197, 198,  71,  72, 201, 202,  75, 204,  77,  78, 207,
+     80, 209, 210,  83, 212,  85,  86, 215, 216,  89,  90, 219,  92, 221, 222,  95,
+     96, 225, 226,  99, 228, 101, 102, 231, 232, 105, 106, 235, 108, 237, 238, 111,
+    240, 113, 114, 243, 116, 245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255,
+GGML_TABLE_END()
+
+//#if __CUDA_ARCH__ >= MIN_CC_DP4A // lowest compute capability for integer intrinsics
+GGML_TABLE_BEGIN(uint64_t, ksigns64, 128)
+    0x0000000000000000, 0xff000000000000ff, 0xff0000000000ff00, 0x000000000000ffff,
+    0xff00000000ff0000, 0x0000000000ff00ff, 0x0000000000ffff00, 0xff00000000ffffff,
+    0xff000000ff000000, 0x00000000ff0000ff, 0x00000000ff00ff00, 0xff000000ff00ffff,
+    0x00000000ffff0000, 0xff000000ffff00ff, 0xff000000ffffff00, 0x00000000ffffffff,
+    0xff0000ff00000000, 0x000000ff000000ff, 0x000000ff0000ff00, 0xff0000ff0000ffff,
+    0x000000ff00ff0000, 0xff0000ff00ff00ff, 0xff0000ff00ffff00, 0x000000ff00ffffff,
+    0x000000ffff000000, 0xff0000ffff0000ff, 0xff0000ffff00ff00, 0x000000ffff00ffff,
+    0xff0000ffffff0000, 0x000000ffffff00ff, 0x000000ffffffff00, 0xff0000ffffffffff,
+    0xff00ff0000000000, 0x0000ff00000000ff, 0x0000ff000000ff00, 0xff00ff000000ffff,
+    0x0000ff0000ff0000, 0xff00ff0000ff00ff, 0xff00ff0000ffff00, 0x0000ff0000ffffff,
+    0x0000ff00ff000000, 0xff00ff00ff0000ff, 0xff00ff00ff00ff00, 0x0000ff00ff00ffff,
+    0xff00ff00ffff0000, 0x0000ff00ffff00ff, 0x0000ff00ffffff00, 0xff00ff00ffffffff,
+    0x0000ffff00000000, 0xff00ffff000000ff, 0xff00ffff0000ff00, 0x0000ffff0000ffff,
+    0xff00ffff00ff0000, 0x0000ffff00ff00ff, 0x0000ffff00ffff00, 0xff00ffff00ffffff,
+    0xff00ffffff000000, 0x0000ffffff0000ff, 0x0000ffffff00ff00, 0xff00ffffff00ffff,
+    0x0000ffffffff0000, 0xff00ffffffff00ff, 0xff00ffffffffff00, 0x0000ffffffffffff,
+    0xffff000000000000, 0x00ff0000000000ff, 0x00ff00000000ff00, 0xffff00000000ffff,
+    0x00ff000000ff0000, 0xffff000000ff00ff, 0xffff000000ffff00, 0x00ff000000ffffff,
+    0x00ff0000ff000000, 0xffff0000ff0000ff, 0xffff0000ff00ff00, 0x00ff0000ff00ffff,
+    0xffff0000ffff0000, 0x00ff0000ffff00ff, 0x00ff0000ffffff00, 0xffff0000ffffffff,
+    0x00ff00ff00000000, 0xffff00ff000000ff, 0xffff00ff0000ff00, 0x00ff00ff0000ffff,
+    0xffff00ff00ff0000, 0x00ff00ff00ff00ff, 0x00ff00ff00ffff00, 0xffff00ff00ffffff,
+    0xffff00ffff000000, 0x00ff00ffff0000ff, 0x00ff00ffff00ff00, 0xffff00ffff00ffff,
+    0x00ff00ffffff0000, 0xffff00ffffff00ff, 0xffff00ffffffff00, 0x00ff00ffffffffff,
+    0x00ffff0000000000, 0xffffff00000000ff, 0xffffff000000ff00, 0x00ffff000000ffff,
+    0xffffff0000ff0000, 0x00ffff0000ff00ff, 0x00ffff0000ffff00, 0xffffff0000ffffff,
+    0xffffff00ff000000, 0x00ffff00ff0000ff, 0x00ffff00ff00ff00, 0xffffff00ff00ffff,
+    0x00ffff00ffff0000, 0xffffff00ffff00ff, 0xffffff00ffffff00, 0x00ffff00ffffffff,
+    0xffffffff00000000, 0x00ffffff000000ff, 0x00ffffff0000ff00, 0xffffffff0000ffff,
+    0x00ffffff00ff0000, 0xffffffff00ff00ff, 0xffffffff00ffff00, 0x00ffffff00ffffff,
+    0x00ffffffff000000, 0xffffffffff0000ff, 0xffffffffff00ff00, 0x00ffffffff00ffff,
+    0xffffffffffff0000, 0x00ffffffffff00ff, 0x00ffffffffffff00, 0xffffffffffffffff,
+GGML_TABLE_END()
+//#endif
+
+
+GGML_TABLE_BEGIN(uint64_t, iq2xxs_grid, 256)
+    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
+    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808,
+    0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819,
+    0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819,
+    0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b,
+    0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808,
+    0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08,
+    0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b,
+    0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819,
+    0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08,
+    0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808,
+    0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08,
+    0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808,
+    0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808,
+    0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919,
+    0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819,
+    0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08,
+    0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908,
+    0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819,
+    0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808,
+    0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808,
+    0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908,
+    0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808,
+    0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08,
+    0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819,
+    0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819,
+    0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819,
+    0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908,
+    0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19,
+    0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819,
+    0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b,
+    0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808,
+    0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908,
+    0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08,
+    0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08,
+    0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908,
+    0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819,
+    0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808,
+    0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808,
+    0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19,
+    0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819,
+    0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919,
+    0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b,
+    0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08,
+    0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808,
+    0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908,
+    0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b,
+    0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819,
+    0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08,
+    0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08,
+    0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808,
+    0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b,
+    0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b,
+    0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908,
+    0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819,
+    0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808,
+    0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908,
+    0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b,
+    0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808,
+    0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b,
+    0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b,
+    0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808,
+    0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19,
+    0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908,
+GGML_TABLE_END()
+
+GGML_TABLE_BEGIN(uint64_t, iq2xs_grid, 512)
+    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
+    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
+    0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
+    0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
+    0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
+    0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808,
+    0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08, 0x080808082b190819,
+    0x080808082b191908, 0x080808082b192b19, 0x080808082b2b0808, 0x0808081908080819,
+    0x0808081908081908, 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808,
+    0x080808190819082b, 0x0808081908191919, 0x0808081908192b08, 0x0808081908192b2b,
+    0x08080819082b0819, 0x08080819082b1908, 0x0808081919080808, 0x080808191908082b,
+    0x0808081919081919, 0x0808081919082b08, 0x0808081919190819, 0x0808081919191908,
+    0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819, 0x080808192b081908,
+    0x080808192b190808, 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b08081919,
+    0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808,
+    0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808, 0x0808082b19191919,
+    0x0808082b2b080808, 0x0808082b2b082b2b, 0x0808190808080819, 0x0808190808081908,
+    0x080819080808192b, 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b,
+    0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908,
+    0x0808190819080808, 0x080819081908082b, 0x0808190819081919, 0x0808190819082b08,
+    0x0808190819190819, 0x0808190819191908, 0x080819081919192b, 0x08081908192b0808,
+    0x080819082b080819, 0x080819082b081908, 0x080819082b190808, 0x0808191908080808,
+    0x080819190808082b, 0x0808191908081919, 0x0808191908082b08, 0x0808191908190819,
+    0x0808191908191908, 0x08081919082b0808, 0x0808191919080819, 0x0808191919081908,
+    0x0808191919190808, 0x08081919192b0819, 0x080819192b080808, 0x0808192b08080819,
+    0x0808192b08081908, 0x0808192b08190808, 0x0808192b082b192b, 0x0808192b19080808,
+    0x0808192b1908082b, 0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b,
+    0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b, 0x08082b0808190819,
+    0x08082b0808191908, 0x08082b08082b0808, 0x08082b08082b1919, 0x08082b0819080819,
+    0x08082b0819081908, 0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808,
+    0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819, 0x08082b1908081908,
+    0x08082b1908190808, 0x08082b1919080808, 0x08082b192b080819, 0x08082b192b082b19,
+    0x08082b2b08080808, 0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b,
+    0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908, 0x081908080808192b,
+    0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, 0x0819080808191919,
+    0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808,
+    0x081908081908082b, 0x0819080819081919, 0x0819080819082b08, 0x0819080819190819,
+    0x0819080819191908, 0x08190808192b0808, 0x08190808192b2b2b, 0x081908082b080819,
+    0x081908082b081908, 0x081908082b190808, 0x0819081908080808, 0x081908190808082b,
+    0x0819081908081919, 0x0819081908082b08, 0x0819081908190819, 0x0819081908191908,
+    0x08190819082b0808, 0x0819081919080819, 0x0819081919081908, 0x0819081919190808,
+    0x081908192b080808, 0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819,
+    0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808, 0x0819082b19080808,
+    0x0819082b192b0808, 0x0819190808080808, 0x081919080808082b, 0x0819190808081919,
+    0x0819190808082b08, 0x0819190808190819, 0x0819190808191908, 0x08191908082b0808,
+    0x0819190819080819, 0x0819190819081908, 0x0819190819082b19, 0x0819190819190808,
+    0x08191908192b1908, 0x081919082b080808, 0x0819191908080819, 0x0819191908081908,
+    0x0819191908190808, 0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908,
+    0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808,
+    0x08192b080819082b, 0x08192b0819080808, 0x08192b0819191908, 0x08192b082b08192b,
+    0x08192b1908080808, 0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819,
+    0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919,
+    0x082b080808082b08, 0x082b080808082b2b, 0x082b080808190819, 0x082b080808191908,
+    0x082b0808082b0808, 0x082b080819080819, 0x082b080819081908, 0x082b080819190808,
+    0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819, 0x082b081908081908,
+    0x082b081908190808, 0x082b081919080808, 0x082b081919082b08, 0x082b0819192b1919,
+    0x082b082b08080808, 0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08,
+    0x082b190808080819, 0x082b190808081908, 0x082b190808190808, 0x082b1908082b2b19,
+    0x082b190819080808, 0x082b191908080808, 0x082b191919080819, 0x082b19191919082b,
+    0x082b19192b192b19, 0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b,
+    0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b, 0x082b2b08082b0808,
+    0x082b2b0819191919, 0x082b2b082b082b08, 0x082b2b082b2b082b, 0x082b2b19192b2b08,
+    0x082b2b192b190808, 0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b,
+    0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, 0x1908080808081908,
+    0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, 0x190808080819082b,
+    0x1908080808191919, 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908,
+    0x1908080819080808, 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08,
+    0x1908080819082b2b, 0x1908080819190819, 0x1908080819191908, 0x19080808192b0808,
+    0x19080808192b1919, 0x190808082b080819, 0x190808082b081908, 0x190808082b190808,
+    0x1908081908080808, 0x190808190808082b, 0x1908081908081919, 0x1908081908082b08,
+    0x1908081908190819, 0x1908081908191908, 0x19080819082b0808, 0x1908081919080819,
+    0x1908081919081908, 0x1908081919190808, 0x190808192b080808, 0x190808192b081919,
+    0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908, 0x1908082b08190808,
+    0x1908082b0819082b, 0x1908082b082b2b19, 0x1908082b19080808, 0x1908190808080808,
+    0x190819080808082b, 0x1908190808081919, 0x1908190808082b08, 0x1908190808190819,
+    0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808, 0x1908190819080819,
+    0x1908190819081908, 0x1908190819190808, 0x190819082b080808, 0x190819082b191908,
+    0x1908191908080819, 0x1908191908081908, 0x1908191908190808, 0x19081919082b1908,
+    0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808, 0x1908192b08082b2b,
+    0x1908192b19081908, 0x1908192b19190808, 0x19082b0808080819, 0x19082b0808081908,
+    0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908,
+    0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819, 0x19082b1919081908,
+    0x19082b1919190808, 0x19082b19192b2b19, 0x19082b2b08081908, 0x1919080808080808,
+    0x191908080808082b, 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819,
+    0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08, 0x1919080819080819,
+    0x1919080819081908, 0x1919080819190808, 0x191908082b080808, 0x1919081908080819,
+    0x1919081908081908, 0x1919081908190808, 0x1919081908191919, 0x1919081919080808,
+    0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908, 0x1919082b2b2b2b2b,
+    0x1919190808080819, 0x1919190808081908, 0x1919190808190808, 0x19191908082b0819,
+    0x1919190819080808, 0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819,
+    0x1919191908080808, 0x1919191908082b08, 0x191919192b080808, 0x191919192b082b08,
+    0x1919192b082b0819, 0x1919192b192b2b08, 0x1919192b2b2b0819, 0x19192b0808080808,
+    0x19192b0808191908, 0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19,
+    0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b, 0x19192b2b2b081919,
+    0x192b080808080819, 0x192b080808081908, 0x192b080808190808, 0x192b080819080808,
+    0x192b080819191908, 0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19,
+    0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b, 0x192b082b2b19082b,
+    0x192b190808080808, 0x192b19080819192b, 0x192b191908190808, 0x192b191919080808,
+    0x192b191919081919, 0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b,
+    0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908, 0x192b2b2b192b082b,
+    0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08,
+    0x2b08080808190819, 0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b,
+    0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808082b080808,
+    0x2b0808082b08082b, 0x2b0808082b2b2b08, 0x2b0808082b2b2b2b, 0x2b08081908080819,
+    0x2b08081908081908, 0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808,
+    0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808, 0x2b08082b082b0808,
+    0x2b08082b2b080808, 0x2b08082b2b08082b, 0x2b08082b2b2b0808, 0x2b08082b2b2b2b08,
+    0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b,
+    0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, 0x2b0819082b082b19,
+    0x2b08191908080808, 0x2b08191919081908, 0x2b0819192b2b1919, 0x2b08192b08192b08,
+    0x2b08192b192b2b2b, 0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919,
+    0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b, 0x2b082b082b2b2b08,
+    0x2b082b190808192b, 0x2b082b2b082b082b, 0x2b082b2b2b080808, 0x2b082b2b2b082b08,
+    0x2b082b2b2b19192b, 0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908,
+    0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b, 0x2b1908082b081908,
+    0x2b19081908080808, 0x2b190819082b082b, 0x2b190819192b1908, 0x2b19082b1919192b,
+    0x2b19082b2b082b19, 0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908,
+    0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19, 0x2b1919192b190808,
+    0x2b1919192b19082b, 0x2b19192b19080819, 0x2b192b0819190819, 0x2b192b082b2b192b,
+    0x2b192b1919082b19, 0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808,
+    0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b, 0x2b2b0808082b0808,
+    0x2b2b0808082b2b2b, 0x2b2b08082b2b0808, 0x2b2b081919190819, 0x2b2b081919192b19,
+    0x2b2b08192b2b192b, 0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08,
+    0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808, 0x2b2b190819080808,
+    0x2b2b19082b191919, 0x2b2b192b192b1919, 0x2b2b192b2b192b08, 0x2b2b2b0808082b2b,
+    0x2b2b2b08082b0808, 0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808,
+    0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908, 0x2b2b2b192b08192b,
+    0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b,
+GGML_TABLE_END()
+
+GGML_TABLE_BEGIN(uint64_t, iq2s_grid, 1024)
+    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
+    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
+    0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
+    0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
+    0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
+    0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x08080808192b192b,
+    0x08080808192b2b19, 0x080808082b080808, 0x080808082b08082b, 0x080808082b081919,
+    0x080808082b082b08, 0x080808082b190819, 0x080808082b191908, 0x080808082b2b0808,
+    0x080808082b2b1919, 0x080808082b2b2b2b, 0x0808081908080819, 0x0808081908081908,
+    0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, 0x080808190819082b,
+    0x0808081908191919, 0x0808081908192b08, 0x08080819082b0819, 0x08080819082b1908,
+    0x0808081919080808, 0x080808191908082b, 0x0808081919081919, 0x0808081919082b08,
+    0x0808081919190819, 0x0808081919191908, 0x080808191919192b, 0x0808081919192b19,
+    0x08080819192b0808, 0x08080819192b1919, 0x08080819192b2b08, 0x080808192b080819,
+    0x080808192b081908, 0x080808192b190808, 0x080808192b19082b, 0x080808192b191919,
+    0x080808192b2b0819, 0x080808192b2b1908, 0x0808082b08080808, 0x0808082b0808082b,
+    0x0808082b08081919, 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908,
+    0x0808082b082b0808, 0x0808082b082b2b2b, 0x0808082b19080819, 0x0808082b19081908,
+    0x0808082b1908192b, 0x0808082b19082b19, 0x0808082b19190808, 0x0808082b19191919,
+    0x0808082b2b080808, 0x0808082b2b081919, 0x0808082b2b082b2b, 0x0808082b2b191908,
+    0x0808082b2b2b082b, 0x0808190808080819, 0x0808190808081908, 0x080819080808192b,
+    0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, 0x0808190808191919,
+    0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, 0x08081908082b192b,
+    0x08081908082b2b19, 0x0808190819080808, 0x080819081908082b, 0x0808190819081919,
+    0x0808190819082b08, 0x0808190819082b2b, 0x0808190819190819, 0x0808190819191908,
+    0x080819081919192b, 0x0808190819192b19, 0x08081908192b0808, 0x08081908192b082b,
+    0x08081908192b1919, 0x080819082b080819, 0x080819082b081908, 0x080819082b08192b,
+    0x080819082b082b19, 0x080819082b190808, 0x080819082b191919, 0x080819082b192b08,
+    0x080819082b2b0819, 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b,
+    0x0808191908081919, 0x0808191908082b08, 0x0808191908082b2b, 0x0808191908190819,
+    0x0808191908191908, 0x080819190819192b, 0x0808191908192b19, 0x08081919082b0808,
+    0x08081919082b1919, 0x08081919082b2b08, 0x0808191919080819, 0x0808191919081908,
+    0x080819191908192b, 0x0808191919082b19, 0x0808191919190808, 0x080819191919082b,
+    0x0808191919191919, 0x0808191919192b08, 0x08081919192b0819, 0x08081919192b1908,
+    0x080819192b080808, 0x080819192b08082b, 0x080819192b081919, 0x080819192b082b08,
+    0x080819192b190819, 0x080819192b191908, 0x080819192b2b0808, 0x0808192b08080819,
+    0x0808192b08081908, 0x0808192b0808192b, 0x0808192b08082b19, 0x0808192b08190808,
+    0x0808192b08191919, 0x0808192b19080808, 0x0808192b19081919, 0x0808192b19082b08,
+    0x0808192b19190819, 0x0808192b19191908, 0x0808192b192b0808, 0x0808192b2b080819,
+    0x0808192b2b081908, 0x0808192b2b190808, 0x08082b0808080808, 0x08082b080808082b,
+    0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808190819, 0x08082b0808191908,
+    0x08082b080819192b, 0x08082b0808192b19, 0x08082b08082b0808, 0x08082b08082b1919,
+    0x08082b08082b2b2b, 0x08082b0819080819, 0x08082b0819081908, 0x08082b081908192b,
+    0x08082b0819082b19, 0x08082b0819190808, 0x08082b081919082b, 0x08082b0819191919,
+    0x08082b0819192b08, 0x08082b08192b0819, 0x08082b08192b1908, 0x08082b082b080808,
+    0x08082b082b081919, 0x08082b082b191908, 0x08082b082b2b2b2b, 0x08082b1908080819,
+    0x08082b1908081908, 0x08082b1908190808, 0x08082b190819082b, 0x08082b1908191919,
+    0x08082b1908192b08, 0x08082b19082b0819, 0x08082b1919080808, 0x08082b1919081919,
+    0x08082b1919082b08, 0x08082b1919190819, 0x08082b1919191908, 0x08082b19192b0808,
+    0x08082b192b080819, 0x08082b192b190808, 0x08082b2b08080808, 0x08082b2b08190819,
+    0x08082b2b08191908, 0x08082b2b082b082b, 0x08082b2b082b2b08, 0x08082b2b082b2b2b,
+    0x08082b2b19190808, 0x08082b2b2b192b19, 0x0819080808080819, 0x0819080808081908,
+    0x081908080808192b, 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b,
+    0x0819080808191919, 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908,
+    0x08190808082b192b, 0x0819080819080808, 0x081908081908082b, 0x0819080819081919,
+    0x0819080819082b08, 0x0819080819190819, 0x0819080819191908, 0x081908081919192b,
+    0x0819080819192b19, 0x08190808192b0808, 0x08190808192b082b, 0x08190808192b1919,
+    0x08190808192b2b08, 0x081908082b080819, 0x081908082b081908, 0x081908082b08192b,
+    0x081908082b190808, 0x081908082b191919, 0x081908082b192b08, 0x081908082b2b0819,
+    0x081908082b2b1908, 0x0819081908080808, 0x081908190808082b, 0x0819081908081919,
+    0x0819081908082b08, 0x0819081908082b2b, 0x0819081908190819, 0x0819081908191908,
+    0x081908190819192b, 0x0819081908192b19, 0x08190819082b0808, 0x08190819082b082b,
+    0x08190819082b1919, 0x08190819082b2b08, 0x0819081919080819, 0x0819081919081908,
+    0x081908191908192b, 0x0819081919082b19, 0x0819081919190808, 0x081908191919082b,
+    0x0819081919191919, 0x0819081919192b08, 0x08190819192b0819, 0x08190819192b1908,
+    0x081908192b080808, 0x081908192b08082b, 0x081908192b081919, 0x081908192b082b08,
+    0x081908192b190819, 0x081908192b191908, 0x0819082b08080819, 0x0819082b08081908,
+    0x0819082b08082b19, 0x0819082b08190808, 0x0819082b08191919, 0x0819082b082b0819,
+    0x0819082b082b1908, 0x0819082b19080808, 0x0819082b19081919, 0x0819082b19190819,
+    0x0819082b19191908, 0x0819082b2b080819, 0x0819082b2b081908, 0x0819082b2b190808,
+    0x0819190808080808, 0x081919080808082b, 0x0819190808081919, 0x0819190808082b08,
+    0x0819190808190819, 0x0819190808191908, 0x081919080819192b, 0x0819190808192b19,
+    0x08191908082b0808, 0x08191908082b1919, 0x08191908082b2b08, 0x0819190819080819,
+    0x0819190819081908, 0x081919081908192b, 0x0819190819082b19, 0x0819190819190808,
+    0x081919081919082b, 0x0819190819191919, 0x0819190819192b08, 0x08191908192b0819,
+    0x08191908192b1908, 0x081919082b080808, 0x081919082b08082b, 0x081919082b081919,
+    0x081919082b082b08, 0x081919082b190819, 0x081919082b191908, 0x081919082b2b0808,
+    0x0819191908080819, 0x0819191908081908, 0x081919190808192b, 0x0819191908082b19,
+    0x0819191908190808, 0x081919190819082b, 0x0819191908191919, 0x0819191908192b08,
+    0x08191919082b0819, 0x08191919082b1908, 0x0819191919080808, 0x081919191908082b,
+    0x0819191919081919, 0x0819191919082b08, 0x0819191919190819, 0x0819191919191908,
+    0x08191919192b0808, 0x081919192b080819, 0x081919192b081908, 0x081919192b190808,
+    0x0819192b08080808, 0x0819192b08081919, 0x0819192b08082b08, 0x0819192b08190819,
+    0x0819192b08191908, 0x0819192b082b0808, 0x0819192b19080819, 0x0819192b19081908,
+    0x0819192b19190808, 0x0819192b2b080808, 0x0819192b2b2b2b2b, 0x08192b0808080819,
+    0x08192b0808081908, 0x08192b080808192b, 0x08192b0808082b19, 0x08192b0808190808,
+    0x08192b0808191919, 0x08192b0808192b08, 0x08192b08082b0819, 0x08192b0819080808,
+    0x08192b081908082b, 0x08192b0819081919, 0x08192b0819082b08, 0x08192b0819190819,
+    0x08192b0819191908, 0x08192b08192b0808, 0x08192b082b080819, 0x08192b082b081908,
+    0x08192b1908080808, 0x08192b190808082b, 0x08192b1908081919, 0x08192b1908082b08,
+    0x08192b1908190819, 0x08192b1908191908, 0x08192b19082b0808, 0x08192b1919080819,
+    0x08192b1919081908, 0x08192b1919190808, 0x08192b19192b2b19, 0x08192b192b2b082b,
+    0x08192b2b08081908, 0x08192b2b08190808, 0x08192b2b19080808, 0x08192b2b1919192b,
+    0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, 0x082b080808082b08,
+    0x082b080808190819, 0x082b080808191908, 0x082b08080819192b, 0x082b080808192b19,
+    0x082b0808082b0808, 0x082b0808082b1919, 0x082b0808082b2b2b, 0x082b080819080819,
+    0x082b080819081908, 0x082b080819190808, 0x082b08081919082b, 0x082b080819191919,
+    0x082b0808192b1908, 0x082b08082b080808, 0x082b08082b082b2b, 0x082b08082b191908,
+    0x082b08082b2b2b2b, 0x082b081908080819, 0x082b081908081908, 0x082b081908190808,
+    0x082b08190819082b, 0x082b081908191919, 0x082b0819082b0819, 0x082b081919080808,
+    0x082b08191908082b, 0x082b081919081919, 0x082b081919190819, 0x082b081919191908,
+    0x082b0819192b0808, 0x082b08192b080819, 0x082b08192b081908, 0x082b08192b190808,
+    0x082b082b08080808, 0x082b082b08082b2b, 0x082b082b082b082b, 0x082b082b082b2b08,
+    0x082b082b082b2b2b, 0x082b082b19081908, 0x082b082b19190808, 0x082b082b2b082b08,
+    0x082b082b2b082b2b, 0x082b082b2b2b2b08, 0x082b190808080819, 0x082b190808081908,
+    0x082b19080808192b, 0x082b190808082b19, 0x082b190808190808, 0x082b190808191919,
+    0x082b190808192b08, 0x082b1908082b0819, 0x082b1908082b1908, 0x082b190819080808,
+    0x082b19081908082b, 0x082b190819081919, 0x082b190819082b08, 0x082b190819190819,
+    0x082b190819191908, 0x082b1908192b0808, 0x082b19082b080819, 0x082b19082b081908,
+    0x082b19082b190808, 0x082b191908080808, 0x082b191908081919, 0x082b191908082b08,
+    0x082b191908190819, 0x082b191908191908, 0x082b1919082b0808, 0x082b191919080819,
+    0x082b191919081908, 0x082b191919190808, 0x082b1919192b192b, 0x082b19192b080808,
+    0x082b192b08080819, 0x082b192b08081908, 0x082b192b08190808, 0x082b192b19080808,
+    0x082b192b19192b19, 0x082b2b0808080808, 0x082b2b0808081919, 0x082b2b0808190819,
+    0x082b2b0808191908, 0x082b2b0819080819, 0x082b2b0819081908, 0x082b2b0819190808,
+    0x082b2b082b082b2b, 0x082b2b082b2b2b2b, 0x082b2b1908080819, 0x082b2b1908081908,
+    0x082b2b1908190808, 0x082b2b192b191919, 0x082b2b2b08082b2b, 0x082b2b2b082b082b,
+    0x082b2b2b192b1908, 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819,
+    0x1908080808081908, 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808,
+    0x190808080819082b, 0x1908080808191919, 0x1908080808192b08, 0x1908080808192b2b,
+    0x19080808082b0819, 0x19080808082b1908, 0x19080808082b192b, 0x1908080819080808,
+    0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, 0x1908080819082b2b,
+    0x1908080819190819, 0x1908080819191908, 0x190808081919192b, 0x1908080819192b19,
+    0x19080808192b0808, 0x19080808192b082b, 0x19080808192b1919, 0x190808082b080819,
+    0x190808082b081908, 0x190808082b190808, 0x190808082b191919, 0x190808082b192b08,
+    0x190808082b2b0819, 0x190808082b2b1908, 0x1908081908080808, 0x190808190808082b,
+    0x1908081908081919, 0x1908081908082b08, 0x1908081908190819, 0x1908081908191908,
+    0x190808190819192b, 0x1908081908192b19, 0x19080819082b0808, 0x19080819082b082b,
+    0x19080819082b1919, 0x1908081919080819, 0x1908081919081908, 0x190808191908192b,
+    0x1908081919082b19, 0x1908081919190808, 0x190808191919082b, 0x1908081919191919,
+    0x1908081919192b08, 0x19080819192b0819, 0x19080819192b1908, 0x190808192b080808,
+    0x190808192b08082b, 0x190808192b081919, 0x190808192b082b08, 0x190808192b190819,
+    0x190808192b191908, 0x190808192b2b0808, 0x1908082b08080819, 0x1908082b08081908,
+    0x1908082b08190808, 0x1908082b0819082b, 0x1908082b08191919, 0x1908082b08192b08,
+    0x1908082b082b1908, 0x1908082b19080808, 0x1908082b19081919, 0x1908082b19082b08,
+    0x1908082b19190819, 0x1908082b19191908, 0x1908082b192b0808, 0x1908082b2b080819,
+    0x1908082b2b081908, 0x1908190808080808, 0x190819080808082b, 0x1908190808081919,
+    0x1908190808082b08, 0x1908190808082b2b, 0x1908190808190819, 0x1908190808191908,
+    0x190819080819192b, 0x1908190808192b19, 0x19081908082b0808, 0x19081908082b082b,
+    0x19081908082b1919, 0x19081908082b2b08, 0x1908190819080819, 0x1908190819081908,
+    0x190819081908192b, 0x1908190819082b19, 0x1908190819190808, 0x190819081919082b,
+    0x1908190819191919, 0x1908190819192b08, 0x19081908192b0819, 0x19081908192b1908,
+    0x190819082b080808, 0x190819082b08082b, 0x190819082b081919, 0x190819082b082b08,
+    0x190819082b190819, 0x190819082b191908, 0x190819082b2b0808, 0x1908191908080819,
+    0x1908191908081908, 0x190819190808192b, 0x1908191908082b19, 0x1908191908190808,
+    0x190819190819082b, 0x1908191908191919, 0x1908191908192b08, 0x19081919082b0819,
+    0x19081919082b1908, 0x1908191919080808, 0x190819191908082b, 0x1908191919081919,
+    0x1908191919082b08, 0x1908191919190819, 0x1908191919191908, 0x19081919192b0808,
+    0x19081919192b2b2b, 0x190819192b080819, 0x190819192b081908, 0x190819192b190808,
+    0x1908192b08080808, 0x1908192b0808082b, 0x1908192b08081919, 0x1908192b08082b08,
+    0x1908192b08190819, 0x1908192b08191908, 0x1908192b082b0808, 0x1908192b19080819,
+    0x1908192b19081908, 0x1908192b19190808, 0x1908192b2b080808, 0x1908192b2b2b1919,
+    0x19082b0808080819, 0x19082b0808081908, 0x19082b0808082b19, 0x19082b0808190808,
+    0x19082b080819082b, 0x19082b0808191919, 0x19082b0808192b08, 0x19082b08082b0819,
+    0x19082b08082b1908, 0x19082b0819080808, 0x19082b081908082b, 0x19082b0819081919,
+    0x19082b0819082b08, 0x19082b0819190819, 0x19082b0819191908, 0x19082b08192b0808,
+    0x19082b082b081908, 0x19082b082b190808, 0x19082b1908080808, 0x19082b190808082b,
+    0x19082b1908081919, 0x19082b1908082b08, 0x19082b1908190819, 0x19082b1908191908,
+    0x19082b19082b0808, 0x19082b1919080819, 0x19082b1919081908, 0x19082b1919190808,
+    0x19082b192b080808, 0x19082b192b19192b, 0x19082b2b08080819, 0x19082b2b08081908,
+    0x19082b2b08190808, 0x19082b2b19080808, 0x1919080808080808, 0x191908080808082b,
+    0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, 0x1919080808191908,
+    0x191908080819192b, 0x1919080808192b19, 0x19190808082b0808, 0x19190808082b082b,
+    0x19190808082b1919, 0x19190808082b2b08, 0x1919080819080819, 0x1919080819081908,
+    0x191908081908192b, 0x1919080819082b19, 0x1919080819190808, 0x191908081919082b,
+    0x1919080819191919, 0x1919080819192b08, 0x19190808192b0819, 0x19190808192b1908,
+    0x191908082b080808, 0x191908082b08082b, 0x191908082b081919, 0x191908082b082b08,
+    0x191908082b190819, 0x191908082b191908, 0x1919081908080819, 0x1919081908081908,
+    0x191908190808192b, 0x1919081908082b19, 0x1919081908190808, 0x191908190819082b,
+    0x1919081908191919, 0x1919081908192b08, 0x19190819082b0819, 0x19190819082b1908,
+    0x1919081919080808, 0x191908191908082b, 0x1919081919081919, 0x1919081919082b08,
+    0x1919081919190819, 0x1919081919191908, 0x19190819192b0808, 0x191908192b080819,
+    0x191908192b081908, 0x191908192b190808, 0x1919082b08080808, 0x1919082b08081919,
+    0x1919082b08082b08, 0x1919082b08190819, 0x1919082b08191908, 0x1919082b082b0808,
+    0x1919082b19080819, 0x1919082b19081908, 0x1919082b19190808, 0x1919082b192b2b19,
+    0x1919082b2b080808, 0x1919190808080819, 0x1919190808081908, 0x191919080808192b,
+    0x1919190808082b19, 0x1919190808190808, 0x191919080819082b, 0x1919190808191919,
+    0x1919190808192b08, 0x19191908082b0819, 0x19191908082b1908, 0x1919190819080808,
+    0x191919081908082b, 0x1919190819081919, 0x1919190819082b08, 0x1919190819190819,
+    0x1919190819191908, 0x19191908192b0808, 0x191919082b080819, 0x191919082b081908,
+    0x191919082b190808, 0x1919191908080808, 0x191919190808082b, 0x1919191908081919,
+    0x1919191908082b08, 0x1919191908190819, 0x1919191908191908, 0x19191919082b0808,
+    0x1919191919080819, 0x1919191919081908, 0x1919191919190808, 0x191919192b080808,
+    0x1919192b08080819, 0x1919192b08081908, 0x1919192b08190808, 0x1919192b082b192b,
+    0x1919192b19080808, 0x19192b0808080808, 0x19192b080808082b, 0x19192b0808081919,
+    0x19192b0808082b08, 0x19192b0808190819, 0x19192b0808191908, 0x19192b08082b0808,
+    0x19192b0819080819, 0x19192b0819081908, 0x19192b0819190808, 0x19192b0819192b2b,
+    0x19192b082b080808, 0x19192b1908080819, 0x19192b1908081908, 0x19192b1908190808,
+    0x19192b1919080808, 0x19192b2b08080808, 0x19192b2b08192b19, 0x19192b2b2b081919,
+    0x19192b2b2b2b2b08, 0x192b080808080819, 0x192b080808081908, 0x192b08080808192b,
+    0x192b080808190808, 0x192b08080819082b, 0x192b080808191919, 0x192b080808192b08,
+    0x192b0808082b0819, 0x192b0808082b1908, 0x192b080819080808, 0x192b080819081919,
+    0x192b080819082b08, 0x192b080819190819, 0x192b080819191908, 0x192b0808192b0808,
+    0x192b08082b081908, 0x192b08082b190808, 0x192b081908080808, 0x192b08190808082b,
+    0x192b081908081919, 0x192b081908082b08, 0x192b081908190819, 0x192b081908191908,
+    0x192b0819082b0808, 0x192b081919080819, 0x192b081919081908, 0x192b081919190808,
+    0x192b08192b080808, 0x192b08192b192b19, 0x192b082b08081908, 0x192b082b08190808,
+    0x192b082b19080808, 0x192b082b1919192b, 0x192b082b2b2b0819, 0x192b190808080808,
+    0x192b190808081919, 0x192b190808082b08, 0x192b190808190819, 0x192b190808191908,
+    0x192b1908082b0808, 0x192b190819080819, 0x192b190819081908, 0x192b190819190808,
+    0x192b19082b080808, 0x192b191908080819, 0x192b191908081908, 0x192b191908190808,
+    0x192b191919080808, 0x192b191919082b2b, 0x192b1919192b2b08, 0x192b19192b19082b,
+    0x192b192b08080808, 0x192b192b2b191908, 0x192b2b0808080819, 0x192b2b0808081908,
+    0x192b2b0808190808, 0x192b2b08192b1919, 0x192b2b082b192b08, 0x192b2b1908080808,
+    0x192b2b19082b2b2b, 0x192b2b2b1908082b, 0x192b2b2b2b2b0819, 0x2b08080808080808,
+    0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, 0x2b08080808190819,
+    0x2b08080808191908, 0x2b08080808192b19, 0x2b080808082b0808, 0x2b080808082b1919,
+    0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808081919082b,
+    0x2b08080819191919, 0x2b08080819192b08, 0x2b080808192b0819, 0x2b0808082b080808,
+    0x2b0808082b081919, 0x2b0808082b190819, 0x2b0808082b191908, 0x2b08081908080819,
+    0x2b08081908081908, 0x2b08081908082b19, 0x2b08081908190808, 0x2b0808190819082b,
+    0x2b08081908191919, 0x2b08081908192b08, 0x2b080819082b0819, 0x2b080819082b1908,
+    0x2b08081919080808, 0x2b0808191908082b, 0x2b08081919081919, 0x2b08081919082b08,
+    0x2b08081919190819, 0x2b08081919191908, 0x2b0808192b080819, 0x2b0808192b081908,
+    0x2b0808192b190808, 0x2b0808192b2b2b19, 0x2b08082b08080808, 0x2b08082b08081919,
+    0x2b08082b08082b2b, 0x2b08082b08190819, 0x2b08082b08191908, 0x2b08082b19080819,
+    0x2b08082b19081908, 0x2b08082b19190808, 0x2b08190808080819, 0x2b08190808081908,
+    0x2b0819080808192b, 0x2b08190808082b19, 0x2b08190808190808, 0x2b0819080819082b,
+    0x2b08190808191919, 0x2b08190808192b08, 0x2b081908082b0819, 0x2b08190819080808,
+    0x2b0819081908082b, 0x2b08190819081919, 0x2b08190819082b08, 0x2b08190819190819,
+    0x2b08190819191908, 0x2b081908192b0808, 0x2b0819082b080819, 0x2b0819082b081908,
+    0x2b0819082b190808, 0x2b08191908080808, 0x2b0819190808082b, 0x2b08191908081919,
+    0x2b08191908082b08, 0x2b08191908190819, 0x2b08191908191908, 0x2b081919082b0808,
+    0x2b08191919080819, 0x2b08191919081908, 0x2b08191919190808, 0x2b0819192b080808,
+    0x2b0819192b082b2b, 0x2b08192b08080819, 0x2b08192b08081908, 0x2b08192b08190808,
+    0x2b08192b082b2b19, 0x2b08192b19080808, 0x2b082b0808080808, 0x2b082b0808081919,
+    0x2b082b0808190819, 0x2b082b0808191908, 0x2b082b0819080819, 0x2b082b0819081908,
+    0x2b082b0819190808, 0x2b082b082b2b082b, 0x2b082b1908080819, 0x2b082b1908081908,
+    0x2b082b1919080808, 0x2b082b19192b1919, 0x2b082b2b082b082b, 0x2b082b2b19192b08,
+    0x2b082b2b19192b2b, 0x2b082b2b2b08082b, 0x2b082b2b2b2b082b, 0x2b19080808080819,
+    0x2b19080808081908, 0x2b19080808082b19, 0x2b19080808190808, 0x2b1908080819082b,
+    0x2b19080808191919, 0x2b19080808192b08, 0x2b190808082b1908, 0x2b19080819080808,
+    0x2b1908081908082b, 0x2b19080819081919, 0x2b19080819082b08, 0x2b19080819190819,
+    0x2b19080819191908, 0x2b190808192b0808, 0x2b1908082b080819, 0x2b1908082b081908,
+    0x2b1908082b190808, 0x2b19081908080808, 0x2b19081908081919, 0x2b19081908190819,
+    0x2b19081908191908, 0x2b19081919080819, 0x2b19081919081908, 0x2b19081919190808,
+    0x2b19081919192b2b, 0x2b19082b08080819, 0x2b19082b08081908, 0x2b19082b08190808,
+    0x2b19082b19080808, 0x2b19082b2b2b192b, 0x2b19190808080808, 0x2b1919080808082b,
+    0x2b19190808081919, 0x2b19190808082b08, 0x2b19190808190819, 0x2b19190808191908,
+    0x2b191908082b0808, 0x2b19190819080819, 0x2b19190819081908, 0x2b19190819190808,
+    0x2b1919082b080808, 0x2b1919082b19192b, 0x2b19191908080819, 0x2b19191908081908,
+    0x2b19191908190808, 0x2b19191919080808, 0x2b1919192b192b08, 0x2b1919192b2b0819,
+    0x2b19192b08080808, 0x2b19192b1908192b, 0x2b19192b192b1908, 0x2b192b0808080819,
+    0x2b192b0808081908, 0x2b192b0808190808, 0x2b192b08082b192b, 0x2b192b0819080808,
+    0x2b192b082b2b2b19, 0x2b192b1908080808, 0x2b192b1919082b19, 0x2b192b191919082b,
+    0x2b192b2b2b190808, 0x2b2b080808080808, 0x2b2b080808081919, 0x2b2b080808082b2b,
+    0x2b2b080808191908, 0x2b2b0808082b082b, 0x2b2b0808082b2b2b, 0x2b2b080819080819,
+    0x2b2b080819081908, 0x2b2b080819190808, 0x2b2b08082b2b082b, 0x2b2b08082b2b2b2b,
+    0x2b2b081919080808, 0x2b2b0819192b1919, 0x2b2b082b0808082b, 0x2b2b082b08082b2b,
+    0x2b2b082b082b082b, 0x2b2b082b082b2b08, 0x2b2b082b082b2b2b, 0x2b2b082b2b08082b,
+    0x2b2b082b2b082b08, 0x2b2b082b2b082b2b, 0x2b2b082b2b2b2b08, 0x2b2b190808080819,
+    0x2b2b190808081908, 0x2b2b190808190808, 0x2b2b190819080808, 0x2b2b19082b082b19,
+    0x2b2b19082b2b1908, 0x2b2b191908080808, 0x2b2b191908192b19, 0x2b2b192b19190819,
+    0x2b2b2b0808082b2b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b082b, 0x2b2b2b1919191908,
+    0x2b2b2b192b08192b, 0x2b2b2b2b08082b08, 0x2b2b2b2b08082b2b, 0x2b2b2b2b082b0808,
+    0x2b2b2b2b082b082b, 0x2b2b2b2b082b2b08, 0x2b2b2b2b2b082b08, 0x2b2b2b2b2b2b2b2b,
+GGML_TABLE_END()
+
+GGML_TABLE_BEGIN(uint32_t, iq3xxs_grid, 256)
+    0x04040404, 0x04040414, 0x04040424, 0x04040c0c, 0x04040c1c, 0x04040c3e, 0x04041404, 0x04041414,
+    0x04041c0c, 0x04042414, 0x04043e1c, 0x04043e2c, 0x040c040c, 0x040c041c, 0x040c0c04, 0x040c0c14,
+    0x040c140c, 0x040c142c, 0x040c1c04, 0x040c1c14, 0x040c240c, 0x040c2c24, 0x040c3e04, 0x04140404,
+    0x04140414, 0x04140424, 0x04140c0c, 0x04141404, 0x04141414, 0x04141c0c, 0x04141c1c, 0x04141c3e,
+    0x04142c0c, 0x04142c3e, 0x04143e2c, 0x041c040c, 0x041c043e, 0x041c0c04, 0x041c0c14, 0x041c142c,
+    0x041c3e04, 0x04240c1c, 0x04241c3e, 0x04242424, 0x04242c3e, 0x04243e1c, 0x04243e2c, 0x042c040c,
+    0x042c043e, 0x042c1c14, 0x042c2c14, 0x04341c2c, 0x04343424, 0x043e0c04, 0x043e0c24, 0x043e0c34,
+    0x043e241c, 0x043e340c, 0x0c04040c, 0x0c04041c, 0x0c040c04, 0x0c040c14, 0x0c04140c, 0x0c04141c,
+    0x0c041c04, 0x0c041c14, 0x0c041c24, 0x0c04243e, 0x0c042c04, 0x0c0c0404, 0x0c0c0414, 0x0c0c0c0c,
+    0x0c0c1404, 0x0c0c1414, 0x0c14040c, 0x0c14041c, 0x0c140c04, 0x0c140c14, 0x0c14140c, 0x0c141c04,
+    0x0c143e14, 0x0c1c0404, 0x0c1c0414, 0x0c1c1404, 0x0c1c1c0c, 0x0c1c2434, 0x0c1c3434, 0x0c24040c,
+    0x0c24042c, 0x0c242c04, 0x0c2c1404, 0x0c2c1424, 0x0c2c2434, 0x0c2c3e0c, 0x0c34042c, 0x0c3e1414,
+    0x0c3e2404, 0x14040404, 0x14040414, 0x14040c0c, 0x14040c1c, 0x14041404, 0x14041414, 0x14041434,
+    0x14041c0c, 0x14042414, 0x140c040c, 0x140c041c, 0x140c042c, 0x140c0c04, 0x140c0c14, 0x140c140c,
+    0x140c1c04, 0x140c341c, 0x140c343e, 0x140c3e04, 0x14140404, 0x14140414, 0x14140c0c, 0x14140c3e,
+    0x14141404, 0x14141414, 0x14141c3e, 0x14142404, 0x14142c2c, 0x141c040c, 0x141c0c04, 0x141c0c24,
+    0x141c3e04, 0x141c3e24, 0x14241c2c, 0x14242c1c, 0x142c041c, 0x142c143e, 0x142c240c, 0x142c3e24,
+    0x143e040c, 0x143e041c, 0x143e0c34, 0x143e242c, 0x1c04040c, 0x1c040c04, 0x1c040c14, 0x1c04140c,
+    0x1c04141c, 0x1c042c04, 0x1c04342c, 0x1c043e14, 0x1c0c0404, 0x1c0c0414, 0x1c0c1404, 0x1c0c1c0c,
+    0x1c0c2424, 0x1c0c2434, 0x1c14040c, 0x1c14041c, 0x1c140c04, 0x1c14142c, 0x1c142c14, 0x1c143e14,
+    0x1c1c0c0c, 0x1c1c1c1c, 0x1c241c04, 0x1c24243e, 0x1c243e14, 0x1c2c0404, 0x1c2c0434, 0x1c2c1414,
+    0x1c2c2c2c, 0x1c340c24, 0x1c341c34, 0x1c34341c, 0x1c3e1c1c, 0x1c3e3404, 0x24040424, 0x24040c3e,
+    0x24041c2c, 0x24041c3e, 0x24042c1c, 0x24042c3e, 0x240c3e24, 0x24141404, 0x24141c3e, 0x24142404,
+    0x24143404, 0x24143434, 0x241c043e, 0x241c242c, 0x24240424, 0x24242c0c, 0x24243424, 0x242c142c,
+    0x242c241c, 0x242c3e04, 0x243e042c, 0x243e0c04, 0x243e0c14, 0x243e1c04, 0x2c040c14, 0x2c04240c,
+    0x2c043e04, 0x2c0c0404, 0x2c0c0434, 0x2c0c1434, 0x2c0c2c2c, 0x2c140c24, 0x2c141c14, 0x2c143e14,
+    0x2c1c0414, 0x2c1c2c1c, 0x2c240c04, 0x2c24141c, 0x2c24143e, 0x2c243e14, 0x2c2c0414, 0x2c2c1c0c,
+    0x2c342c04, 0x2c3e1424, 0x2c3e2414, 0x34041424, 0x34042424, 0x34042434, 0x34043424, 0x340c140c,
+    0x340c340c, 0x34140c3e, 0x34143424, 0x341c1c04, 0x341c1c34, 0x34242424, 0x342c042c, 0x342c2c14,
+    0x34341c1c, 0x343e041c, 0x343e140c, 0x3e04041c, 0x3e04042c, 0x3e04043e, 0x3e040c04, 0x3e041c14,
+    0x3e042c14, 0x3e0c1434, 0x3e0c2404, 0x3e140c14, 0x3e14242c, 0x3e142c14, 0x3e1c0404, 0x3e1c0c2c,
+    0x3e1c1c1c, 0x3e1c3404, 0x3e24140c, 0x3e24240c, 0x3e2c0404, 0x3e2c0414, 0x3e2c1424, 0x3e341c04,
+GGML_TABLE_END()
+
+GGML_TABLE_BEGIN(uint32_t, iq3s_grid, 512)
+    0x01010101, 0x01010103, 0x01010105, 0x0101010b, 0x0101010f, 0x01010301, 0x01010303, 0x01010305,
+    0x01010309, 0x0101030d, 0x01010501, 0x01010503, 0x0101050b, 0x01010707, 0x01010901, 0x01010905,
+    0x0101090b, 0x0101090f, 0x01010b03, 0x01010b07, 0x01010d01, 0x01010d05, 0x01010f03, 0x01010f09,
+    0x01010f0f, 0x01030101, 0x01030103, 0x01030105, 0x01030109, 0x01030301, 0x01030303, 0x0103030b,
+    0x01030501, 0x01030507, 0x0103050f, 0x01030703, 0x0103070b, 0x01030909, 0x01030d03, 0x01030d0b,
+    0x01030f05, 0x01050101, 0x01050103, 0x0105010b, 0x0105010f, 0x01050301, 0x01050307, 0x0105030d,
+    0x01050503, 0x0105050b, 0x01050701, 0x01050709, 0x01050905, 0x0105090b, 0x0105090f, 0x01050b03,
+    0x01050b07, 0x01050f01, 0x01050f07, 0x01070107, 0x01070303, 0x0107030b, 0x01070501, 0x01070505,
+    0x01070703, 0x01070707, 0x0107070d, 0x01070909, 0x01070b01, 0x01070b05, 0x01070d0f, 0x01070f03,
+    0x01070f0b, 0x01090101, 0x01090307, 0x0109030f, 0x01090503, 0x01090509, 0x01090705, 0x01090901,
+    0x01090907, 0x01090b03, 0x01090f01, 0x010b0105, 0x010b0109, 0x010b0501, 0x010b0505, 0x010b050d,
+    0x010b0707, 0x010b0903, 0x010b090b, 0x010b090f, 0x010b0d0d, 0x010b0f07, 0x010d010d, 0x010d0303,
+    0x010d0307, 0x010d0703, 0x010d0b05, 0x010d0f03, 0x010f0101, 0x010f0105, 0x010f0109, 0x010f0501,
+    0x010f0505, 0x010f050d, 0x010f0707, 0x010f0b01, 0x010f0b09, 0x03010101, 0x03010103, 0x03010105,
+    0x03010109, 0x03010301, 0x03010303, 0x03010307, 0x0301030b, 0x0301030f, 0x03010501, 0x03010505,
+    0x03010703, 0x03010709, 0x0301070d, 0x03010b09, 0x03010b0d, 0x03010d03, 0x03010f05, 0x03030101,
+    0x03030103, 0x03030107, 0x0303010d, 0x03030301, 0x03030309, 0x03030503, 0x03030701, 0x03030707,
+    0x03030903, 0x03030b01, 0x03030b05, 0x03030f01, 0x03030f0d, 0x03050101, 0x03050305, 0x0305030b,
+    0x0305030f, 0x03050501, 0x03050509, 0x03050705, 0x03050901, 0x03050907, 0x03050b0b, 0x03050d01,
+    0x03050f05, 0x03070103, 0x03070109, 0x0307010f, 0x03070301, 0x03070307, 0x03070503, 0x0307050f,
+    0x03070701, 0x03070709, 0x03070903, 0x03070d05, 0x03070f01, 0x03090107, 0x0309010b, 0x03090305,
+    0x03090309, 0x03090703, 0x03090707, 0x03090905, 0x0309090d, 0x03090b01, 0x03090b09, 0x030b0103,
+    0x030b0301, 0x030b0307, 0x030b0503, 0x030b0701, 0x030b0705, 0x030b0b03, 0x030d0501, 0x030d0509,
+    0x030d050f, 0x030d0909, 0x030d090d, 0x030f0103, 0x030f0107, 0x030f0301, 0x030f0305, 0x030f0503,
+    0x030f070b, 0x030f0903, 0x030f0d05, 0x030f0f01, 0x05010101, 0x05010103, 0x05010107, 0x0501010b,
+    0x0501010f, 0x05010301, 0x05010305, 0x05010309, 0x0501030d, 0x05010503, 0x05010507, 0x0501050f,
+    0x05010701, 0x05010705, 0x05010903, 0x05010907, 0x0501090b, 0x05010b01, 0x05010b05, 0x05010d0f,
+    0x05010f01, 0x05010f07, 0x05010f0b, 0x05030101, 0x05030105, 0x05030301, 0x05030307, 0x0503030f,
+    0x05030505, 0x0503050b, 0x05030703, 0x05030709, 0x05030905, 0x05030b03, 0x05050103, 0x05050109,
+    0x0505010f, 0x05050503, 0x05050507, 0x05050701, 0x0505070f, 0x05050903, 0x05050b07, 0x05050b0f,
+    0x05050f03, 0x05050f09, 0x05070101, 0x05070105, 0x0507010b, 0x05070303, 0x05070505, 0x05070509,
+    0x05070703, 0x05070707, 0x05070905, 0x05070b01, 0x05070d0d, 0x05090103, 0x0509010f, 0x05090501,
+    0x05090507, 0x05090705, 0x0509070b, 0x05090903, 0x05090f05, 0x05090f0b, 0x050b0109, 0x050b0303,
+    0x050b0505, 0x050b070f, 0x050b0901, 0x050b0b07, 0x050b0f01, 0x050d0101, 0x050d0105, 0x050d010f,
+    0x050d0503, 0x050d0b0b, 0x050d0d03, 0x050f010b, 0x050f0303, 0x050f050d, 0x050f0701, 0x050f0907,
+    0x050f0b01, 0x07010105, 0x07010303, 0x07010307, 0x0701030b, 0x0701030f, 0x07010505, 0x07010703,
+    0x07010707, 0x0701070b, 0x07010905, 0x07010909, 0x0701090f, 0x07010b03, 0x07010d07, 0x07010f03,
+    0x07030103, 0x07030107, 0x0703010b, 0x07030309, 0x07030503, 0x07030507, 0x07030901, 0x07030d01,
+    0x07030f05, 0x07030f0d, 0x07050101, 0x07050305, 0x07050501, 0x07050705, 0x07050709, 0x07050b01,
+    0x07070103, 0x07070301, 0x07070309, 0x07070503, 0x07070507, 0x0707050f, 0x07070701, 0x07070903,
+    0x07070907, 0x0707090f, 0x07070b0b, 0x07070f07, 0x07090107, 0x07090303, 0x0709030d, 0x07090505,
+    0x07090703, 0x07090b05, 0x07090d01, 0x07090d09, 0x070b0103, 0x070b0301, 0x070b0305, 0x070b050b,
+    0x070b0705, 0x070b0909, 0x070b0b0d, 0x070b0f07, 0x070d030d, 0x070d0903, 0x070f0103, 0x070f0107,
+    0x070f0501, 0x070f0505, 0x070f070b, 0x09010101, 0x09010109, 0x09010305, 0x09010501, 0x09010509,
+    0x0901050f, 0x09010705, 0x09010903, 0x09010b01, 0x09010f01, 0x09030105, 0x0903010f, 0x09030303,
+    0x09030307, 0x09030505, 0x09030701, 0x0903070b, 0x09030907, 0x09030b03, 0x09030b0b, 0x09050103,
+    0x09050107, 0x09050301, 0x0905030b, 0x09050503, 0x09050707, 0x09050901, 0x09050b0f, 0x09050d05,
+    0x09050f01, 0x09070109, 0x09070303, 0x09070307, 0x09070501, 0x09070505, 0x09070703, 0x0907070b,
+    0x09090101, 0x09090105, 0x09090509, 0x0909070f, 0x09090901, 0x09090f03, 0x090b010b, 0x090b010f,
+    0x090b0503, 0x090b0d05, 0x090d0307, 0x090d0709, 0x090d0d01, 0x090f0301, 0x090f030b, 0x090f0701,
+    0x090f0907, 0x090f0b03, 0x0b010105, 0x0b010301, 0x0b010309, 0x0b010505, 0x0b010901, 0x0b010909,
+    0x0b01090f, 0x0b010b05, 0x0b010d0d, 0x0b010f09, 0x0b030103, 0x0b030107, 0x0b03010b, 0x0b030305,
+    0x0b030503, 0x0b030705, 0x0b030f05, 0x0b050101, 0x0b050303, 0x0b050507, 0x0b050701, 0x0b05070d,
+    0x0b050b07, 0x0b070105, 0x0b07010f, 0x0b070301, 0x0b07050f, 0x0b070909, 0x0b070b03, 0x0b070d0b,
+    0x0b070f07, 0x0b090103, 0x0b090109, 0x0b090501, 0x0b090705, 0x0b09090d, 0x0b0b0305, 0x0b0b050d,
+    0x0b0b0b03, 0x0b0b0b07, 0x0b0d0905, 0x0b0f0105, 0x0b0f0109, 0x0b0f0505, 0x0d010303, 0x0d010307,
+    0x0d01030b, 0x0d010703, 0x0d010707, 0x0d010d01, 0x0d030101, 0x0d030501, 0x0d03050f, 0x0d030d09,
+    0x0d050305, 0x0d050709, 0x0d050905, 0x0d050b0b, 0x0d050d05, 0x0d050f01, 0x0d070101, 0x0d070309,
+    0x0d070503, 0x0d070901, 0x0d09050b, 0x0d090907, 0x0d090d05, 0x0d0b0101, 0x0d0b0107, 0x0d0b0709,
+    0x0d0b0d01, 0x0d0d010b, 0x0d0d0901, 0x0d0f0303, 0x0d0f0307, 0x0f010101, 0x0f010109, 0x0f01010f,
+    0x0f010501, 0x0f010505, 0x0f01070d, 0x0f010901, 0x0f010b09, 0x0f010d05, 0x0f030105, 0x0f030303,
+    0x0f030509, 0x0f030907, 0x0f03090b, 0x0f050103, 0x0f050109, 0x0f050301, 0x0f05030d, 0x0f050503,
+    0x0f050701, 0x0f050b03, 0x0f070105, 0x0f070705, 0x0f07070b, 0x0f070b07, 0x0f090103, 0x0f09010b,
+    0x0f090307, 0x0f090501, 0x0f090b01, 0x0f0b0505, 0x0f0b0905, 0x0f0d0105, 0x0f0d0703, 0x0f0f0101,
+GGML_TABLE_END()
+
+#define NGRID_IQ2XXS 512
+GGML_TABLE_BEGIN(uint64_t, iq1s_grid, NGRID_IQ2XXS)
+    0xffffffffffff0101, 0xffffffffff01ff00, 0xffffffffff010100, 0xffffffff00000000,
+    0xffffffff01ff00ff, 0xffffffff01ff0001, 0xffffffff0101ffff, 0xffffffff0101ff01,
+    0xffffff00ff000000, 0xffffff000000ff00, 0xffffff00000000ff, 0xffffff0000000100,
+    0xffffff0000010000, 0xffffff0001000000, 0xffffff01ffff00ff, 0xffffff01ff01ff00,
+    0xffffff01ff010100, 0xffffff0100000001, 0xffffff0101ffff00, 0xffffff0101ff0101,
+    0xffffff0101010100, 0xffff00ffff00ff01, 0xffff00ffff0000ff, 0xffff00ff00ff0100,
+    0xffff00ff0100ff00, 0xffff00ff010001ff, 0xffff0000ff0101ff, 0xffff000000ffff00,
+    0xffff000000000000, 0xffff00000001ff01, 0xffff000001000101, 0xffff0000010100ff,
+    0xffff0001ffff0100, 0xffff00010000ff00, 0xffff000100010101, 0xffff000101000000,
+    0xffff01ffffff0000, 0xffff01ffff01ffff, 0xffff01ffff010100, 0xffff01ff00000000,
+    0xffff01ff01ffffff, 0xffff01ff01ff0001, 0xffff01ff0101ffff, 0xffff01ff01010001,
+    0xffff0100ffffff01, 0xffff01000000ffff, 0xffff010000000100, 0xffff010001ff01ff,
+    0xffff010001000000, 0xffff0101ff000000, 0xffff0101000101ff, 0xffff010101ffff01,
+    0xffff01010101ff00, 0xff00ffffff000000, 0xff00ffff00ffff00, 0xff00ffff00000001,
+    0xff00ffff000001ff, 0xff00ffff01010000, 0xff00ff00ffff0000, 0xff00ff00ff00ff00,
+    0xff00ff00ff0000ff, 0xff00ff00ff000100, 0xff00ff00ff010001, 0xff00ff0000ff0001,
+    0xff00ff000000ffff, 0xff00ff0000000000, 0xff00ff000001ff00, 0xff00ff0000010100,
+    0xff00ff0001ff0000, 0xff00ff000100ff00, 0xff00ff0001000100, 0xff00ff01ff000000,
+    0xff00ff0100ff0000, 0xff00ff01000001ff, 0xff00ff0101010001, 0xff0000ff00000000,
+    0xff0000ff0001ff00, 0xff0000ff00010100, 0xff000000ffff0101, 0xff000000ff000000,
+    0xff000000ff01ff00, 0xff00000000ff0000, 0xff0000000000ff00, 0xff000000000000ff,
+    0xff00000000000000, 0xff00000000000001, 0xff00000000000100, 0xff0000000001ffff,
+    0xff00000000010000, 0xff00000001000000, 0xff00000001010100, 0xff000001ff00ff01,
+    0xff000001ff0100ff, 0xff00000100000000, 0xff0000010001ff00, 0xff00000101ff0100,
+    0xff0000010100ff00, 0xff0001ff00ff00ff, 0xff0001ff00000101, 0xff0001ff000100ff,
+    0xff0001ff01000000, 0xff000100ff0001ff, 0xff0001000000ff01, 0xff00010000000000,
+    0xff00010000010001, 0xff00010000010100, 0xff00010001ffff00, 0xff00010001ff0101,
+    0xff00010001010000, 0xff000101ffffffff, 0xff000101ff000101, 0xff00010101ff00ff,
+    0xff00010101000001, 0xff000101010100ff, 0xff01ffffff000101, 0xff01ffffff01ffff,
+    0xff01ffffff01ff01, 0xff01ffffff0101ff, 0xff01ffff00000000, 0xff01ffff01ff0001,
+    0xff01ffff0101ff01, 0xff01ff00ff000000, 0xff01ff0000ff0100, 0xff01ff000000ff01,
+    0xff01ff0000010000, 0xff01ff00010000ff, 0xff01ff01ff01ff00, 0xff01ff0100000101,
+    0xff0100ffffff0000, 0xff0100ffff010000, 0xff0100ff01ff00ff, 0xff0100ff01000100,
+    0xff0100ff010100ff, 0xff010000ffffff01, 0xff01000000000000, 0xff0100000101ff00,
+    0xff010001ffff00ff, 0xff010001ff000100, 0xff01000100ffff00, 0xff01000100010001,
+    0xff01000101ff0001, 0xff010001010001ff, 0xff0101ffffffffff, 0xff0101ffff01ffff,
+    0xff0101ffff010101, 0xff0101ff0000ff00, 0xff0101ff01010001, 0xff010100ff000000,
+    0xff010100ff01ff01, 0xff01010000ff0001, 0xff01010000000100, 0xff01010001000000,
+    0xff0101010100ffff, 0x00ffffff0000ff01, 0x00ffffff000000ff, 0x00ffffff00000100,
+    0x00ffffff00010000, 0x00ffff00ffff0001, 0x00ffff00ff0000ff, 0x00ffff00ff000100,
+    0x00ffff0000000000, 0x00ffff0001000100, 0x00ffff0001010001, 0x00ffff01ff00ff01,
+    0x00ffff0100ff0100, 0x00ffff010000ff00, 0x00ffff01000100ff, 0x00ffff0101ff00ff,
+    0x00ffff010101ff00, 0x00ff00ffffffffff, 0x00ff00ffffff01ff, 0x00ff00ffff000101,
+    0x00ff00ff00000000, 0x00ff00ff000101ff, 0x00ff00ff01010101, 0x00ff0000ff000000,
+    0x00ff0000ff01ffff, 0x00ff000000ff0000, 0x00ff00000000ff00, 0x00ff0000000000ff,
+    0x00ff000000000000, 0x00ff000000000001, 0x00ff000000000100, 0x00ff000000010000,
+    0x00ff000001ffff01, 0x00ff000001000000, 0x00ff0001ff000101, 0x00ff000100ffffff,
+    0x00ff000100000000, 0x00ff0001010001ff, 0x00ff01ffff000000, 0x00ff01ff0001ff00,
+    0x00ff01ff01ff0100, 0x00ff0100ff01ff01, 0x00ff010000ff00ff, 0x00ff010000ff0101,
+    0x00ff010000000000, 0x00ff010000010101, 0x00ff01000100ff00, 0x00ff010001010000,
+    0x00ff0101ffffff00, 0x00ff01010000ff01, 0x00ff010100000100, 0x00ff010101ff0000,
+    0x0000ffffffff0100, 0x0000ffffff00ff00, 0x0000ffffff0000ff, 0x0000ffffff010000,
+    0x0000ffff00000000, 0x0000ffff00010101, 0x0000ffff01ffff01, 0x0000ffff01000100,
+    0x0000ff00ff000000, 0x0000ff00ff01ff00, 0x0000ff00ff0101ff, 0x0000ff0000ff0000,
+    0x0000ff000000ff00, 0x0000ff00000000ff, 0x0000ff0000000000, 0x0000ff0000000001,
+    0x0000ff0000000100, 0x0000ff0000010000, 0x0000ff0001ffffff, 0x0000ff0001ff01ff,
+    0x0000ff0001000000, 0x0000ff000101ffff, 0x0000ff01ffff0101, 0x0000ff01ff010000,
+    0x0000ff0100000000, 0x0000ff0101000101, 0x000000ffffff0001, 0x000000ffff000000,
+    0x000000ff00ff0000, 0x000000ff0000ff00, 0x000000ff000000ff, 0x000000ff00000000,
+    0x000000ff00000001, 0x000000ff00000100, 0x000000ff00010000, 0x000000ff01000000,
+    0x000000ff0101ff00, 0x00000000ffff0000, 0x00000000ff00ff00, 0x00000000ff0000ff,
+    0x00000000ff000000, 0x00000000ff000001, 0x00000000ff000100, 0x00000000ff010000,
+    0x0000000000ffff00, 0x0000000000ff00ff, 0x0000000000ff0000, 0x0000000000ff0001,
+    0x0000000000ff0100, 0x000000000000ffff, 0x000000000000ff00, 0x000000000000ff01,
+    0x00000000000000ff, 0x0000000000000001, 0x00000000000001ff, 0x0000000000000100,
+    0x0000000000000101, 0x000000000001ff00, 0x00000000000100ff, 0x0000000000010000,
+    0x0000000000010001, 0x0000000000010100, 0x0000000001ff0000, 0x000000000100ff00,
+    0x00000000010000ff, 0x0000000001000000, 0x0000000001000001, 0x0000000001000100,
+    0x0000000001010000, 0x00000001ffff01ff, 0x00000001ff000000, 0x0000000100ff0000,
+    0x000000010000ff00, 0x00000001000000ff, 0x0000000100000000, 0x0000000100000001,
+    0x0000000100000100, 0x0000000100010000, 0x0000000101000000, 0x000001ffff00ff00,
+    0x000001ffff010001, 0x000001ffff0101ff, 0x000001ff00ffff01, 0x000001ff0000ffff,
+    0x000001ff00000000, 0x000001ff010000ff, 0x000001ff01010100, 0x00000100ffff0100,
+    0x00000100ff000000, 0x0000010000ff0000, 0x000001000000ff00, 0x00000100000000ff,
+    0x0000010000000000, 0x0000010000000001, 0x0000010000000100, 0x0000010000010000,
+    0x0000010001000000, 0x000001000101ff01, 0x00000101ffff0001, 0x00000101ff01ffff,
+    0x0000010100000000, 0x0000010101010100, 0x0001ffffff000000, 0x0001ffff00ffffff,
+    0x0001ffff00000100, 0x0001ffff0001ff00, 0x0001ffff01000000, 0x0001ff00ffffff00,
+    0x0001ff00ffff01ff, 0x0001ff00ff010000, 0x0001ff0000000000, 0x0001ff0000010001,
+    0x0001ff0001ff0000, 0x0001ff0001010100, 0x0001ff01ff0000ff, 0x0001ff01ff000001,
+    0x0001ff0100ffffff, 0x0001ff010001ffff, 0x0001ff01000101ff, 0x0001ff010100ff01,
+    0x000100ffff00ffff, 0x000100ffff00ff01, 0x000100ffff000100, 0x000100ff00000000,
+    0x000100ff000101ff, 0x000100ff01ff0101, 0x000100ff0100ffff, 0x000100ff01010101,
+    0x00010000ff000000, 0x00010000ff010100, 0x0001000000ff0000, 0x000100000000ff00,
+    0x00010000000000ff, 0x0001000000000000, 0x0001000000000001, 0x0001000000000100,
+    0x0001000000010000, 0x0001000001ffff01, 0x0001000001000000, 0x0001000100ff0101,
+    0x0001000100000000, 0x00010001010100ff, 0x000101ffffff01ff, 0x000101ffffff0101,
+    0x000101ff00010000, 0x000101ff01ff0000, 0x000101ff0100ff01, 0x00010100ffff0000,
+    0x0001010000000000, 0x000101000001ffff, 0x0001010000010101, 0x00010100010001ff,
+    0x00010101ff00ff00, 0x00010101ff010001, 0x0001010100ffffff, 0x0001010100ff01ff,
+    0x00010101000101ff, 0x0001010101ff0000, 0x000101010100ff01, 0x0001010101000101,
+    0x01ffffffffff0101, 0x01ffffffff01ffff, 0x01ffffffff01ff01, 0x01ffffffff0101ff,
+    0x01ffffffff010101, 0x01ffffff00000000, 0x01ffffff01ff01ff, 0x01ffffff01000101,
+    0x01ffffff0101ff01, 0x01ffffff010100ff, 0x01ffff000000ff00, 0x01ffff0000000001,
+    0x01ffff00000001ff, 0x01ffff0000010000, 0x01ffff0001ff0000, 0x01ffff01ffffffff,
+    0x01ffff01ffff01ff, 0x01ffff01ff000000, 0x01ffff01ff01ffff, 0x01ffff01ff0101ff,
+    0x01ffff010100ffff, 0x01ff00ffffff0000, 0x01ff00ffff010000, 0x01ff00ff00ffff01,
+    0x01ff0000ff0000ff, 0x01ff000000000000, 0x01ff00000001ff01, 0x01ff000001ffffff,
+    0x01ff000001010100, 0x01ff0001ffffff01, 0x01ff0001ff010001, 0x01ff000101ff0100,
+    0x01ff000101000001, 0x01ff0001010100ff, 0x01ff01ffff00ffff, 0x01ff01ff00010001,
+    0x01ff01ff01000000, 0x01ff01ff010101ff, 0x01ff0100ff000001, 0x01ff010000ffff00,
+    0x01ff010000000100, 0x01ff010001ff01ff, 0x01ff01000101ffff, 0x01ff0101ffff00ff,
+    0x01ff0101ffff0101, 0x01ff0101ff0101ff, 0x01ff010100010000, 0x0100ffff00ff00ff,
+    0x0100ffff00ff0001, 0x0100ffff00000100, 0x0100ffff0100ff00, 0x0100ff00ffff0000,
+    0x0100ff00ff00ffff, 0x0100ff00ff00ff01, 0x0100ff00ff000100, 0x0100ff00ff010000,
+    0x0100ff0000000000, 0x0100ff00000100ff, 0x0100ff0001ff0101, 0x0100ff0001010101,
+    0x0100ff0100ff00ff, 0x0100ff0100ff0001, 0x0100ff0100000100, 0x0100ff0100010001,
+    0x0100ff0101000000, 0x010000ffff00ff00, 0x010000ff0000ffff, 0x010000ff00000000,
+    0x010000ff010001ff, 0x010000ff01010001, 0x01000000ffffff00, 0x01000000ffff0101,
+    0x01000000ff000000, 0x01000000ff0100ff, 0x01000000ff010101, 0x0100000000ff0000,
+    0x010000000000ff00, 0x01000000000000ff, 0x0100000000000000, 0x0100000000000001,
+    0x0100000000000100, 0x0100000000010000, 0x0100000001000000, 0x0100000100000000,
+    0x01000001000101ff, 0x0100000101ffff01, 0x010001ffff000101, 0x010001ff00ff0100,
+    0x010001ff0000ff00, 0x010001ff000100ff, 0x010001ff01ffffff, 0x01000100ffff0000,
+    0x01000100ff0001ff, 0x0100010000000000, 0x010001000001ff00, 0x0100010001ff0000,
+    0x01000100010000ff, 0x0100010001000101, 0x01000101ff00ff01, 0x0100010100ff0100,
+    0x010001010000ffff, 0x0100010101010001, 0x0101ffffffff0101, 0x0101ffffff0001ff,
+    0x0101ffffff01ffff, 0x0101ffffff010101, 0x0101ffff00000000, 0x0101ffff0101ffff,
+    0x0101ffff010101ff, 0x0101ff00ff000000, 0x0101ff0000ff0100, 0x0101ff000000ff00,
+    0x0101ff0000010000, 0x0101ff00010000ff, 0x0101ff0001000001, 0x0101ff01ff010101,
+    0x0101ff0100000000, 0x0101ff010101ff00, 0x010100ffffff0000, 0x010100ffff010000,
+    0x010100ff00ff01ff, 0x010100ff000000ff, 0x010100ff00000101, 0x010100ff01ffff00,
+    0x01010000ffffff01, 0x01010000ff000100, 0x01010000ff01ff01, 0x0101000000000000,
+    0x01010000000100ff, 0x010100000101ff01, 0x01010001ffff0000, 0x01010001ff00ffff,
+    0x01010001ff010000, 0x0101000101ffffff, 0x0101000101ff01ff, 0x0101000101010101,
+    0x010101ffff01ffff, 0x010101ff00000000, 0x010101ff0001ff01, 0x010101ff0101ffff,
+    0x010101ff010101ff, 0x01010100ffffffff, 0x01010100ff000001, 0x010101000000ff00,
+    0x0101010001010000, 0x0101010100ff0001, 0x010101010001ff01, 0x010101010101ffff,
+GGML_TABLE_END()
+
+#endif // GGML_COMMON_IMPL
@@ -2,6 +2,9 @@
 #include "ggml.h"
 #include "ggml-backend-impl.h"

+#define GGML_COMMON_IMPL_CUDA
+#include "ggml-common.h"
+
 #include <algorithm>
 #include <assert.h>
 #include <atomic>
@@ -1569,746 +1572,6 @@ static __global__ void dequantize_block_q6_K(const void * __restrict__ vx, dst_t
 #endif
 }

-static const __device__ uint64_t iq2xxs_grid[256] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808,
-    0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819,
-    0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819,
-    0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b,
-    0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808,
-    0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08,
-    0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b,
-    0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819,
-    0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08,
-    0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808,
-    0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08,
-    0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808,
-    0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808,
-    0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919,
-    0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819,
-    0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08,
-    0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908,
-    0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819,
-    0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808,
-    0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808,
-    0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908,
-    0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808,
-    0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08,
-    0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819,
-    0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819,
-    0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819,
-    0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908,
-    0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19,
-    0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819,
-    0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b,
-    0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808,
-    0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908,
-    0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08,
-    0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08,
-    0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908,
-    0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819,
-    0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808,
-    0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808,
-    0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19,
-    0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819,
-    0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919,
-    0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b,
-    0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08,
-    0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808,
-    0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908,
-    0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b,
-    0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819,
-    0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08,
-    0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08,
-    0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808,
-    0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b,
-    0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b,
-    0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908,
-    0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819,
-    0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808,
-    0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908,
-    0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b,
-    0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808,
-    0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b,
-    0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b,
-    0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808,
-    0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19,
-    0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908,
-};
-
-static const __device__ uint64_t iq2xs_grid[512] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
-    0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
-    0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
-    0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
-    0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808,
-    0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08, 0x080808082b190819,
-    0x080808082b191908, 0x080808082b192b19, 0x080808082b2b0808, 0x0808081908080819,
-    0x0808081908081908, 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808,
-    0x080808190819082b, 0x0808081908191919, 0x0808081908192b08, 0x0808081908192b2b,
-    0x08080819082b0819, 0x08080819082b1908, 0x0808081919080808, 0x080808191908082b,
-    0x0808081919081919, 0x0808081919082b08, 0x0808081919190819, 0x0808081919191908,
-    0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819, 0x080808192b081908,
-    0x080808192b190808, 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b08081919,
-    0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808,
-    0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808, 0x0808082b19191919,
-    0x0808082b2b080808, 0x0808082b2b082b2b, 0x0808190808080819, 0x0808190808081908,
-    0x080819080808192b, 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b,
-    0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908,
-    0x0808190819080808, 0x080819081908082b, 0x0808190819081919, 0x0808190819082b08,
-    0x0808190819190819, 0x0808190819191908, 0x080819081919192b, 0x08081908192b0808,
-    0x080819082b080819, 0x080819082b081908, 0x080819082b190808, 0x0808191908080808,
-    0x080819190808082b, 0x0808191908081919, 0x0808191908082b08, 0x0808191908190819,
-    0x0808191908191908, 0x08081919082b0808, 0x0808191919080819, 0x0808191919081908,
-    0x0808191919190808, 0x08081919192b0819, 0x080819192b080808, 0x0808192b08080819,
-    0x0808192b08081908, 0x0808192b08190808, 0x0808192b082b192b, 0x0808192b19080808,
-    0x0808192b1908082b, 0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b,
-    0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b, 0x08082b0808190819,
-    0x08082b0808191908, 0x08082b08082b0808, 0x08082b08082b1919, 0x08082b0819080819,
-    0x08082b0819081908, 0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808,
-    0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819, 0x08082b1908081908,
-    0x08082b1908190808, 0x08082b1919080808, 0x08082b192b080819, 0x08082b192b082b19,
-    0x08082b2b08080808, 0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b,
-    0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908, 0x081908080808192b,
-    0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, 0x0819080808191919,
-    0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808,
-    0x081908081908082b, 0x0819080819081919, 0x0819080819082b08, 0x0819080819190819,
-    0x0819080819191908, 0x08190808192b0808, 0x08190808192b2b2b, 0x081908082b080819,
-    0x081908082b081908, 0x081908082b190808, 0x0819081908080808, 0x081908190808082b,
-    0x0819081908081919, 0x0819081908082b08, 0x0819081908190819, 0x0819081908191908,
-    0x08190819082b0808, 0x0819081919080819, 0x0819081919081908, 0x0819081919190808,
-    0x081908192b080808, 0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819,
-    0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808, 0x0819082b19080808,
-    0x0819082b192b0808, 0x0819190808080808, 0x081919080808082b, 0x0819190808081919,
-    0x0819190808082b08, 0x0819190808190819, 0x0819190808191908, 0x08191908082b0808,
-    0x0819190819080819, 0x0819190819081908, 0x0819190819082b19, 0x0819190819190808,
-    0x08191908192b1908, 0x081919082b080808, 0x0819191908080819, 0x0819191908081908,
-    0x0819191908190808, 0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908,
-    0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808,
-    0x08192b080819082b, 0x08192b0819080808, 0x08192b0819191908, 0x08192b082b08192b,
-    0x08192b1908080808, 0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819,
-    0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919,
-    0x082b080808082b08, 0x082b080808082b2b, 0x082b080808190819, 0x082b080808191908,
-    0x082b0808082b0808, 0x082b080819080819, 0x082b080819081908, 0x082b080819190808,
-    0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819, 0x082b081908081908,
-    0x082b081908190808, 0x082b081919080808, 0x082b081919082b08, 0x082b0819192b1919,
-    0x082b082b08080808, 0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08,
-    0x082b190808080819, 0x082b190808081908, 0x082b190808190808, 0x082b1908082b2b19,
-    0x082b190819080808, 0x082b191908080808, 0x082b191919080819, 0x082b19191919082b,
-    0x082b19192b192b19, 0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b,
-    0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b, 0x082b2b08082b0808,
-    0x082b2b0819191919, 0x082b2b082b082b08, 0x082b2b082b2b082b, 0x082b2b19192b2b08,
-    0x082b2b192b190808, 0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b,
-    0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, 0x1908080808081908,
-    0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, 0x190808080819082b,
-    0x1908080808191919, 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908,
-    0x1908080819080808, 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08,
-    0x1908080819082b2b, 0x1908080819190819, 0x1908080819191908, 0x19080808192b0808,
-    0x19080808192b1919, 0x190808082b080819, 0x190808082b081908, 0x190808082b190808,
-    0x1908081908080808, 0x190808190808082b, 0x1908081908081919, 0x1908081908082b08,
-    0x1908081908190819, 0x1908081908191908, 0x19080819082b0808, 0x1908081919080819,
-    0x1908081919081908, 0x1908081919190808, 0x190808192b080808, 0x190808192b081919,
-    0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908, 0x1908082b08190808,
-    0x1908082b0819082b, 0x1908082b082b2b19, 0x1908082b19080808, 0x1908190808080808,
-    0x190819080808082b, 0x1908190808081919, 0x1908190808082b08, 0x1908190808190819,
-    0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808, 0x1908190819080819,
-    0x1908190819081908, 0x1908190819190808, 0x190819082b080808, 0x190819082b191908,
-    0x1908191908080819, 0x1908191908081908, 0x1908191908190808, 0x19081919082b1908,
-    0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808, 0x1908192b08082b2b,
-    0x1908192b19081908, 0x1908192b19190808, 0x19082b0808080819, 0x19082b0808081908,
-    0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908,
-    0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819, 0x19082b1919081908,
-    0x19082b1919190808, 0x19082b19192b2b19, 0x19082b2b08081908, 0x1919080808080808,
-    0x191908080808082b, 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819,
-    0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08, 0x1919080819080819,
-    0x1919080819081908, 0x1919080819190808, 0x191908082b080808, 0x1919081908080819,
-    0x1919081908081908, 0x1919081908190808, 0x1919081908191919, 0x1919081919080808,
-    0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908, 0x1919082b2b2b2b2b,
-    0x1919190808080819, 0x1919190808081908, 0x1919190808190808, 0x19191908082b0819,
-    0x1919190819080808, 0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819,
-    0x1919191908080808, 0x1919191908082b08, 0x191919192b080808, 0x191919192b082b08,
-    0x1919192b082b0819, 0x1919192b192b2b08, 0x1919192b2b2b0819, 0x19192b0808080808,
-    0x19192b0808191908, 0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19,
-    0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b, 0x19192b2b2b081919,
-    0x192b080808080819, 0x192b080808081908, 0x192b080808190808, 0x192b080819080808,
-    0x192b080819191908, 0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19,
-    0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b, 0x192b082b2b19082b,
-    0x192b190808080808, 0x192b19080819192b, 0x192b191908190808, 0x192b191919080808,
-    0x192b191919081919, 0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b,
-    0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908, 0x192b2b2b192b082b,
-    0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08,
-    0x2b08080808190819, 0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b,
-    0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808082b080808,
-    0x2b0808082b08082b, 0x2b0808082b2b2b08, 0x2b0808082b2b2b2b, 0x2b08081908080819,
-    0x2b08081908081908, 0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808,
-    0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808, 0x2b08082b082b0808,
-    0x2b08082b2b080808, 0x2b08082b2b08082b, 0x2b08082b2b2b0808, 0x2b08082b2b2b2b08,
-    0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b,
-    0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, 0x2b0819082b082b19,
-    0x2b08191908080808, 0x2b08191919081908, 0x2b0819192b2b1919, 0x2b08192b08192b08,
-    0x2b08192b192b2b2b, 0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919,
-    0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b, 0x2b082b082b2b2b08,
-    0x2b082b190808192b, 0x2b082b2b082b082b, 0x2b082b2b2b080808, 0x2b082b2b2b082b08,
-    0x2b082b2b2b19192b, 0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908,
-    0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b, 0x2b1908082b081908,
-    0x2b19081908080808, 0x2b190819082b082b, 0x2b190819192b1908, 0x2b19082b1919192b,
-    0x2b19082b2b082b19, 0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908,
-    0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19, 0x2b1919192b190808,
-    0x2b1919192b19082b, 0x2b19192b19080819, 0x2b192b0819190819, 0x2b192b082b2b192b,
-    0x2b192b1919082b19, 0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808,
-    0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b, 0x2b2b0808082b0808,
-    0x2b2b0808082b2b2b, 0x2b2b08082b2b0808, 0x2b2b081919190819, 0x2b2b081919192b19,
-    0x2b2b08192b2b192b, 0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08,
-    0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808, 0x2b2b190819080808,
-    0x2b2b19082b191919, 0x2b2b192b192b1919, 0x2b2b192b2b192b08, 0x2b2b2b0808082b2b,
-    0x2b2b2b08082b0808, 0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808,
-    0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908, 0x2b2b2b192b08192b,
-    0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b,
-};
-
-static const __device__ uint64_t iq2s_grid[1024] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
-    0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
-    0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
-    0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
-    0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x08080808192b192b,
-    0x08080808192b2b19, 0x080808082b080808, 0x080808082b08082b, 0x080808082b081919,
-    0x080808082b082b08, 0x080808082b190819, 0x080808082b191908, 0x080808082b2b0808,
-    0x080808082b2b1919, 0x080808082b2b2b2b, 0x0808081908080819, 0x0808081908081908,
-    0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, 0x080808190819082b,
-    0x0808081908191919, 0x0808081908192b08, 0x08080819082b0819, 0x08080819082b1908,
-    0x0808081919080808, 0x080808191908082b, 0x0808081919081919, 0x0808081919082b08,
-    0x0808081919190819, 0x0808081919191908, 0x080808191919192b, 0x0808081919192b19,
-    0x08080819192b0808, 0x08080819192b1919, 0x08080819192b2b08, 0x080808192b080819,
-    0x080808192b081908, 0x080808192b190808, 0x080808192b19082b, 0x080808192b191919,
-    0x080808192b2b0819, 0x080808192b2b1908, 0x0808082b08080808, 0x0808082b0808082b,
-    0x0808082b08081919, 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908,
-    0x0808082b082b0808, 0x0808082b082b2b2b, 0x0808082b19080819, 0x0808082b19081908,
-    0x0808082b1908192b, 0x0808082b19082b19, 0x0808082b19190808, 0x0808082b19191919,
-    0x0808082b2b080808, 0x0808082b2b081919, 0x0808082b2b082b2b, 0x0808082b2b191908,
-    0x0808082b2b2b082b, 0x0808190808080819, 0x0808190808081908, 0x080819080808192b,
-    0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, 0x0808190808191919,
-    0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, 0x08081908082b192b,
-    0x08081908082b2b19, 0x0808190819080808, 0x080819081908082b, 0x0808190819081919,
-    0x0808190819082b08, 0x0808190819082b2b, 0x0808190819190819, 0x0808190819191908,
-    0x080819081919192b, 0x0808190819192b19, 0x08081908192b0808, 0x08081908192b082b,
-    0x08081908192b1919, 0x080819082b080819, 0x080819082b081908, 0x080819082b08192b,
-    0x080819082b082b19, 0x080819082b190808, 0x080819082b191919, 0x080819082b192b08,
-    0x080819082b2b0819, 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b,
-    0x0808191908081919, 0x0808191908082b08, 0x0808191908082b2b, 0x0808191908190819,
-    0x0808191908191908, 0x080819190819192b, 0x0808191908192b19, 0x08081919082b0808,
-    0x08081919082b1919, 0x08081919082b2b08, 0x0808191919080819, 0x0808191919081908,
-    0x080819191908192b, 0x0808191919082b19, 0x0808191919190808, 0x080819191919082b,
-    0x0808191919191919, 0x0808191919192b08, 0x08081919192b0819, 0x08081919192b1908,
-    0x080819192b080808, 0x080819192b08082b, 0x080819192b081919, 0x080819192b082b08,
-    0x080819192b190819, 0x080819192b191908, 0x080819192b2b0808, 0x0808192b08080819,
-    0x0808192b08081908, 0x0808192b0808192b, 0x0808192b08082b19, 0x0808192b08190808,
-    0x0808192b08191919, 0x0808192b19080808, 0x0808192b19081919, 0x0808192b19082b08,
-    0x0808192b19190819, 0x0808192b19191908, 0x0808192b192b0808, 0x0808192b2b080819,
-    0x0808192b2b081908, 0x0808192b2b190808, 0x08082b0808080808, 0x08082b080808082b,
-    0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808190819, 0x08082b0808191908,
-    0x08082b080819192b, 0x08082b0808192b19, 0x08082b08082b0808, 0x08082b08082b1919,
-    0x08082b08082b2b2b, 0x08082b0819080819, 0x08082b0819081908, 0x08082b081908192b,
-    0x08082b0819082b19, 0x08082b0819190808, 0x08082b081919082b, 0x08082b0819191919,
-    0x08082b0819192b08, 0x08082b08192b0819, 0x08082b08192b1908, 0x08082b082b080808,
-    0x08082b082b081919, 0x08082b082b191908, 0x08082b082b2b2b2b, 0x08082b1908080819,
-    0x08082b1908081908, 0x08082b1908190808, 0x08082b190819082b, 0x08082b1908191919,
-    0x08082b1908192b08, 0x08082b19082b0819, 0x08082b1919080808, 0x08082b1919081919,
-    0x08082b1919082b08, 0x08082b1919190819, 0x08082b1919191908, 0x08082b19192b0808,
-    0x08082b192b080819, 0x08082b192b190808, 0x08082b2b08080808, 0x08082b2b08190819,
-    0x08082b2b08191908, 0x08082b2b082b082b, 0x08082b2b082b2b08, 0x08082b2b082b2b2b,
-    0x08082b2b19190808, 0x08082b2b2b192b19, 0x0819080808080819, 0x0819080808081908,
-    0x081908080808192b, 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b,
-    0x0819080808191919, 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908,
-    0x08190808082b192b, 0x0819080819080808, 0x081908081908082b, 0x0819080819081919,
-    0x0819080819082b08, 0x0819080819190819, 0x0819080819191908, 0x081908081919192b,
-    0x0819080819192b19, 0x08190808192b0808, 0x08190808192b082b, 0x08190808192b1919,
-    0x08190808192b2b08, 0x081908082b080819, 0x081908082b081908, 0x081908082b08192b,
-    0x081908082b190808, 0x081908082b191919, 0x081908082b192b08, 0x081908082b2b0819,
-    0x081908082b2b1908, 0x0819081908080808, 0x081908190808082b, 0x0819081908081919,
-    0x0819081908082b08, 0x0819081908082b2b, 0x0819081908190819, 0x0819081908191908,
-    0x081908190819192b, 0x0819081908192b19, 0x08190819082b0808, 0x08190819082b082b,
-    0x08190819082b1919, 0x08190819082b2b08, 0x0819081919080819, 0x0819081919081908,
-    0x081908191908192b, 0x0819081919082b19, 0x0819081919190808, 0x081908191919082b,
-    0x0819081919191919, 0x0819081919192b08, 0x08190819192b0819, 0x08190819192b1908,
-    0x081908192b080808, 0x081908192b08082b, 0x081908192b081919, 0x081908192b082b08,
-    0x081908192b190819, 0x081908192b191908, 0x0819082b08080819, 0x0819082b08081908,
-    0x0819082b08082b19, 0x0819082b08190808, 0x0819082b08191919, 0x0819082b082b0819,
-    0x0819082b082b1908, 0x0819082b19080808, 0x0819082b19081919, 0x0819082b19190819,
-    0x0819082b19191908, 0x0819082b2b080819, 0x0819082b2b081908, 0x0819082b2b190808,
-    0x0819190808080808, 0x081919080808082b, 0x0819190808081919, 0x0819190808082b08,
-    0x0819190808190819, 0x0819190808191908, 0x081919080819192b, 0x0819190808192b19,
-    0x08191908082b0808, 0x08191908082b1919, 0x08191908082b2b08, 0x0819190819080819,
-    0x0819190819081908, 0x081919081908192b, 0x0819190819082b19, 0x0819190819190808,
-    0x081919081919082b, 0x0819190819191919, 0x0819190819192b08, 0x08191908192b0819,
-    0x08191908192b1908, 0x081919082b080808, 0x081919082b08082b, 0x081919082b081919,
-    0x081919082b082b08, 0x081919082b190819, 0x081919082b191908, 0x081919082b2b0808,
-    0x0819191908080819, 0x0819191908081908, 0x081919190808192b, 0x0819191908082b19,
-    0x0819191908190808, 0x081919190819082b, 0x0819191908191919, 0x0819191908192b08,
-    0x08191919082b0819, 0x08191919082b1908, 0x0819191919080808, 0x081919191908082b,
-    0x0819191919081919, 0x0819191919082b08, 0x0819191919190819, 0x0819191919191908,
-    0x08191919192b0808, 0x081919192b080819, 0x081919192b081908, 0x081919192b190808,
-    0x0819192b08080808, 0x0819192b08081919, 0x0819192b08082b08, 0x0819192b08190819,
-    0x0819192b08191908, 0x0819192b082b0808, 0x0819192b19080819, 0x0819192b19081908,
-    0x0819192b19190808, 0x0819192b2b080808, 0x0819192b2b2b2b2b, 0x08192b0808080819,
-    0x08192b0808081908, 0x08192b080808192b, 0x08192b0808082b19, 0x08192b0808190808,
-    0x08192b0808191919, 0x08192b0808192b08, 0x08192b08082b0819, 0x08192b0819080808,
-    0x08192b081908082b, 0x08192b0819081919, 0x08192b0819082b08, 0x08192b0819190819,
-    0x08192b0819191908, 0x08192b08192b0808, 0x08192b082b080819, 0x08192b082b081908,
-    0x08192b1908080808, 0x08192b190808082b, 0x08192b1908081919, 0x08192b1908082b08,
-    0x08192b1908190819, 0x08192b1908191908, 0x08192b19082b0808, 0x08192b1919080819,
-    0x08192b1919081908, 0x08192b1919190808, 0x08192b19192b2b19, 0x08192b192b2b082b,
-    0x08192b2b08081908, 0x08192b2b08190808, 0x08192b2b19080808, 0x08192b2b1919192b,
-    0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, 0x082b080808082b08,
-    0x082b080808190819, 0x082b080808191908, 0x082b08080819192b, 0x082b080808192b19,
-    0x082b0808082b0808, 0x082b0808082b1919, 0x082b0808082b2b2b, 0x082b080819080819,
-    0x082b080819081908, 0x082b080819190808, 0x082b08081919082b, 0x082b080819191919,
-    0x082b0808192b1908, 0x082b08082b080808, 0x082b08082b082b2b, 0x082b08082b191908,
-    0x082b08082b2b2b2b, 0x082b081908080819, 0x082b081908081908, 0x082b081908190808,
-    0x082b08190819082b, 0x082b081908191919, 0x082b0819082b0819, 0x082b081919080808,
-    0x082b08191908082b, 0x082b081919081919, 0x082b081919190819, 0x082b081919191908,
-    0x082b0819192b0808, 0x082b08192b080819, 0x082b08192b081908, 0x082b08192b190808,
-    0x082b082b08080808, 0x082b082b08082b2b, 0x082b082b082b082b, 0x082b082b082b2b08,
-    0x082b082b082b2b2b, 0x082b082b19081908, 0x082b082b19190808, 0x082b082b2b082b08,
-    0x082b082b2b082b2b, 0x082b082b2b2b2b08, 0x082b190808080819, 0x082b190808081908,
-    0x082b19080808192b, 0x082b190808082b19, 0x082b190808190808, 0x082b190808191919,
-    0x082b190808192b08, 0x082b1908082b0819, 0x082b1908082b1908, 0x082b190819080808,
-    0x082b19081908082b, 0x082b190819081919, 0x082b190819082b08, 0x082b190819190819,
-    0x082b190819191908, 0x082b1908192b0808, 0x082b19082b080819, 0x082b19082b081908,
-    0x082b19082b190808, 0x082b191908080808, 0x082b191908081919, 0x082b191908082b08,
-    0x082b191908190819, 0x082b191908191908, 0x082b1919082b0808, 0x082b191919080819,
-    0x082b191919081908, 0x082b191919190808, 0x082b1919192b192b, 0x082b19192b080808,
-    0x082b192b08080819, 0x082b192b08081908, 0x082b192b08190808, 0x082b192b19080808,
-    0x082b192b19192b19, 0x082b2b0808080808, 0x082b2b0808081919, 0x082b2b0808190819,
-    0x082b2b0808191908, 0x082b2b0819080819, 0x082b2b0819081908, 0x082b2b0819190808,
-    0x082b2b082b082b2b, 0x082b2b082b2b2b2b, 0x082b2b1908080819, 0x082b2b1908081908,
-    0x082b2b1908190808, 0x082b2b192b191919, 0x082b2b2b08082b2b, 0x082b2b2b082b082b,
-    0x082b2b2b192b1908, 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819,
-    0x1908080808081908, 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808,
-    0x190808080819082b, 0x1908080808191919, 0x1908080808192b08, 0x1908080808192b2b,
-    0x19080808082b0819, 0x19080808082b1908, 0x19080808082b192b, 0x1908080819080808,
-    0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, 0x1908080819082b2b,
-    0x1908080819190819, 0x1908080819191908, 0x190808081919192b, 0x1908080819192b19,
-    0x19080808192b0808, 0x19080808192b082b, 0x19080808192b1919, 0x190808082b080819,
-    0x190808082b081908, 0x190808082b190808, 0x190808082b191919, 0x190808082b192b08,
-    0x190808082b2b0819, 0x190808082b2b1908, 0x1908081908080808, 0x190808190808082b,
-    0x1908081908081919, 0x1908081908082b08, 0x1908081908190819, 0x1908081908191908,
-    0x190808190819192b, 0x1908081908192b19, 0x19080819082b0808, 0x19080819082b082b,
-    0x19080819082b1919, 0x1908081919080819, 0x1908081919081908, 0x190808191908192b,
-    0x1908081919082b19, 0x1908081919190808, 0x190808191919082b, 0x1908081919191919,
-    0x1908081919192b08, 0x19080819192b0819, 0x19080819192b1908, 0x190808192b080808,
-    0x190808192b08082b, 0x190808192b081919, 0x190808192b082b08, 0x190808192b190819,
-    0x190808192b191908, 0x190808192b2b0808, 0x1908082b08080819, 0x1908082b08081908,
-    0x1908082b08190808, 0x1908082b0819082b, 0x1908082b08191919, 0x1908082b08192b08,
-    0x1908082b082b1908, 0x1908082b19080808, 0x1908082b19081919, 0x1908082b19082b08,
-    0x1908082b19190819, 0x1908082b19191908, 0x1908082b192b0808, 0x1908082b2b080819,
-    0x1908082b2b081908, 0x1908190808080808, 0x190819080808082b, 0x1908190808081919,
-    0x1908190808082b08, 0x1908190808082b2b, 0x1908190808190819, 0x1908190808191908,
-    0x190819080819192b, 0x1908190808192b19, 0x19081908082b0808, 0x19081908082b082b,
-    0x19081908082b1919, 0x19081908082b2b08, 0x1908190819080819, 0x1908190819081908,
-    0x190819081908192b, 0x1908190819082b19, 0x1908190819190808, 0x190819081919082b,
-    0x1908190819191919, 0x1908190819192b08, 0x19081908192b0819, 0x19081908192b1908,
-    0x190819082b080808, 0x190819082b08082b, 0x190819082b081919, 0x190819082b082b08,
-    0x190819082b190819, 0x190819082b191908, 0x190819082b2b0808, 0x1908191908080819,
-    0x1908191908081908, 0x190819190808192b, 0x1908191908082b19, 0x1908191908190808,
-    0x190819190819082b, 0x1908191908191919, 0x1908191908192b08, 0x19081919082b0819,
-    0x19081919082b1908, 0x1908191919080808, 0x190819191908082b, 0x1908191919081919,
-    0x1908191919082b08, 0x1908191919190819, 0x1908191919191908, 0x19081919192b0808,
-    0x19081919192b2b2b, 0x190819192b080819, 0x190819192b081908, 0x190819192b190808,
-    0x1908192b08080808, 0x1908192b0808082b, 0x1908192b08081919, 0x1908192b08082b08,
-    0x1908192b08190819, 0x1908192b08191908, 0x1908192b082b0808, 0x1908192b19080819,
-    0x1908192b19081908, 0x1908192b19190808, 0x1908192b2b080808, 0x1908192b2b2b1919,
-    0x19082b0808080819, 0x19082b0808081908, 0x19082b0808082b19, 0x19082b0808190808,
-    0x19082b080819082b, 0x19082b0808191919, 0x19082b0808192b08, 0x19082b08082b0819,
-    0x19082b08082b1908, 0x19082b0819080808, 0x19082b081908082b, 0x19082b0819081919,
-    0x19082b0819082b08, 0x19082b0819190819, 0x19082b0819191908, 0x19082b08192b0808,
-    0x19082b082b081908, 0x19082b082b190808, 0x19082b1908080808, 0x19082b190808082b,
-    0x19082b1908081919, 0x19082b1908082b08, 0x19082b1908190819, 0x19082b1908191908,
-    0x19082b19082b0808, 0x19082b1919080819, 0x19082b1919081908, 0x19082b1919190808,
-    0x19082b192b080808, 0x19082b192b19192b, 0x19082b2b08080819, 0x19082b2b08081908,
-    0x19082b2b08190808, 0x19082b2b19080808, 0x1919080808080808, 0x191908080808082b,
-    0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, 0x1919080808191908,
-    0x191908080819192b, 0x1919080808192b19, 0x19190808082b0808, 0x19190808082b082b,
-    0x19190808082b1919, 0x19190808082b2b08, 0x1919080819080819, 0x1919080819081908,
-    0x191908081908192b, 0x1919080819082b19, 0x1919080819190808, 0x191908081919082b,
-    0x1919080819191919, 0x1919080819192b08, 0x19190808192b0819, 0x19190808192b1908,
-    0x191908082b080808, 0x191908082b08082b, 0x191908082b081919, 0x191908082b082b08,
-    0x191908082b190819, 0x191908082b191908, 0x1919081908080819, 0x1919081908081908,
-    0x191908190808192b, 0x1919081908082b19, 0x1919081908190808, 0x191908190819082b,
-    0x1919081908191919, 0x1919081908192b08, 0x19190819082b0819, 0x19190819082b1908,
-    0x1919081919080808, 0x191908191908082b, 0x1919081919081919, 0x1919081919082b08,
-    0x1919081919190819, 0x1919081919191908, 0x19190819192b0808, 0x191908192b080819,
-    0x191908192b081908, 0x191908192b190808, 0x1919082b08080808, 0x1919082b08081919,
-    0x1919082b08082b08, 0x1919082b08190819, 0x1919082b08191908, 0x1919082b082b0808,
-    0x1919082b19080819, 0x1919082b19081908, 0x1919082b19190808, 0x1919082b192b2b19,
-    0x1919082b2b080808, 0x1919190808080819, 0x1919190808081908, 0x191919080808192b,
-    0x1919190808082b19, 0x1919190808190808, 0x191919080819082b, 0x1919190808191919,
-    0x1919190808192b08, 0x19191908082b0819, 0x19191908082b1908, 0x1919190819080808,
-    0x191919081908082b, 0x1919190819081919, 0x1919190819082b08, 0x1919190819190819,
-    0x1919190819191908, 0x19191908192b0808, 0x191919082b080819, 0x191919082b081908,
-    0x191919082b190808, 0x1919191908080808, 0x191919190808082b, 0x1919191908081919,
-    0x1919191908082b08, 0x1919191908190819, 0x1919191908191908, 0x19191919082b0808,
-    0x1919191919080819, 0x1919191919081908, 0x1919191919190808, 0x191919192b080808,
-    0x1919192b08080819, 0x1919192b08081908, 0x1919192b08190808, 0x1919192b082b192b,
-    0x1919192b19080808, 0x19192b0808080808, 0x19192b080808082b, 0x19192b0808081919,
-    0x19192b0808082b08, 0x19192b0808190819, 0x19192b0808191908, 0x19192b08082b0808,
-    0x19192b0819080819, 0x19192b0819081908, 0x19192b0819190808, 0x19192b0819192b2b,
-    0x19192b082b080808, 0x19192b1908080819, 0x19192b1908081908, 0x19192b1908190808,
-    0x19192b1919080808, 0x19192b2b08080808, 0x19192b2b08192b19, 0x19192b2b2b081919,
-    0x19192b2b2b2b2b08, 0x192b080808080819, 0x192b080808081908, 0x192b08080808192b,
-    0x192b080808190808, 0x192b08080819082b, 0x192b080808191919, 0x192b080808192b08,
-    0x192b0808082b0819, 0x192b0808082b1908, 0x192b080819080808, 0x192b080819081919,
-    0x192b080819082b08, 0x192b080819190819, 0x192b080819191908, 0x192b0808192b0808,
-    0x192b08082b081908, 0x192b08082b190808, 0x192b081908080808, 0x192b08190808082b,
-    0x192b081908081919, 0x192b081908082b08, 0x192b081908190819, 0x192b081908191908,
-    0x192b0819082b0808, 0x192b081919080819, 0x192b081919081908, 0x192b081919190808,
-    0x192b08192b080808, 0x192b08192b192b19, 0x192b082b08081908, 0x192b082b08190808,
-    0x192b082b19080808, 0x192b082b1919192b, 0x192b082b2b2b0819, 0x192b190808080808,
-    0x192b190808081919, 0x192b190808082b08, 0x192b190808190819, 0x192b190808191908,
-    0x192b1908082b0808, 0x192b190819080819, 0x192b190819081908, 0x192b190819190808,
-    0x192b19082b080808, 0x192b191908080819, 0x192b191908081908, 0x192b191908190808,
-    0x192b191919080808, 0x192b191919082b2b, 0x192b1919192b2b08, 0x192b19192b19082b,
-    0x192b192b08080808, 0x192b192b2b191908, 0x192b2b0808080819, 0x192b2b0808081908,
-    0x192b2b0808190808, 0x192b2b08192b1919, 0x192b2b082b192b08, 0x192b2b1908080808,
-    0x192b2b19082b2b2b, 0x192b2b2b1908082b, 0x192b2b2b2b2b0819, 0x2b08080808080808,
-    0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, 0x2b08080808190819,
-    0x2b08080808191908, 0x2b08080808192b19, 0x2b080808082b0808, 0x2b080808082b1919,
-    0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808081919082b,
-    0x2b08080819191919, 0x2b08080819192b08, 0x2b080808192b0819, 0x2b0808082b080808,
-    0x2b0808082b081919, 0x2b0808082b190819, 0x2b0808082b191908, 0x2b08081908080819,
-    0x2b08081908081908, 0x2b08081908082b19, 0x2b08081908190808, 0x2b0808190819082b,
-    0x2b08081908191919, 0x2b08081908192b08, 0x2b080819082b0819, 0x2b080819082b1908,
-    0x2b08081919080808, 0x2b0808191908082b, 0x2b08081919081919, 0x2b08081919082b08,
-    0x2b08081919190819, 0x2b08081919191908, 0x2b0808192b080819, 0x2b0808192b081908,
-    0x2b0808192b190808, 0x2b0808192b2b2b19, 0x2b08082b08080808, 0x2b08082b08081919,
-    0x2b08082b08082b2b, 0x2b08082b08190819, 0x2b08082b08191908, 0x2b08082b19080819,
-    0x2b08082b19081908, 0x2b08082b19190808, 0x2b08190808080819, 0x2b08190808081908,
-    0x2b0819080808192b, 0x2b08190808082b19, 0x2b08190808190808, 0x2b0819080819082b,
-    0x2b08190808191919, 0x2b08190808192b08, 0x2b081908082b0819, 0x2b08190819080808,
-    0x2b0819081908082b, 0x2b08190819081919, 0x2b08190819082b08, 0x2b08190819190819,
-    0x2b08190819191908, 0x2b081908192b0808, 0x2b0819082b080819, 0x2b0819082b081908,
-    0x2b0819082b190808, 0x2b08191908080808, 0x2b0819190808082b, 0x2b08191908081919,
-    0x2b08191908082b08, 0x2b08191908190819, 0x2b08191908191908, 0x2b081919082b0808,
-    0x2b08191919080819, 0x2b08191919081908, 0x2b08191919190808, 0x2b0819192b080808,
-    0x2b0819192b082b2b, 0x2b08192b08080819, 0x2b08192b08081908, 0x2b08192b08190808,
-    0x2b08192b082b2b19, 0x2b08192b19080808, 0x2b082b0808080808, 0x2b082b0808081919,
-    0x2b082b0808190819, 0x2b082b0808191908, 0x2b082b0819080819, 0x2b082b0819081908,
-    0x2b082b0819190808, 0x2b082b082b2b082b, 0x2b082b1908080819, 0x2b082b1908081908,
-    0x2b082b1919080808, 0x2b082b19192b1919, 0x2b082b2b082b082b, 0x2b082b2b19192b08,
-    0x2b082b2b19192b2b, 0x2b082b2b2b08082b, 0x2b082b2b2b2b082b, 0x2b19080808080819,
-    0x2b19080808081908, 0x2b19080808082b19, 0x2b19080808190808, 0x2b1908080819082b,
-    0x2b19080808191919, 0x2b19080808192b08, 0x2b190808082b1908, 0x2b19080819080808,
-    0x2b1908081908082b, 0x2b19080819081919, 0x2b19080819082b08, 0x2b19080819190819,
-    0x2b19080819191908, 0x2b190808192b0808, 0x2b1908082b080819, 0x2b1908082b081908,
-    0x2b1908082b190808, 0x2b19081908080808, 0x2b19081908081919, 0x2b19081908190819,
-    0x2b19081908191908, 0x2b19081919080819, 0x2b19081919081908, 0x2b19081919190808,
-    0x2b19081919192b2b, 0x2b19082b08080819, 0x2b19082b08081908, 0x2b19082b08190808,
-    0x2b19082b19080808, 0x2b19082b2b2b192b, 0x2b19190808080808, 0x2b1919080808082b,
-    0x2b19190808081919, 0x2b19190808082b08, 0x2b19190808190819, 0x2b19190808191908,
-    0x2b191908082b0808, 0x2b19190819080819, 0x2b19190819081908, 0x2b19190819190808,
-    0x2b1919082b080808, 0x2b1919082b19192b, 0x2b19191908080819, 0x2b19191908081908,
-    0x2b19191908190808, 0x2b19191919080808, 0x2b1919192b192b08, 0x2b1919192b2b0819,
-    0x2b19192b08080808, 0x2b19192b1908192b, 0x2b19192b192b1908, 0x2b192b0808080819,
-    0x2b192b0808081908, 0x2b192b0808190808, 0x2b192b08082b192b, 0x2b192b0819080808,
-    0x2b192b082b2b2b19, 0x2b192b1908080808, 0x2b192b1919082b19, 0x2b192b191919082b,
-    0x2b192b2b2b190808, 0x2b2b080808080808, 0x2b2b080808081919, 0x2b2b080808082b2b,
-    0x2b2b080808191908, 0x2b2b0808082b082b, 0x2b2b0808082b2b2b, 0x2b2b080819080819,
-    0x2b2b080819081908, 0x2b2b080819190808, 0x2b2b08082b2b082b, 0x2b2b08082b2b2b2b,
-    0x2b2b081919080808, 0x2b2b0819192b1919, 0x2b2b082b0808082b, 0x2b2b082b08082b2b,
-    0x2b2b082b082b082b, 0x2b2b082b082b2b08, 0x2b2b082b082b2b2b, 0x2b2b082b2b08082b,
-    0x2b2b082b2b082b08, 0x2b2b082b2b082b2b, 0x2b2b082b2b2b2b08, 0x2b2b190808080819,
-    0x2b2b190808081908, 0x2b2b190808190808, 0x2b2b190819080808, 0x2b2b19082b082b19,
-    0x2b2b19082b2b1908, 0x2b2b191908080808, 0x2b2b191908192b19, 0x2b2b192b19190819,
-    0x2b2b2b0808082b2b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b082b, 0x2b2b2b1919191908,
-    0x2b2b2b192b08192b, 0x2b2b2b2b08082b08, 0x2b2b2b2b08082b2b, 0x2b2b2b2b082b0808,
-    0x2b2b2b2b082b082b, 0x2b2b2b2b082b2b08, 0x2b2b2b2b2b082b08, 0x2b2b2b2b2b2b2b2b,
-};
-
-static const __device__ uint32_t iq3xxs_grid[256] = {
-    0x04040404, 0x04040414, 0x04040424, 0x04040c0c, 0x04040c1c, 0x04040c3e, 0x04041404, 0x04041414,
-    0x04041c0c, 0x04042414, 0x04043e1c, 0x04043e2c, 0x040c040c, 0x040c041c, 0x040c0c04, 0x040c0c14,
-    0x040c140c, 0x040c142c, 0x040c1c04, 0x040c1c14, 0x040c240c, 0x040c2c24, 0x040c3e04, 0x04140404,
-    0x04140414, 0x04140424, 0x04140c0c, 0x04141404, 0x04141414, 0x04141c0c, 0x04141c1c, 0x04141c3e,
-    0x04142c0c, 0x04142c3e, 0x04143e2c, 0x041c040c, 0x041c043e, 0x041c0c04, 0x041c0c14, 0x041c142c,
-    0x041c3e04, 0x04240c1c, 0x04241c3e, 0x04242424, 0x04242c3e, 0x04243e1c, 0x04243e2c, 0x042c040c,
-    0x042c043e, 0x042c1c14, 0x042c2c14, 0x04341c2c, 0x04343424, 0x043e0c04, 0x043e0c24, 0x043e0c34,
-    0x043e241c, 0x043e340c, 0x0c04040c, 0x0c04041c, 0x0c040c04, 0x0c040c14, 0x0c04140c, 0x0c04141c,
-    0x0c041c04, 0x0c041c14, 0x0c041c24, 0x0c04243e, 0x0c042c04, 0x0c0c0404, 0x0c0c0414, 0x0c0c0c0c,
-    0x0c0c1404, 0x0c0c1414, 0x0c14040c, 0x0c14041c, 0x0c140c04, 0x0c140c14, 0x0c14140c, 0x0c141c04,
-    0x0c143e14, 0x0c1c0404, 0x0c1c0414, 0x0c1c1404, 0x0c1c1c0c, 0x0c1c2434, 0x0c1c3434, 0x0c24040c,
-    0x0c24042c, 0x0c242c04, 0x0c2c1404, 0x0c2c1424, 0x0c2c2434, 0x0c2c3e0c, 0x0c34042c, 0x0c3e1414,
-    0x0c3e2404, 0x14040404, 0x14040414, 0x14040c0c, 0x14040c1c, 0x14041404, 0x14041414, 0x14041434,
-    0x14041c0c, 0x14042414, 0x140c040c, 0x140c041c, 0x140c042c, 0x140c0c04, 0x140c0c14, 0x140c140c,
-    0x140c1c04, 0x140c341c, 0x140c343e, 0x140c3e04, 0x14140404, 0x14140414, 0x14140c0c, 0x14140c3e,
-    0x14141404, 0x14141414, 0x14141c3e, 0x14142404, 0x14142c2c, 0x141c040c, 0x141c0c04, 0x141c0c24,
-    0x141c3e04, 0x141c3e24, 0x14241c2c, 0x14242c1c, 0x142c041c, 0x142c143e, 0x142c240c, 0x142c3e24,
-    0x143e040c, 0x143e041c, 0x143e0c34, 0x143e242c, 0x1c04040c, 0x1c040c04, 0x1c040c14, 0x1c04140c,
-    0x1c04141c, 0x1c042c04, 0x1c04342c, 0x1c043e14, 0x1c0c0404, 0x1c0c0414, 0x1c0c1404, 0x1c0c1c0c,
-    0x1c0c2424, 0x1c0c2434, 0x1c14040c, 0x1c14041c, 0x1c140c04, 0x1c14142c, 0x1c142c14, 0x1c143e14,
-    0x1c1c0c0c, 0x1c1c1c1c, 0x1c241c04, 0x1c24243e, 0x1c243e14, 0x1c2c0404, 0x1c2c0434, 0x1c2c1414,
-    0x1c2c2c2c, 0x1c340c24, 0x1c341c34, 0x1c34341c, 0x1c3e1c1c, 0x1c3e3404, 0x24040424, 0x24040c3e,
-    0x24041c2c, 0x24041c3e, 0x24042c1c, 0x24042c3e, 0x240c3e24, 0x24141404, 0x24141c3e, 0x24142404,
-    0x24143404, 0x24143434, 0x241c043e, 0x241c242c, 0x24240424, 0x24242c0c, 0x24243424, 0x242c142c,
-    0x242c241c, 0x242c3e04, 0x243e042c, 0x243e0c04, 0x243e0c14, 0x243e1c04, 0x2c040c14, 0x2c04240c,
-    0x2c043e04, 0x2c0c0404, 0x2c0c0434, 0x2c0c1434, 0x2c0c2c2c, 0x2c140c24, 0x2c141c14, 0x2c143e14,
-    0x2c1c0414, 0x2c1c2c1c, 0x2c240c04, 0x2c24141c, 0x2c24143e, 0x2c243e14, 0x2c2c0414, 0x2c2c1c0c,
-    0x2c342c04, 0x2c3e1424, 0x2c3e2414, 0x34041424, 0x34042424, 0x34042434, 0x34043424, 0x340c140c,
-    0x340c340c, 0x34140c3e, 0x34143424, 0x341c1c04, 0x341c1c34, 0x34242424, 0x342c042c, 0x342c2c14,
-    0x34341c1c, 0x343e041c, 0x343e140c, 0x3e04041c, 0x3e04042c, 0x3e04043e, 0x3e040c04, 0x3e041c14,
-    0x3e042c14, 0x3e0c1434, 0x3e0c2404, 0x3e140c14, 0x3e14242c, 0x3e142c14, 0x3e1c0404, 0x3e1c0c2c,
-    0x3e1c1c1c, 0x3e1c3404, 0x3e24140c, 0x3e24240c, 0x3e2c0404, 0x3e2c0414, 0x3e2c1424, 0x3e341c04,
-};
-
-static const __device__ uint32_t iq3s_grid[512] = {
-    0x01010101, 0x01010103, 0x01010105, 0x0101010b, 0x0101010f, 0x01010301, 0x01010303, 0x01010305,
-    0x01010309, 0x0101030d, 0x01010501, 0x01010503, 0x0101050b, 0x01010707, 0x01010901, 0x01010905,
-    0x0101090b, 0x0101090f, 0x01010b03, 0x01010b07, 0x01010d01, 0x01010d05, 0x01010f03, 0x01010f09,
-    0x01010f0f, 0x01030101, 0x01030103, 0x01030105, 0x01030109, 0x01030301, 0x01030303, 0x0103030b,
-    0x01030501, 0x01030507, 0x0103050f, 0x01030703, 0x0103070b, 0x01030909, 0x01030d03, 0x01030d0b,
-    0x01030f05, 0x01050101, 0x01050103, 0x0105010b, 0x0105010f, 0x01050301, 0x01050307, 0x0105030d,
-    0x01050503, 0x0105050b, 0x01050701, 0x01050709, 0x01050905, 0x0105090b, 0x0105090f, 0x01050b03,
-    0x01050b07, 0x01050f01, 0x01050f07, 0x01070107, 0x01070303, 0x0107030b, 0x01070501, 0x01070505,
-    0x01070703, 0x01070707, 0x0107070d, 0x01070909, 0x01070b01, 0x01070b05, 0x01070d0f, 0x01070f03,
-    0x01070f0b, 0x01090101, 0x01090307, 0x0109030f, 0x01090503, 0x01090509, 0x01090705, 0x01090901,
-    0x01090907, 0x01090b03, 0x01090f01, 0x010b0105, 0x010b0109, 0x010b0501, 0x010b0505, 0x010b050d,
-    0x010b0707, 0x010b0903, 0x010b090b, 0x010b090f, 0x010b0d0d, 0x010b0f07, 0x010d010d, 0x010d0303,
-    0x010d0307, 0x010d0703, 0x010d0b05, 0x010d0f03, 0x010f0101, 0x010f0105, 0x010f0109, 0x010f0501,
-    0x010f0505, 0x010f050d, 0x010f0707, 0x010f0b01, 0x010f0b09, 0x03010101, 0x03010103, 0x03010105,
-    0x03010109, 0x03010301, 0x03010303, 0x03010307, 0x0301030b, 0x0301030f, 0x03010501, 0x03010505,
-    0x03010703, 0x03010709, 0x0301070d, 0x03010b09, 0x03010b0d, 0x03010d03, 0x03010f05, 0x03030101,
-    0x03030103, 0x03030107, 0x0303010d, 0x03030301, 0x03030309, 0x03030503, 0x03030701, 0x03030707,
-    0x03030903, 0x03030b01, 0x03030b05, 0x03030f01, 0x03030f0d, 0x03050101, 0x03050305, 0x0305030b,
-    0x0305030f, 0x03050501, 0x03050509, 0x03050705, 0x03050901, 0x03050907, 0x03050b0b, 0x03050d01,
-    0x03050f05, 0x03070103, 0x03070109, 0x0307010f, 0x03070301, 0x03070307, 0x03070503, 0x0307050f,
-    0x03070701, 0x03070709, 0x03070903, 0x03070d05, 0x03070f01, 0x03090107, 0x0309010b, 0x03090305,
-    0x03090309, 0x03090703, 0x03090707, 0x03090905, 0x0309090d, 0x03090b01, 0x03090b09, 0x030b0103,
-    0x030b0301, 0x030b0307, 0x030b0503, 0x030b0701, 0x030b0705, 0x030b0b03, 0x030d0501, 0x030d0509,
-    0x030d050f, 0x030d0909, 0x030d090d, 0x030f0103, 0x030f0107, 0x030f0301, 0x030f0305, 0x030f0503,
-    0x030f070b, 0x030f0903, 0x030f0d05, 0x030f0f01, 0x05010101, 0x05010103, 0x05010107, 0x0501010b,
-    0x0501010f, 0x05010301, 0x05010305, 0x05010309, 0x0501030d, 0x05010503, 0x05010507, 0x0501050f,
-    0x05010701, 0x05010705, 0x05010903, 0x05010907, 0x0501090b, 0x05010b01, 0x05010b05, 0x05010d0f,
-    0x05010f01, 0x05010f07, 0x05010f0b, 0x05030101, 0x05030105, 0x05030301, 0x05030307, 0x0503030f,
-    0x05030505, 0x0503050b, 0x05030703, 0x05030709, 0x05030905, 0x05030b03, 0x05050103, 0x05050109,
-    0x0505010f, 0x05050503, 0x05050507, 0x05050701, 0x0505070f, 0x05050903, 0x05050b07, 0x05050b0f,
-    0x05050f03, 0x05050f09, 0x05070101, 0x05070105, 0x0507010b, 0x05070303, 0x05070505, 0x05070509,
-    0x05070703, 0x05070707, 0x05070905, 0x05070b01, 0x05070d0d, 0x05090103, 0x0509010f, 0x05090501,
-    0x05090507, 0x05090705, 0x0509070b, 0x05090903, 0x05090f05, 0x05090f0b, 0x050b0109, 0x050b0303,
-    0x050b0505, 0x050b070f, 0x050b0901, 0x050b0b07, 0x050b0f01, 0x050d0101, 0x050d0105, 0x050d010f,
-    0x050d0503, 0x050d0b0b, 0x050d0d03, 0x050f010b, 0x050f0303, 0x050f050d, 0x050f0701, 0x050f0907,
-    0x050f0b01, 0x07010105, 0x07010303, 0x07010307, 0x0701030b, 0x0701030f, 0x07010505, 0x07010703,
-    0x07010707, 0x0701070b, 0x07010905, 0x07010909, 0x0701090f, 0x07010b03, 0x07010d07, 0x07010f03,
-    0x07030103, 0x07030107, 0x0703010b, 0x07030309, 0x07030503, 0x07030507, 0x07030901, 0x07030d01,
-    0x07030f05, 0x07030f0d, 0x07050101, 0x07050305, 0x07050501, 0x07050705, 0x07050709, 0x07050b01,
-    0x07070103, 0x07070301, 0x07070309, 0x07070503, 0x07070507, 0x0707050f, 0x07070701, 0x07070903,
-    0x07070907, 0x0707090f, 0x07070b0b, 0x07070f07, 0x07090107, 0x07090303, 0x0709030d, 0x07090505,
-    0x07090703, 0x07090b05, 0x07090d01, 0x07090d09, 0x070b0103, 0x070b0301, 0x070b0305, 0x070b050b,
-    0x070b0705, 0x070b0909, 0x070b0b0d, 0x070b0f07, 0x070d030d, 0x070d0903, 0x070f0103, 0x070f0107,
-    0x070f0501, 0x070f0505, 0x070f070b, 0x09010101, 0x09010109, 0x09010305, 0x09010501, 0x09010509,
-    0x0901050f, 0x09010705, 0x09010903, 0x09010b01, 0x09010f01, 0x09030105, 0x0903010f, 0x09030303,
-    0x09030307, 0x09030505, 0x09030701, 0x0903070b, 0x09030907, 0x09030b03, 0x09030b0b, 0x09050103,
-    0x09050107, 0x09050301, 0x0905030b, 0x09050503, 0x09050707, 0x09050901, 0x09050b0f, 0x09050d05,
-    0x09050f01, 0x09070109, 0x09070303, 0x09070307, 0x09070501, 0x09070505, 0x09070703, 0x0907070b,
-    0x09090101, 0x09090105, 0x09090509, 0x0909070f, 0x09090901, 0x09090f03, 0x090b010b, 0x090b010f,
-    0x090b0503, 0x090b0d05, 0x090d0307, 0x090d0709, 0x090d0d01, 0x090f0301, 0x090f030b, 0x090f0701,
-    0x090f0907, 0x090f0b03, 0x0b010105, 0x0b010301, 0x0b010309, 0x0b010505, 0x0b010901, 0x0b010909,
-    0x0b01090f, 0x0b010b05, 0x0b010d0d, 0x0b010f09, 0x0b030103, 0x0b030107, 0x0b03010b, 0x0b030305,
-    0x0b030503, 0x0b030705, 0x0b030f05, 0x0b050101, 0x0b050303, 0x0b050507, 0x0b050701, 0x0b05070d,
-    0x0b050b07, 0x0b070105, 0x0b07010f, 0x0b070301, 0x0b07050f, 0x0b070909, 0x0b070b03, 0x0b070d0b,
-    0x0b070f07, 0x0b090103, 0x0b090109, 0x0b090501, 0x0b090705, 0x0b09090d, 0x0b0b0305, 0x0b0b050d,
-    0x0b0b0b03, 0x0b0b0b07, 0x0b0d0905, 0x0b0f0105, 0x0b0f0109, 0x0b0f0505, 0x0d010303, 0x0d010307,
-    0x0d01030b, 0x0d010703, 0x0d010707, 0x0d010d01, 0x0d030101, 0x0d030501, 0x0d03050f, 0x0d030d09,
-    0x0d050305, 0x0d050709, 0x0d050905, 0x0d050b0b, 0x0d050d05, 0x0d050f01, 0x0d070101, 0x0d070309,
-    0x0d070503, 0x0d070901, 0x0d09050b, 0x0d090907, 0x0d090d05, 0x0d0b0101, 0x0d0b0107, 0x0d0b0709,
-    0x0d0b0d01, 0x0d0d010b, 0x0d0d0901, 0x0d0f0303, 0x0d0f0307, 0x0f010101, 0x0f010109, 0x0f01010f,
-    0x0f010501, 0x0f010505, 0x0f01070d, 0x0f010901, 0x0f010b09, 0x0f010d05, 0x0f030105, 0x0f030303,
-    0x0f030509, 0x0f030907, 0x0f03090b, 0x0f050103, 0x0f050109, 0x0f050301, 0x0f05030d, 0x0f050503,
-    0x0f050701, 0x0f050b03, 0x0f070105, 0x0f070705, 0x0f07070b, 0x0f070b07, 0x0f090103, 0x0f09010b,
-    0x0f090307, 0x0f090501, 0x0f090b01, 0x0f0b0505, 0x0f0b0905, 0x0f0d0105, 0x0f0d0703, 0x0f0f0101,
-};
-
-static const __device__ uint64_t iq1s_grid[512] = {
-    0xffffffffffff0101, 0xffffffffff01ff00, 0xffffffffff010100, 0xffffffff00000000,
-    0xffffffff01ff00ff, 0xffffffff01ff0001, 0xffffffff0101ffff, 0xffffffff0101ff01,
-    0xffffff00ff000000, 0xffffff000000ff00, 0xffffff00000000ff, 0xffffff0000000100,
-    0xffffff0000010000, 0xffffff0001000000, 0xffffff01ffff00ff, 0xffffff01ff01ff00,
-    0xffffff01ff010100, 0xffffff0100000001, 0xffffff0101ffff00, 0xffffff0101ff0101,
-    0xffffff0101010100, 0xffff00ffff00ff01, 0xffff00ffff0000ff, 0xffff00ff00ff0100,
-    0xffff00ff0100ff00, 0xffff00ff010001ff, 0xffff0000ff0101ff, 0xffff000000ffff00,
-    0xffff000000000000, 0xffff00000001ff01, 0xffff000001000101, 0xffff0000010100ff,
-    0xffff0001ffff0100, 0xffff00010000ff00, 0xffff000100010101, 0xffff000101000000,
-    0xffff01ffffff0000, 0xffff01ffff01ffff, 0xffff01ffff010100, 0xffff01ff00000000,
-    0xffff01ff01ffffff, 0xffff01ff01ff0001, 0xffff01ff0101ffff, 0xffff01ff01010001,
-    0xffff0100ffffff01, 0xffff01000000ffff, 0xffff010000000100, 0xffff010001ff01ff,
-    0xffff010001000000, 0xffff0101ff000000, 0xffff0101000101ff, 0xffff010101ffff01,
-    0xffff01010101ff00, 0xff00ffffff000000, 0xff00ffff00ffff00, 0xff00ffff00000001,
-    0xff00ffff000001ff, 0xff00ffff01010000, 0xff00ff00ffff0000, 0xff00ff00ff00ff00,
-    0xff00ff00ff0000ff, 0xff00ff00ff000100, 0xff00ff00ff010001, 0xff00ff0000ff0001,
-    0xff00ff000000ffff, 0xff00ff0000000000, 0xff00ff000001ff00, 0xff00ff0000010100,
-    0xff00ff0001ff0000, 0xff00ff000100ff00, 0xff00ff0001000100, 0xff00ff01ff000000,
-    0xff00ff0100ff0000, 0xff00ff01000001ff, 0xff00ff0101010001, 0xff0000ff00000000,
-    0xff0000ff0001ff00, 0xff0000ff00010100, 0xff000000ffff0101, 0xff000000ff000000,
-    0xff000000ff01ff00, 0xff00000000ff0000, 0xff0000000000ff00, 0xff000000000000ff,
-    0xff00000000000000, 0xff00000000000001, 0xff00000000000100, 0xff0000000001ffff,
-    0xff00000000010000, 0xff00000001000000, 0xff00000001010100, 0xff000001ff00ff01,
-    0xff000001ff0100ff, 0xff00000100000000, 0xff0000010001ff00, 0xff00000101ff0100,
-    0xff0000010100ff00, 0xff0001ff00ff00ff, 0xff0001ff00000101, 0xff0001ff000100ff,
-    0xff0001ff01000000, 0xff000100ff0001ff, 0xff0001000000ff01, 0xff00010000000000,
-    0xff00010000010001, 0xff00010000010100, 0xff00010001ffff00, 0xff00010001ff0101,
-    0xff00010001010000, 0xff000101ffffffff, 0xff000101ff000101, 0xff00010101ff00ff,
-    0xff00010101000001, 0xff000101010100ff, 0xff01ffffff000101, 0xff01ffffff01ffff,
-    0xff01ffffff01ff01, 0xff01ffffff0101ff, 0xff01ffff00000000, 0xff01ffff01ff0001,
-    0xff01ffff0101ff01, 0xff01ff00ff000000, 0xff01ff0000ff0100, 0xff01ff000000ff01,
-    0xff01ff0000010000, 0xff01ff00010000ff, 0xff01ff01ff01ff00, 0xff01ff0100000101,
-    0xff0100ffffff0000, 0xff0100ffff010000, 0xff0100ff01ff00ff, 0xff0100ff01000100,
-    0xff0100ff010100ff, 0xff010000ffffff01, 0xff01000000000000, 0xff0100000101ff00,
-    0xff010001ffff00ff, 0xff010001ff000100, 0xff01000100ffff00, 0xff01000100010001,
-    0xff01000101ff0001, 0xff010001010001ff, 0xff0101ffffffffff, 0xff0101ffff01ffff,
-    0xff0101ffff010101, 0xff0101ff0000ff00, 0xff0101ff01010001, 0xff010100ff000000,
-    0xff010100ff01ff01, 0xff01010000ff0001, 0xff01010000000100, 0xff01010001000000,
-    0xff0101010100ffff, 0x00ffffff0000ff01, 0x00ffffff000000ff, 0x00ffffff00000100,
-    0x00ffffff00010000, 0x00ffff00ffff0001, 0x00ffff00ff0000ff, 0x00ffff00ff000100,
-    0x00ffff0000000000, 0x00ffff0001000100, 0x00ffff0001010001, 0x00ffff01ff00ff01,
-    0x00ffff0100ff0100, 0x00ffff010000ff00, 0x00ffff01000100ff, 0x00ffff0101ff00ff,
-    0x00ffff010101ff00, 0x00ff00ffffffffff, 0x00ff00ffffff01ff, 0x00ff00ffff000101,
-    0x00ff00ff00000000, 0x00ff00ff000101ff, 0x00ff00ff01010101, 0x00ff0000ff000000,
-    0x00ff0000ff01ffff, 0x00ff000000ff0000, 0x00ff00000000ff00, 0x00ff0000000000ff,
-    0x00ff000000000000, 0x00ff000000000001, 0x00ff000000000100, 0x00ff000000010000,
-    0x00ff000001ffff01, 0x00ff000001000000, 0x00ff0001ff000101, 0x00ff000100ffffff,
-    0x00ff000100000000, 0x00ff0001010001ff, 0x00ff01ffff000000, 0x00ff01ff0001ff00,
-    0x00ff01ff01ff0100, 0x00ff0100ff01ff01, 0x00ff010000ff00ff, 0x00ff010000ff0101,
-    0x00ff010000000000, 0x00ff010000010101, 0x00ff01000100ff00, 0x00ff010001010000,
-    0x00ff0101ffffff00, 0x00ff01010000ff01, 0x00ff010100000100, 0x00ff010101ff0000,
-    0x0000ffffffff0100, 0x0000ffffff00ff00, 0x0000ffffff0000ff, 0x0000ffffff010000,
-    0x0000ffff00000000, 0x0000ffff00010101, 0x0000ffff01ffff01, 0x0000ffff01000100,
-    0x0000ff00ff000000, 0x0000ff00ff01ff00, 0x0000ff00ff0101ff, 0x0000ff0000ff0000,
-    0x0000ff000000ff00, 0x0000ff00000000ff, 0x0000ff0000000000, 0x0000ff0000000001,
-    0x0000ff0000000100, 0x0000ff0000010000, 0x0000ff0001ffffff, 0x0000ff0001ff01ff,
-    0x0000ff0001000000, 0x0000ff000101ffff, 0x0000ff01ffff0101, 0x0000ff01ff010000,
-    0x0000ff0100000000, 0x0000ff0101000101, 0x000000ffffff0001, 0x000000ffff000000,
-    0x000000ff00ff0000, 0x000000ff0000ff00, 0x000000ff000000ff, 0x000000ff00000000,
-    0x000000ff00000001, 0x000000ff00000100, 0x000000ff00010000, 0x000000ff01000000,
-    0x000000ff0101ff00, 0x00000000ffff0000, 0x00000000ff00ff00, 0x00000000ff0000ff,
-    0x00000000ff000000, 0x00000000ff000001, 0x00000000ff000100, 0x00000000ff010000,
-    0x0000000000ffff00, 0x0000000000ff00ff, 0x0000000000ff0000, 0x0000000000ff0001,
-    0x0000000000ff0100, 0x000000000000ffff, 0x000000000000ff00, 0x000000000000ff01,
-    0x00000000000000ff, 0x0000000000000001, 0x00000000000001ff, 0x0000000000000100,
-    0x0000000000000101, 0x000000000001ff00, 0x00000000000100ff, 0x0000000000010000,
-    0x0000000000010001, 0x0000000000010100, 0x0000000001ff0000, 0x000000000100ff00,
-    0x00000000010000ff, 0x0000000001000000, 0x0000000001000001, 0x0000000001000100,
-    0x0000000001010000, 0x00000001ffff01ff, 0x00000001ff000000, 0x0000000100ff0000,
-    0x000000010000ff00, 0x00000001000000ff, 0x0000000100000000, 0x0000000100000001,
-    0x0000000100000100, 0x0000000100010000, 0x0000000101000000, 0x000001ffff00ff00,
-    0x000001ffff010001, 0x000001ffff0101ff, 0x000001ff00ffff01, 0x000001ff0000ffff,
-    0x000001ff00000000, 0x000001ff010000ff, 0x000001ff01010100, 0x00000100ffff0100,
-    0x00000100ff000000, 0x0000010000ff0000, 0x000001000000ff00, 0x00000100000000ff,
-    0x0000010000000000, 0x0000010000000001, 0x0000010000000100, 0x0000010000010000,
-    0x0000010001000000, 0x000001000101ff01, 0x00000101ffff0001, 0x00000101ff01ffff,
-    0x0000010100000000, 0x0000010101010100, 0x0001ffffff000000, 0x0001ffff00ffffff,
-    0x0001ffff00000100, 0x0001ffff0001ff00, 0x0001ffff01000000, 0x0001ff00ffffff00,
-    0x0001ff00ffff01ff, 0x0001ff00ff010000, 0x0001ff0000000000, 0x0001ff0000010001,
-    0x0001ff0001ff0000, 0x0001ff0001010100, 0x0001ff01ff0000ff, 0x0001ff01ff000001,
-    0x0001ff0100ffffff, 0x0001ff010001ffff, 0x0001ff01000101ff, 0x0001ff010100ff01,
-    0x000100ffff00ffff, 0x000100ffff00ff01, 0x000100ffff000100, 0x000100ff00000000,
-    0x000100ff000101ff, 0x000100ff01ff0101, 0x000100ff0100ffff, 0x000100ff01010101,
-    0x00010000ff000000, 0x00010000ff010100, 0x0001000000ff0000, 0x000100000000ff00,
-    0x00010000000000ff, 0x0001000000000000, 0x0001000000000001, 0x0001000000000100,
-    0x0001000000010000, 0x0001000001ffff01, 0x0001000001000000, 0x0001000100ff0101,
-    0x0001000100000000, 0x00010001010100ff, 0x000101ffffff01ff, 0x000101ffffff0101,
-    0x000101ff00010000, 0x000101ff01ff0000, 0x000101ff0100ff01, 0x00010100ffff0000,
-    0x0001010000000000, 0x000101000001ffff, 0x0001010000010101, 0x00010100010001ff,
-    0x00010101ff00ff00, 0x00010101ff010001, 0x0001010100ffffff, 0x0001010100ff01ff,
-    0x00010101000101ff, 0x0001010101ff0000, 0x000101010100ff01, 0x0001010101000101,
-    0x01ffffffffff0101, 0x01ffffffff01ffff, 0x01ffffffff01ff01, 0x01ffffffff0101ff,
-    0x01ffffffff010101, 0x01ffffff00000000, 0x01ffffff01ff01ff, 0x01ffffff01000101,
-    0x01ffffff0101ff01, 0x01ffffff010100ff, 0x01ffff000000ff00, 0x01ffff0000000001,
-    0x01ffff00000001ff, 0x01ffff0000010000, 0x01ffff0001ff0000, 0x01ffff01ffffffff,
-    0x01ffff01ffff01ff, 0x01ffff01ff000000, 0x01ffff01ff01ffff, 0x01ffff01ff0101ff,
-    0x01ffff010100ffff, 0x01ff00ffffff0000, 0x01ff00ffff010000, 0x01ff00ff00ffff01,
-    0x01ff0000ff0000ff, 0x01ff000000000000, 0x01ff00000001ff01, 0x01ff000001ffffff,
-    0x01ff000001010100, 0x01ff0001ffffff01, 0x01ff0001ff010001, 0x01ff000101ff0100,
-    0x01ff000101000001, 0x01ff0001010100ff, 0x01ff01ffff00ffff, 0x01ff01ff00010001,
-    0x01ff01ff01000000, 0x01ff01ff010101ff, 0x01ff0100ff000001, 0x01ff010000ffff00,
-    0x01ff010000000100, 0x01ff010001ff01ff, 0x01ff01000101ffff, 0x01ff0101ffff00ff,
-    0x01ff0101ffff0101, 0x01ff0101ff0101ff, 0x01ff010100010000, 0x0100ffff00ff00ff,
-    0x0100ffff00ff0001, 0x0100ffff00000100, 0x0100ffff0100ff00, 0x0100ff00ffff0000,
-    0x0100ff00ff00ffff, 0x0100ff00ff00ff01, 0x0100ff00ff000100, 0x0100ff00ff010000,
-    0x0100ff0000000000, 0x0100ff00000100ff, 0x0100ff0001ff0101, 0x0100ff0001010101,
-    0x0100ff0100ff00ff, 0x0100ff0100ff0001, 0x0100ff0100000100, 0x0100ff0100010001,
-    0x0100ff0101000000, 0x010000ffff00ff00, 0x010000ff0000ffff, 0x010000ff00000000,
-    0x010000ff010001ff, 0x010000ff01010001, 0x01000000ffffff00, 0x01000000ffff0101,
-    0x01000000ff000000, 0x01000000ff0100ff, 0x01000000ff010101, 0x0100000000ff0000,
-    0x010000000000ff00, 0x01000000000000ff, 0x0100000000000000, 0x0100000000000001,
-    0x0100000000000100, 0x0100000000010000, 0x0100000001000000, 0x0100000100000000,
-    0x01000001000101ff, 0x0100000101ffff01, 0x010001ffff000101, 0x010001ff00ff0100,
-    0x010001ff0000ff00, 0x010001ff000100ff, 0x010001ff01ffffff, 0x01000100ffff0000,
-    0x01000100ff0001ff, 0x0100010000000000, 0x010001000001ff00, 0x0100010001ff0000,
-    0x01000100010000ff, 0x0100010001000101, 0x01000101ff00ff01, 0x0100010100ff0100,
-    0x010001010000ffff, 0x0100010101010001, 0x0101ffffffff0101, 0x0101ffffff0001ff,
-    0x0101ffffff01ffff, 0x0101ffffff010101, 0x0101ffff00000000, 0x0101ffff0101ffff,
-    0x0101ffff010101ff, 0x0101ff00ff000000, 0x0101ff0000ff0100, 0x0101ff000000ff00,
-    0x0101ff0000010000, 0x0101ff00010000ff, 0x0101ff0001000001, 0x0101ff01ff010101,
-    0x0101ff0100000000, 0x0101ff010101ff00, 0x010100ffffff0000, 0x010100ffff010000,
-    0x010100ff00ff01ff, 0x010100ff000000ff, 0x010100ff00000101, 0x010100ff01ffff00,
-    0x01010000ffffff01, 0x01010000ff000100, 0x01010000ff01ff01, 0x0101000000000000,
-    0x01010000000100ff, 0x010100000101ff01, 0x01010001ffff0000, 0x01010001ff00ffff,
-    0x01010001ff010000, 0x0101000101ffffff, 0x0101000101ff01ff, 0x0101000101010101,
-    0x010101ffff01ffff, 0x010101ff00000000, 0x010101ff0001ff01, 0x010101ff0101ffff,
-    0x010101ff010101ff, 0x01010100ffffffff, 0x01010100ff000001, 0x010101000000ff00,
-    0x0101010001010000, 0x0101010100ff0001, 0x010101010001ff01, 0x010101010101ffff,
-};
-
-static const __device__ uint8_t ksigns_iq2xs[128] = {
-      0, 129, 130,   3, 132,   5,   6, 135, 136,   9,  10, 139,  12, 141, 142,  15,
-    144,  17,  18, 147,  20, 149, 150,  23,  24, 153, 154,  27, 156,  29,  30, 159,
-    160,  33,  34, 163,  36, 165, 166,  39,  40, 169, 170,  43, 172,  45,  46, 175,
-     48, 177, 178,  51, 180,  53,  54, 183, 184,  57,  58, 187,  60, 189, 190,  63,
-    192,  65,  66, 195,  68, 197, 198,  71,  72, 201, 202,  75, 204,  77,  78, 207,
-     80, 209, 210,  83, 212,  85,  86, 215, 216,  89,  90, 219,  92, 221, 222,  95,
-     96, 225, 226,  99, 228, 101, 102, 231, 232, 105, 106, 235, 108, 237, 238, 111,
-    240, 113, 114, 243, 116, 245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255,
-};
-
-//#if __CUDA_ARCH__ >= MIN_CC_DP4A // lowest compute capability for integer intrinsics
-static const __device__ uint64_t ksigns64[128] = {
-    0x0000000000000000, 0xff000000000000ff, 0xff0000000000ff00, 0x000000000000ffff,
-    0xff00000000ff0000, 0x0000000000ff00ff, 0x0000000000ffff00, 0xff00000000ffffff,
-    0xff000000ff000000, 0x00000000ff0000ff, 0x00000000ff00ff00, 0xff000000ff00ffff,
-    0x00000000ffff0000, 0xff000000ffff00ff, 0xff000000ffffff00, 0x00000000ffffffff,
-    0xff0000ff00000000, 0x000000ff000000ff, 0x000000ff0000ff00, 0xff0000ff0000ffff,
-    0x000000ff00ff0000, 0xff0000ff00ff00ff, 0xff0000ff00ffff00, 0x000000ff00ffffff,
-    0x000000ffff000000, 0xff0000ffff0000ff, 0xff0000ffff00ff00, 0x000000ffff00ffff,
-    0xff0000ffffff0000, 0x000000ffffff00ff, 0x000000ffffffff00, 0xff0000ffffffffff,
-    0xff00ff0000000000, 0x0000ff00000000ff, 0x0000ff000000ff00, 0xff00ff000000ffff,
-    0x0000ff0000ff0000, 0xff00ff0000ff00ff, 0xff00ff0000ffff00, 0x0000ff0000ffffff,
-    0x0000ff00ff000000, 0xff00ff00ff0000ff, 0xff00ff00ff00ff00, 0x0000ff00ff00ffff,
-    0xff00ff00ffff0000, 0x0000ff00ffff00ff, 0x0000ff00ffffff00, 0xff00ff00ffffffff,
-    0x0000ffff00000000, 0xff00ffff000000ff, 0xff00ffff0000ff00, 0x0000ffff0000ffff,
-    0xff00ffff00ff0000, 0x0000ffff00ff00ff, 0x0000ffff00ffff00, 0xff00ffff00ffffff,
-    0xff00ffffff000000, 0x0000ffffff0000ff, 0x0000ffffff00ff00, 0xff00ffffff00ffff,
-    0x0000ffffffff0000, 0xff00ffffffff00ff, 0xff00ffffffffff00, 0x0000ffffffffffff,
-    0xffff000000000000, 0x00ff0000000000ff, 0x00ff00000000ff00, 0xffff00000000ffff,
-    0x00ff000000ff0000, 0xffff000000ff00ff, 0xffff000000ffff00, 0x00ff000000ffffff,
-    0x00ff0000ff000000, 0xffff0000ff0000ff, 0xffff0000ff00ff00, 0x00ff0000ff00ffff,
-    0xffff0000ffff0000, 0x00ff0000ffff00ff, 0x00ff0000ffffff00, 0xffff0000ffffffff,
-    0x00ff00ff00000000, 0xffff00ff000000ff, 0xffff00ff0000ff00, 0x00ff00ff0000ffff,
-    0xffff00ff00ff0000, 0x00ff00ff00ff00ff, 0x00ff00ff00ffff00, 0xffff00ff00ffffff,
-    0xffff00ffff000000, 0x00ff00ffff0000ff, 0x00ff00ffff00ff00, 0xffff00ffff00ffff,
-    0x00ff00ffffff0000, 0xffff00ffffff00ff, 0xffff00ffffffff00, 0x00ff00ffffffffff,
-    0x00ffff0000000000, 0xffffff00000000ff, 0xffffff000000ff00, 0x00ffff000000ffff,
-    0xffffff0000ff0000, 0x00ffff0000ff00ff, 0x00ffff0000ffff00, 0xffffff0000ffffff,
-    0xffffff00ff000000, 0x00ffff00ff0000ff, 0x00ffff00ff00ff00, 0xffffff00ff00ffff,
-    0x00ffff00ffff0000, 0xffffff00ffff00ff, 0xffffff00ffffff00, 0x00ffff00ffffffff,
-    0xffffffff00000000, 0x00ffffff000000ff, 0x00ffffff0000ff00, 0xffffffff0000ffff,
-    0x00ffffff00ff0000, 0xffffffff00ff00ff, 0xffffffff00ffff00, 0x00ffffff00ffffff,
-    0x00ffffffff000000, 0xffffffffff0000ff, 0xffffffffff00ff00, 0x00ffffffff00ffff,
-    0xffffffffffff0000, 0x00ffffffffff00ff, 0x00ffffffffffff00, 0xffffffffffffffff,
-};
-//#endif
-
-static const __device__ uint8_t kmask_iq2xs[8] = {1, 2, 4, 8, 16, 32, 64, 128};
-
 inline bool ggml_cuda_supports_mmq(enum ggml_type type) {
    switch (type) {
        case GGML_TYPE_Q4_0:
@@ -1,5 +1,8 @@
 #include <metal_stdlib>

+#define GGML_COMMON_IMPL_METAL
+#include "ggml-common.h"
+
 using namespace metal;

 #define MAX(x, y) ((x) > (y) ? (x) : (y))
@@ -3638,710 +3641,6 @@ kernel void kernel_mul_mv_q6_K_f32(

 // ======================= "True" 2-bit

-constexpr constant static uint64_t iq2xxs_grid[256] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808,
-    0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819,
-    0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819,
-    0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b,
-    0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808,
-    0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08,
-    0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b,
-    0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819,
-    0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08,
-    0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808,
-    0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08,
-    0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808,
-    0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808,
-    0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919,
-    0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819,
-    0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08,
-    0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908,
-    0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819,
-    0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808,
-    0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808,
-    0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908,
-    0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808,
-    0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08,
-    0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819,
-    0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819,
-    0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819,
-    0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908,
-    0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19,
-    0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819,
-    0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b,
-    0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808,
-    0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908,
-    0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08,
-    0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08,
-    0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908,
-    0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819,
-    0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808,
-    0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808,
-    0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19,
-    0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819,
-    0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919,
-    0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b,
-    0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08,
-    0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808,
-    0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908,
-    0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b,
-    0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819,
-    0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08,
-    0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08,
-    0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808,
-    0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b,
-    0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b,
-    0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908,
-    0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819,
-    0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808,
-    0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908,
-    0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b,
-    0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808,
-    0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b,
-    0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b,
-    0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808,
-    0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19,
-    0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908,
-};
-
-constexpr constant static uint64_t iq2xs_grid[512] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
-    0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
-    0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
-    0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
-    0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808,
-    0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08, 0x080808082b190819,
-    0x080808082b191908, 0x080808082b192b19, 0x080808082b2b0808, 0x0808081908080819,
-    0x0808081908081908, 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808,
-    0x080808190819082b, 0x0808081908191919, 0x0808081908192b08, 0x0808081908192b2b,
-    0x08080819082b0819, 0x08080819082b1908, 0x0808081919080808, 0x080808191908082b,
-    0x0808081919081919, 0x0808081919082b08, 0x0808081919190819, 0x0808081919191908,
-    0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819, 0x080808192b081908,
-    0x080808192b190808, 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b08081919,
-    0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808,
-    0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808, 0x0808082b19191919,
-    0x0808082b2b080808, 0x0808082b2b082b2b, 0x0808190808080819, 0x0808190808081908,
-    0x080819080808192b, 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b,
-    0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908,
-    0x0808190819080808, 0x080819081908082b, 0x0808190819081919, 0x0808190819082b08,
-    0x0808190819190819, 0x0808190819191908, 0x080819081919192b, 0x08081908192b0808,
-    0x080819082b080819, 0x080819082b081908, 0x080819082b190808, 0x0808191908080808,
-    0x080819190808082b, 0x0808191908081919, 0x0808191908082b08, 0x0808191908190819,
-    0x0808191908191908, 0x08081919082b0808, 0x0808191919080819, 0x0808191919081908,
-    0x0808191919190808, 0x08081919192b0819, 0x080819192b080808, 0x0808192b08080819,
-    0x0808192b08081908, 0x0808192b08190808, 0x0808192b082b192b, 0x0808192b19080808,
-    0x0808192b1908082b, 0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b,
-    0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b, 0x08082b0808190819,
-    0x08082b0808191908, 0x08082b08082b0808, 0x08082b08082b1919, 0x08082b0819080819,
-    0x08082b0819081908, 0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808,
-    0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819, 0x08082b1908081908,
-    0x08082b1908190808, 0x08082b1919080808, 0x08082b192b080819, 0x08082b192b082b19,
-    0x08082b2b08080808, 0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b,
-    0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908, 0x081908080808192b,
-    0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, 0x0819080808191919,
-    0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808,
-    0x081908081908082b, 0x0819080819081919, 0x0819080819082b08, 0x0819080819190819,
-    0x0819080819191908, 0x08190808192b0808, 0x08190808192b2b2b, 0x081908082b080819,
-    0x081908082b081908, 0x081908082b190808, 0x0819081908080808, 0x081908190808082b,
-    0x0819081908081919, 0x0819081908082b08, 0x0819081908190819, 0x0819081908191908,
-    0x08190819082b0808, 0x0819081919080819, 0x0819081919081908, 0x0819081919190808,
-    0x081908192b080808, 0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819,
-    0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808, 0x0819082b19080808,
-    0x0819082b192b0808, 0x0819190808080808, 0x081919080808082b, 0x0819190808081919,
-    0x0819190808082b08, 0x0819190808190819, 0x0819190808191908, 0x08191908082b0808,
-    0x0819190819080819, 0x0819190819081908, 0x0819190819082b19, 0x0819190819190808,
-    0x08191908192b1908, 0x081919082b080808, 0x0819191908080819, 0x0819191908081908,
-    0x0819191908190808, 0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908,
-    0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808,
-    0x08192b080819082b, 0x08192b0819080808, 0x08192b0819191908, 0x08192b082b08192b,
-    0x08192b1908080808, 0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819,
-    0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919,
-    0x082b080808082b08, 0x082b080808082b2b, 0x082b080808190819, 0x082b080808191908,
-    0x082b0808082b0808, 0x082b080819080819, 0x082b080819081908, 0x082b080819190808,
-    0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819, 0x082b081908081908,
-    0x082b081908190808, 0x082b081919080808, 0x082b081919082b08, 0x082b0819192b1919,
-    0x082b082b08080808, 0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08,
-    0x082b190808080819, 0x082b190808081908, 0x082b190808190808, 0x082b1908082b2b19,
-    0x082b190819080808, 0x082b191908080808, 0x082b191919080819, 0x082b19191919082b,
-    0x082b19192b192b19, 0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b,
-    0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b, 0x082b2b08082b0808,
-    0x082b2b0819191919, 0x082b2b082b082b08, 0x082b2b082b2b082b, 0x082b2b19192b2b08,
-    0x082b2b192b190808, 0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b,
-    0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, 0x1908080808081908,
-    0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, 0x190808080819082b,
-    0x1908080808191919, 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908,
-    0x1908080819080808, 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08,
-    0x1908080819082b2b, 0x1908080819190819, 0x1908080819191908, 0x19080808192b0808,
-    0x19080808192b1919, 0x190808082b080819, 0x190808082b081908, 0x190808082b190808,
-    0x1908081908080808, 0x190808190808082b, 0x1908081908081919, 0x1908081908082b08,
-    0x1908081908190819, 0x1908081908191908, 0x19080819082b0808, 0x1908081919080819,
-    0x1908081919081908, 0x1908081919190808, 0x190808192b080808, 0x190808192b081919,
-    0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908, 0x1908082b08190808,
-    0x1908082b0819082b, 0x1908082b082b2b19, 0x1908082b19080808, 0x1908190808080808,
-    0x190819080808082b, 0x1908190808081919, 0x1908190808082b08, 0x1908190808190819,
-    0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808, 0x1908190819080819,
-    0x1908190819081908, 0x1908190819190808, 0x190819082b080808, 0x190819082b191908,
-    0x1908191908080819, 0x1908191908081908, 0x1908191908190808, 0x19081919082b1908,
-    0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808, 0x1908192b08082b2b,
-    0x1908192b19081908, 0x1908192b19190808, 0x19082b0808080819, 0x19082b0808081908,
-    0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908,
-    0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819, 0x19082b1919081908,
-    0x19082b1919190808, 0x19082b19192b2b19, 0x19082b2b08081908, 0x1919080808080808,
-    0x191908080808082b, 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819,
-    0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08, 0x1919080819080819,
-    0x1919080819081908, 0x1919080819190808, 0x191908082b080808, 0x1919081908080819,
-    0x1919081908081908, 0x1919081908190808, 0x1919081908191919, 0x1919081919080808,
-    0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908, 0x1919082b2b2b2b2b,
-    0x1919190808080819, 0x1919190808081908, 0x1919190808190808, 0x19191908082b0819,
-    0x1919190819080808, 0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819,
-    0x1919191908080808, 0x1919191908082b08, 0x191919192b080808, 0x191919192b082b08,
-    0x1919192b082b0819, 0x1919192b192b2b08, 0x1919192b2b2b0819, 0x19192b0808080808,
-    0x19192b0808191908, 0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19,
-    0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b, 0x19192b2b2b081919,
-    0x192b080808080819, 0x192b080808081908, 0x192b080808190808, 0x192b080819080808,
-    0x192b080819191908, 0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19,
-    0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b, 0x192b082b2b19082b,
-    0x192b190808080808, 0x192b19080819192b, 0x192b191908190808, 0x192b191919080808,
-    0x192b191919081919, 0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b,
-    0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908, 0x192b2b2b192b082b,
-    0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08,
-    0x2b08080808190819, 0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b,
-    0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808082b080808,
-    0x2b0808082b08082b, 0x2b0808082b2b2b08, 0x2b0808082b2b2b2b, 0x2b08081908080819,
-    0x2b08081908081908, 0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808,
-    0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808, 0x2b08082b082b0808,
-    0x2b08082b2b080808, 0x2b08082b2b08082b, 0x2b08082b2b2b0808, 0x2b08082b2b2b2b08,
-    0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b,
-    0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, 0x2b0819082b082b19,
-    0x2b08191908080808, 0x2b08191919081908, 0x2b0819192b2b1919, 0x2b08192b08192b08,
-    0x2b08192b192b2b2b, 0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919,
-    0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b, 0x2b082b082b2b2b08,
-    0x2b082b190808192b, 0x2b082b2b082b082b, 0x2b082b2b2b080808, 0x2b082b2b2b082b08,
-    0x2b082b2b2b19192b, 0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908,
-    0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b, 0x2b1908082b081908,
-    0x2b19081908080808, 0x2b190819082b082b, 0x2b190819192b1908, 0x2b19082b1919192b,
-    0x2b19082b2b082b19, 0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908,
-    0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19, 0x2b1919192b190808,
-    0x2b1919192b19082b, 0x2b19192b19080819, 0x2b192b0819190819, 0x2b192b082b2b192b,
-    0x2b192b1919082b19, 0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808,
-    0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b, 0x2b2b0808082b0808,
-    0x2b2b0808082b2b2b, 0x2b2b08082b2b0808, 0x2b2b081919190819, 0x2b2b081919192b19,
-    0x2b2b08192b2b192b, 0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08,
-    0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808, 0x2b2b190819080808,
-    0x2b2b19082b191919, 0x2b2b192b192b1919, 0x2b2b192b2b192b08, 0x2b2b2b0808082b2b,
-    0x2b2b2b08082b0808, 0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808,
-    0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908, 0x2b2b2b192b08192b,
-    0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b,
-};
-
-constexpr constant static uint64_t iq2s_grid[1024] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
-    0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
-    0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
-    0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
-    0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x08080808192b192b,
-    0x08080808192b2b19, 0x080808082b080808, 0x080808082b08082b, 0x080808082b081919,
-    0x080808082b082b08, 0x080808082b190819, 0x080808082b191908, 0x080808082b2b0808,
-    0x080808082b2b1919, 0x080808082b2b2b2b, 0x0808081908080819, 0x0808081908081908,
-    0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, 0x080808190819082b,
-    0x0808081908191919, 0x0808081908192b08, 0x08080819082b0819, 0x08080819082b1908,
-    0x0808081919080808, 0x080808191908082b, 0x0808081919081919, 0x0808081919082b08,
-    0x0808081919190819, 0x0808081919191908, 0x080808191919192b, 0x0808081919192b19,
-    0x08080819192b0808, 0x08080819192b1919, 0x08080819192b2b08, 0x080808192b080819,
-    0x080808192b081908, 0x080808192b190808, 0x080808192b19082b, 0x080808192b191919,
-    0x080808192b2b0819, 0x080808192b2b1908, 0x0808082b08080808, 0x0808082b0808082b,
-    0x0808082b08081919, 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908,
-    0x0808082b082b0808, 0x0808082b082b2b2b, 0x0808082b19080819, 0x0808082b19081908,
-    0x0808082b1908192b, 0x0808082b19082b19, 0x0808082b19190808, 0x0808082b19191919,
-    0x0808082b2b080808, 0x0808082b2b081919, 0x0808082b2b082b2b, 0x0808082b2b191908,
-    0x0808082b2b2b082b, 0x0808190808080819, 0x0808190808081908, 0x080819080808192b,
-    0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, 0x0808190808191919,
-    0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, 0x08081908082b192b,
-    0x08081908082b2b19, 0x0808190819080808, 0x080819081908082b, 0x0808190819081919,
-    0x0808190819082b08, 0x0808190819082b2b, 0x0808190819190819, 0x0808190819191908,
-    0x080819081919192b, 0x0808190819192b19, 0x08081908192b0808, 0x08081908192b082b,
-    0x08081908192b1919, 0x080819082b080819, 0x080819082b081908, 0x080819082b08192b,
-    0x080819082b082b19, 0x080819082b190808, 0x080819082b191919, 0x080819082b192b08,
-    0x080819082b2b0819, 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b,
-    0x0808191908081919, 0x0808191908082b08, 0x0808191908082b2b, 0x0808191908190819,
-    0x0808191908191908, 0x080819190819192b, 0x0808191908192b19, 0x08081919082b0808,
-    0x08081919082b1919, 0x08081919082b2b08, 0x0808191919080819, 0x0808191919081908,
-    0x080819191908192b, 0x0808191919082b19, 0x0808191919190808, 0x080819191919082b,
-    0x0808191919191919, 0x0808191919192b08, 0x08081919192b0819, 0x08081919192b1908,
-    0x080819192b080808, 0x080819192b08082b, 0x080819192b081919, 0x080819192b082b08,
-    0x080819192b190819, 0x080819192b191908, 0x080819192b2b0808, 0x0808192b08080819,
-    0x0808192b08081908, 0x0808192b0808192b, 0x0808192b08082b19, 0x0808192b08190808,
-    0x0808192b08191919, 0x0808192b19080808, 0x0808192b19081919, 0x0808192b19082b08,
-    0x0808192b19190819, 0x0808192b19191908, 0x0808192b192b0808, 0x0808192b2b080819,
-    0x0808192b2b081908, 0x0808192b2b190808, 0x08082b0808080808, 0x08082b080808082b,
-    0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808190819, 0x08082b0808191908,
-    0x08082b080819192b, 0x08082b0808192b19, 0x08082b08082b0808, 0x08082b08082b1919,
-    0x08082b08082b2b2b, 0x08082b0819080819, 0x08082b0819081908, 0x08082b081908192b,
-    0x08082b0819082b19, 0x08082b0819190808, 0x08082b081919082b, 0x08082b0819191919,
-    0x08082b0819192b08, 0x08082b08192b0819, 0x08082b08192b1908, 0x08082b082b080808,
-    0x08082b082b081919, 0x08082b082b191908, 0x08082b082b2b2b2b, 0x08082b1908080819,
-    0x08082b1908081908, 0x08082b1908190808, 0x08082b190819082b, 0x08082b1908191919,
-    0x08082b1908192b08, 0x08082b19082b0819, 0x08082b1919080808, 0x08082b1919081919,
-    0x08082b1919082b08, 0x08082b1919190819, 0x08082b1919191908, 0x08082b19192b0808,
-    0x08082b192b080819, 0x08082b192b190808, 0x08082b2b08080808, 0x08082b2b08190819,
-    0x08082b2b08191908, 0x08082b2b082b082b, 0x08082b2b082b2b08, 0x08082b2b082b2b2b,
-    0x08082b2b19190808, 0x08082b2b2b192b19, 0x0819080808080819, 0x0819080808081908,
-    0x081908080808192b, 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b,
-    0x0819080808191919, 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908,
-    0x08190808082b192b, 0x0819080819080808, 0x081908081908082b, 0x0819080819081919,
-    0x0819080819082b08, 0x0819080819190819, 0x0819080819191908, 0x081908081919192b,
-    0x0819080819192b19, 0x08190808192b0808, 0x08190808192b082b, 0x08190808192b1919,
-    0x08190808192b2b08, 0x081908082b080819, 0x081908082b081908, 0x081908082b08192b,
-    0x081908082b190808, 0x081908082b191919, 0x081908082b192b08, 0x081908082b2b0819,
-    0x081908082b2b1908, 0x0819081908080808, 0x081908190808082b, 0x0819081908081919,
-    0x0819081908082b08, 0x0819081908082b2b, 0x0819081908190819, 0x0819081908191908,
-    0x081908190819192b, 0x0819081908192b19, 0x08190819082b0808, 0x08190819082b082b,
-    0x08190819082b1919, 0x08190819082b2b08, 0x0819081919080819, 0x0819081919081908,
-    0x081908191908192b, 0x0819081919082b19, 0x0819081919190808, 0x081908191919082b,
-    0x0819081919191919, 0x0819081919192b08, 0x08190819192b0819, 0x08190819192b1908,
-    0x081908192b080808, 0x081908192b08082b, 0x081908192b081919, 0x081908192b082b08,
-    0x081908192b190819, 0x081908192b191908, 0x0819082b08080819, 0x0819082b08081908,
-    0x0819082b08082b19, 0x0819082b08190808, 0x0819082b08191919, 0x0819082b082b0819,
-    0x0819082b082b1908, 0x0819082b19080808, 0x0819082b19081919, 0x0819082b19190819,
-    0x0819082b19191908, 0x0819082b2b080819, 0x0819082b2b081908, 0x0819082b2b190808,
-    0x0819190808080808, 0x081919080808082b, 0x0819190808081919, 0x0819190808082b08,
-    0x0819190808190819, 0x0819190808191908, 0x081919080819192b, 0x0819190808192b19,
-    0x08191908082b0808, 0x08191908082b1919, 0x08191908082b2b08, 0x0819190819080819,
-    0x0819190819081908, 0x081919081908192b, 0x0819190819082b19, 0x0819190819190808,
-    0x081919081919082b, 0x0819190819191919, 0x0819190819192b08, 0x08191908192b0819,
-    0x08191908192b1908, 0x081919082b080808, 0x081919082b08082b, 0x081919082b081919,
-    0x081919082b082b08, 0x081919082b190819, 0x081919082b191908, 0x081919082b2b0808,
-    0x0819191908080819, 0x0819191908081908, 0x081919190808192b, 0x0819191908082b19,
-    0x0819191908190808, 0x081919190819082b, 0x0819191908191919, 0x0819191908192b08,
-    0x08191919082b0819, 0x08191919082b1908, 0x0819191919080808, 0x081919191908082b,
-    0x0819191919081919, 0x0819191919082b08, 0x0819191919190819, 0x0819191919191908,
-    0x08191919192b0808, 0x081919192b080819, 0x081919192b081908, 0x081919192b190808,
-    0x0819192b08080808, 0x0819192b08081919, 0x0819192b08082b08, 0x0819192b08190819,
-    0x0819192b08191908, 0x0819192b082b0808, 0x0819192b19080819, 0x0819192b19081908,
-    0x0819192b19190808, 0x0819192b2b080808, 0x0819192b2b2b2b2b, 0x08192b0808080819,
-    0x08192b0808081908, 0x08192b080808192b, 0x08192b0808082b19, 0x08192b0808190808,
-    0x08192b0808191919, 0x08192b0808192b08, 0x08192b08082b0819, 0x08192b0819080808,
-    0x08192b081908082b, 0x08192b0819081919, 0x08192b0819082b08, 0x08192b0819190819,
-    0x08192b0819191908, 0x08192b08192b0808, 0x08192b082b080819, 0x08192b082b081908,
-    0x08192b1908080808, 0x08192b190808082b, 0x08192b1908081919, 0x08192b1908082b08,
-    0x08192b1908190819, 0x08192b1908191908, 0x08192b19082b0808, 0x08192b1919080819,
-    0x08192b1919081908, 0x08192b1919190808, 0x08192b19192b2b19, 0x08192b192b2b082b,
-    0x08192b2b08081908, 0x08192b2b08190808, 0x08192b2b19080808, 0x08192b2b1919192b,
-    0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, 0x082b080808082b08,
-    0x082b080808190819, 0x082b080808191908, 0x082b08080819192b, 0x082b080808192b19,
-    0x082b0808082b0808, 0x082b0808082b1919, 0x082b0808082b2b2b, 0x082b080819080819,
-    0x082b080819081908, 0x082b080819190808, 0x082b08081919082b, 0x082b080819191919,
-    0x082b0808192b1908, 0x082b08082b080808, 0x082b08082b082b2b, 0x082b08082b191908,
-    0x082b08082b2b2b2b, 0x082b081908080819, 0x082b081908081908, 0x082b081908190808,
-    0x082b08190819082b, 0x082b081908191919, 0x082b0819082b0819, 0x082b081919080808,
-    0x082b08191908082b, 0x082b081919081919, 0x082b081919190819, 0x082b081919191908,
-    0x082b0819192b0808, 0x082b08192b080819, 0x082b08192b081908, 0x082b08192b190808,
-    0x082b082b08080808, 0x082b082b08082b2b, 0x082b082b082b082b, 0x082b082b082b2b08,
-    0x082b082b082b2b2b, 0x082b082b19081908, 0x082b082b19190808, 0x082b082b2b082b08,
-    0x082b082b2b082b2b, 0x082b082b2b2b2b08, 0x082b190808080819, 0x082b190808081908,
-    0x082b19080808192b, 0x082b190808082b19, 0x082b190808190808, 0x082b190808191919,
-    0x082b190808192b08, 0x082b1908082b0819, 0x082b1908082b1908, 0x082b190819080808,
-    0x082b19081908082b, 0x082b190819081919, 0x082b190819082b08, 0x082b190819190819,
-    0x082b190819191908, 0x082b1908192b0808, 0x082b19082b080819, 0x082b19082b081908,
-    0x082b19082b190808, 0x082b191908080808, 0x082b191908081919, 0x082b191908082b08,
-    0x082b191908190819, 0x082b191908191908, 0x082b1919082b0808, 0x082b191919080819,
-    0x082b191919081908, 0x082b191919190808, 0x082b1919192b192b, 0x082b19192b080808,
-    0x082b192b08080819, 0x082b192b08081908, 0x082b192b08190808, 0x082b192b19080808,
-    0x082b192b19192b19, 0x082b2b0808080808, 0x082b2b0808081919, 0x082b2b0808190819,
-    0x082b2b0808191908, 0x082b2b0819080819, 0x082b2b0819081908, 0x082b2b0819190808,
-    0x082b2b082b082b2b, 0x082b2b082b2b2b2b, 0x082b2b1908080819, 0x082b2b1908081908,
-    0x082b2b1908190808, 0x082b2b192b191919, 0x082b2b2b08082b2b, 0x082b2b2b082b082b,
-    0x082b2b2b192b1908, 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819,
-    0x1908080808081908, 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808,
-    0x190808080819082b, 0x1908080808191919, 0x1908080808192b08, 0x1908080808192b2b,
-    0x19080808082b0819, 0x19080808082b1908, 0x19080808082b192b, 0x1908080819080808,
-    0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, 0x1908080819082b2b,
-    0x1908080819190819, 0x1908080819191908, 0x190808081919192b, 0x1908080819192b19,
-    0x19080808192b0808, 0x19080808192b082b, 0x19080808192b1919, 0x190808082b080819,
-    0x190808082b081908, 0x190808082b190808, 0x190808082b191919, 0x190808082b192b08,
-    0x190808082b2b0819, 0x190808082b2b1908, 0x1908081908080808, 0x190808190808082b,
-    0x1908081908081919, 0x1908081908082b08, 0x1908081908190819, 0x1908081908191908,
-    0x190808190819192b, 0x1908081908192b19, 0x19080819082b0808, 0x19080819082b082b,
-    0x19080819082b1919, 0x1908081919080819, 0x1908081919081908, 0x190808191908192b,
-    0x1908081919082b19, 0x1908081919190808, 0x190808191919082b, 0x1908081919191919,
-    0x1908081919192b08, 0x19080819192b0819, 0x19080819192b1908, 0x190808192b080808,
-    0x190808192b08082b, 0x190808192b081919, 0x190808192b082b08, 0x190808192b190819,
-    0x190808192b191908, 0x190808192b2b0808, 0x1908082b08080819, 0x1908082b08081908,
-    0x1908082b08190808, 0x1908082b0819082b, 0x1908082b08191919, 0x1908082b08192b08,
-    0x1908082b082b1908, 0x1908082b19080808, 0x1908082b19081919, 0x1908082b19082b08,
-    0x1908082b19190819, 0x1908082b19191908, 0x1908082b192b0808, 0x1908082b2b080819,
-    0x1908082b2b081908, 0x1908190808080808, 0x190819080808082b, 0x1908190808081919,
-    0x1908190808082b08, 0x1908190808082b2b, 0x1908190808190819, 0x1908190808191908,
-    0x190819080819192b, 0x1908190808192b19, 0x19081908082b0808, 0x19081908082b082b,
-    0x19081908082b1919, 0x19081908082b2b08, 0x1908190819080819, 0x1908190819081908,
-    0x190819081908192b, 0x1908190819082b19, 0x1908190819190808, 0x190819081919082b,
-    0x1908190819191919, 0x1908190819192b08, 0x19081908192b0819, 0x19081908192b1908,
-    0x190819082b080808, 0x190819082b08082b, 0x190819082b081919, 0x190819082b082b08,
-    0x190819082b190819, 0x190819082b191908, 0x190819082b2b0808, 0x1908191908080819,
-    0x1908191908081908, 0x190819190808192b, 0x1908191908082b19, 0x1908191908190808,
-    0x190819190819082b, 0x1908191908191919, 0x1908191908192b08, 0x19081919082b0819,
-    0x19081919082b1908, 0x1908191919080808, 0x190819191908082b, 0x1908191919081919,
-    0x1908191919082b08, 0x1908191919190819, 0x1908191919191908, 0x19081919192b0808,
-    0x19081919192b2b2b, 0x190819192b080819, 0x190819192b081908, 0x190819192b190808,
-    0x1908192b08080808, 0x1908192b0808082b, 0x1908192b08081919, 0x1908192b08082b08,
-    0x1908192b08190819, 0x1908192b08191908, 0x1908192b082b0808, 0x1908192b19080819,
-    0x1908192b19081908, 0x1908192b19190808, 0x1908192b2b080808, 0x1908192b2b2b1919,
-    0x19082b0808080819, 0x19082b0808081908, 0x19082b0808082b19, 0x19082b0808190808,
-    0x19082b080819082b, 0x19082b0808191919, 0x19082b0808192b08, 0x19082b08082b0819,
-    0x19082b08082b1908, 0x19082b0819080808, 0x19082b081908082b, 0x19082b0819081919,
-    0x19082b0819082b08, 0x19082b0819190819, 0x19082b0819191908, 0x19082b08192b0808,
-    0x19082b082b081908, 0x19082b082b190808, 0x19082b1908080808, 0x19082b190808082b,
-    0x19082b1908081919, 0x19082b1908082b08, 0x19082b1908190819, 0x19082b1908191908,
-    0x19082b19082b0808, 0x19082b1919080819, 0x19082b1919081908, 0x19082b1919190808,
-    0x19082b192b080808, 0x19082b192b19192b, 0x19082b2b08080819, 0x19082b2b08081908,
-    0x19082b2b08190808, 0x19082b2b19080808, 0x1919080808080808, 0x191908080808082b,
-    0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, 0x1919080808191908,
-    0x191908080819192b, 0x1919080808192b19, 0x19190808082b0808, 0x19190808082b082b,
-    0x19190808082b1919, 0x19190808082b2b08, 0x1919080819080819, 0x1919080819081908,
-    0x191908081908192b, 0x1919080819082b19, 0x1919080819190808, 0x191908081919082b,
-    0x1919080819191919, 0x1919080819192b08, 0x19190808192b0819, 0x19190808192b1908,
-    0x191908082b080808, 0x191908082b08082b, 0x191908082b081919, 0x191908082b082b08,
-    0x191908082b190819, 0x191908082b191908, 0x1919081908080819, 0x1919081908081908,
-    0x191908190808192b, 0x1919081908082b19, 0x1919081908190808, 0x191908190819082b,
-    0x1919081908191919, 0x1919081908192b08, 0x19190819082b0819, 0x19190819082b1908,
-    0x1919081919080808, 0x191908191908082b, 0x1919081919081919, 0x1919081919082b08,
-    0x1919081919190819, 0x1919081919191908, 0x19190819192b0808, 0x191908192b080819,
-    0x191908192b081908, 0x191908192b190808, 0x1919082b08080808, 0x1919082b08081919,
-    0x1919082b08082b08, 0x1919082b08190819, 0x1919082b08191908, 0x1919082b082b0808,
-    0x1919082b19080819, 0x1919082b19081908, 0x1919082b19190808, 0x1919082b192b2b19,
-    0x1919082b2b080808, 0x1919190808080819, 0x1919190808081908, 0x191919080808192b,
-    0x1919190808082b19, 0x1919190808190808, 0x191919080819082b, 0x1919190808191919,
-    0x1919190808192b08, 0x19191908082b0819, 0x19191908082b1908, 0x1919190819080808,
-    0x191919081908082b, 0x1919190819081919, 0x1919190819082b08, 0x1919190819190819,
-    0x1919190819191908, 0x19191908192b0808, 0x191919082b080819, 0x191919082b081908,
-    0x191919082b190808, 0x1919191908080808, 0x191919190808082b, 0x1919191908081919,
-    0x1919191908082b08, 0x1919191908190819, 0x1919191908191908, 0x19191919082b0808,
-    0x1919191919080819, 0x1919191919081908, 0x1919191919190808, 0x191919192b080808,
-    0x1919192b08080819, 0x1919192b08081908, 0x1919192b08190808, 0x1919192b082b192b,
-    0x1919192b19080808, 0x19192b0808080808, 0x19192b080808082b, 0x19192b0808081919,
-    0x19192b0808082b08, 0x19192b0808190819, 0x19192b0808191908, 0x19192b08082b0808,
-    0x19192b0819080819, 0x19192b0819081908, 0x19192b0819190808, 0x19192b0819192b2b,
-    0x19192b082b080808, 0x19192b1908080819, 0x19192b1908081908, 0x19192b1908190808,
-    0x19192b1919080808, 0x19192b2b08080808, 0x19192b2b08192b19, 0x19192b2b2b081919,
-    0x19192b2b2b2b2b08, 0x192b080808080819, 0x192b080808081908, 0x192b08080808192b,
-    0x192b080808190808, 0x192b08080819082b, 0x192b080808191919, 0x192b080808192b08,
-    0x192b0808082b0819, 0x192b0808082b1908, 0x192b080819080808, 0x192b080819081919,
-    0x192b080819082b08, 0x192b080819190819, 0x192b080819191908, 0x192b0808192b0808,
-    0x192b08082b081908, 0x192b08082b190808, 0x192b081908080808, 0x192b08190808082b,
-    0x192b081908081919, 0x192b081908082b08, 0x192b081908190819, 0x192b081908191908,
-    0x192b0819082b0808, 0x192b081919080819, 0x192b081919081908, 0x192b081919190808,
-    0x192b08192b080808, 0x192b08192b192b19, 0x192b082b08081908, 0x192b082b08190808,
-    0x192b082b19080808, 0x192b082b1919192b, 0x192b082b2b2b0819, 0x192b190808080808,
-    0x192b190808081919, 0x192b190808082b08, 0x192b190808190819, 0x192b190808191908,
-    0x192b1908082b0808, 0x192b190819080819, 0x192b190819081908, 0x192b190819190808,
-    0x192b19082b080808, 0x192b191908080819, 0x192b191908081908, 0x192b191908190808,
-    0x192b191919080808, 0x192b191919082b2b, 0x192b1919192b2b08, 0x192b19192b19082b,
-    0x192b192b08080808, 0x192b192b2b191908, 0x192b2b0808080819, 0x192b2b0808081908,
-    0x192b2b0808190808, 0x192b2b08192b1919, 0x192b2b082b192b08, 0x192b2b1908080808,
-    0x192b2b19082b2b2b, 0x192b2b2b1908082b, 0x192b2b2b2b2b0819, 0x2b08080808080808,
-    0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, 0x2b08080808190819,
-    0x2b08080808191908, 0x2b08080808192b19, 0x2b080808082b0808, 0x2b080808082b1919,
-    0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808081919082b,
-    0x2b08080819191919, 0x2b08080819192b08, 0x2b080808192b0819, 0x2b0808082b080808,
-    0x2b0808082b081919, 0x2b0808082b190819, 0x2b0808082b191908, 0x2b08081908080819,
-    0x2b08081908081908, 0x2b08081908082b19, 0x2b08081908190808, 0x2b0808190819082b,
-    0x2b08081908191919, 0x2b08081908192b08, 0x2b080819082b0819, 0x2b080819082b1908,
-    0x2b08081919080808, 0x2b0808191908082b, 0x2b08081919081919, 0x2b08081919082b08,
-    0x2b08081919190819, 0x2b08081919191908, 0x2b0808192b080819, 0x2b0808192b081908,
-    0x2b0808192b190808, 0x2b0808192b2b2b19, 0x2b08082b08080808, 0x2b08082b08081919,
-    0x2b08082b08082b2b, 0x2b08082b08190819, 0x2b08082b08191908, 0x2b08082b19080819,
-    0x2b08082b19081908, 0x2b08082b19190808, 0x2b08190808080819, 0x2b08190808081908,
-    0x2b0819080808192b, 0x2b08190808082b19, 0x2b08190808190808, 0x2b0819080819082b,
-    0x2b08190808191919, 0x2b08190808192b08, 0x2b081908082b0819, 0x2b08190819080808,
-    0x2b0819081908082b, 0x2b08190819081919, 0x2b08190819082b08, 0x2b08190819190819,
-    0x2b08190819191908, 0x2b081908192b0808, 0x2b0819082b080819, 0x2b0819082b081908,
-    0x2b0819082b190808, 0x2b08191908080808, 0x2b0819190808082b, 0x2b08191908081919,
-    0x2b08191908082b08, 0x2b08191908190819, 0x2b08191908191908, 0x2b081919082b0808,
-    0x2b08191919080819, 0x2b08191919081908, 0x2b08191919190808, 0x2b0819192b080808,
-    0x2b0819192b082b2b, 0x2b08192b08080819, 0x2b08192b08081908, 0x2b08192b08190808,
-    0x2b08192b082b2b19, 0x2b08192b19080808, 0x2b082b0808080808, 0x2b082b0808081919,
-    0x2b082b0808190819, 0x2b082b0808191908, 0x2b082b0819080819, 0x2b082b0819081908,
-    0x2b082b0819190808, 0x2b082b082b2b082b, 0x2b082b1908080819, 0x2b082b1908081908,
-    0x2b082b1919080808, 0x2b082b19192b1919, 0x2b082b2b082b082b, 0x2b082b2b19192b08,
-    0x2b082b2b19192b2b, 0x2b082b2b2b08082b, 0x2b082b2b2b2b082b, 0x2b19080808080819,
-    0x2b19080808081908, 0x2b19080808082b19, 0x2b19080808190808, 0x2b1908080819082b,
-    0x2b19080808191919, 0x2b19080808192b08, 0x2b190808082b1908, 0x2b19080819080808,
-    0x2b1908081908082b, 0x2b19080819081919, 0x2b19080819082b08, 0x2b19080819190819,
-    0x2b19080819191908, 0x2b190808192b0808, 0x2b1908082b080819, 0x2b1908082b081908,
-    0x2b1908082b190808, 0x2b19081908080808, 0x2b19081908081919, 0x2b19081908190819,
-    0x2b19081908191908, 0x2b19081919080819, 0x2b19081919081908, 0x2b19081919190808,
-    0x2b19081919192b2b, 0x2b19082b08080819, 0x2b19082b08081908, 0x2b19082b08190808,
-    0x2b19082b19080808, 0x2b19082b2b2b192b, 0x2b19190808080808, 0x2b1919080808082b,
-    0x2b19190808081919, 0x2b19190808082b08, 0x2b19190808190819, 0x2b19190808191908,
-    0x2b191908082b0808, 0x2b19190819080819, 0x2b19190819081908, 0x2b19190819190808,
-    0x2b1919082b080808, 0x2b1919082b19192b, 0x2b19191908080819, 0x2b19191908081908,
-    0x2b19191908190808, 0x2b19191919080808, 0x2b1919192b192b08, 0x2b1919192b2b0819,
-    0x2b19192b08080808, 0x2b19192b1908192b, 0x2b19192b192b1908, 0x2b192b0808080819,
-    0x2b192b0808081908, 0x2b192b0808190808, 0x2b192b08082b192b, 0x2b192b0819080808,
-    0x2b192b082b2b2b19, 0x2b192b1908080808, 0x2b192b1919082b19, 0x2b192b191919082b,
-    0x2b192b2b2b190808, 0x2b2b080808080808, 0x2b2b080808081919, 0x2b2b080808082b2b,
-    0x2b2b080808191908, 0x2b2b0808082b082b, 0x2b2b0808082b2b2b, 0x2b2b080819080819,
-    0x2b2b080819081908, 0x2b2b080819190808, 0x2b2b08082b2b082b, 0x2b2b08082b2b2b2b,
-    0x2b2b081919080808, 0x2b2b0819192b1919, 0x2b2b082b0808082b, 0x2b2b082b08082b2b,
-    0x2b2b082b082b082b, 0x2b2b082b082b2b08, 0x2b2b082b082b2b2b, 0x2b2b082b2b08082b,
-    0x2b2b082b2b082b08, 0x2b2b082b2b082b2b, 0x2b2b082b2b2b2b08, 0x2b2b190808080819,
-    0x2b2b190808081908, 0x2b2b190808190808, 0x2b2b190819080808, 0x2b2b19082b082b19,
-    0x2b2b19082b2b1908, 0x2b2b191908080808, 0x2b2b191908192b19, 0x2b2b192b19190819,
-    0x2b2b2b0808082b2b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b082b, 0x2b2b2b1919191908,
-    0x2b2b2b192b08192b, 0x2b2b2b2b08082b08, 0x2b2b2b2b08082b2b, 0x2b2b2b2b082b0808,
-    0x2b2b2b2b082b082b, 0x2b2b2b2b082b2b08, 0x2b2b2b2b2b082b08, 0x2b2b2b2b2b2b2b2b,
-};
-
-constexpr constant static uint32_t iq3xxs_grid[256] = {
-    0x04040404, 0x04040414, 0x04040424, 0x04040c0c, 0x04040c1c, 0x04040c3e, 0x04041404, 0x04041414,
-    0x04041c0c, 0x04042414, 0x04043e1c, 0x04043e2c, 0x040c040c, 0x040c041c, 0x040c0c04, 0x040c0c14,
-    0x040c140c, 0x040c142c, 0x040c1c04, 0x040c1c14, 0x040c240c, 0x040c2c24, 0x040c3e04, 0x04140404,
-    0x04140414, 0x04140424, 0x04140c0c, 0x04141404, 0x04141414, 0x04141c0c, 0x04141c1c, 0x04141c3e,
-    0x04142c0c, 0x04142c3e, 0x04143e2c, 0x041c040c, 0x041c043e, 0x041c0c04, 0x041c0c14, 0x041c142c,
-    0x041c3e04, 0x04240c1c, 0x04241c3e, 0x04242424, 0x04242c3e, 0x04243e1c, 0x04243e2c, 0x042c040c,
-    0x042c043e, 0x042c1c14, 0x042c2c14, 0x04341c2c, 0x04343424, 0x043e0c04, 0x043e0c24, 0x043e0c34,
-    0x043e241c, 0x043e340c, 0x0c04040c, 0x0c04041c, 0x0c040c04, 0x0c040c14, 0x0c04140c, 0x0c04141c,
-    0x0c041c04, 0x0c041c14, 0x0c041c24, 0x0c04243e, 0x0c042c04, 0x0c0c0404, 0x0c0c0414, 0x0c0c0c0c,
-    0x0c0c1404, 0x0c0c1414, 0x0c14040c, 0x0c14041c, 0x0c140c04, 0x0c140c14, 0x0c14140c, 0x0c141c04,
-    0x0c143e14, 0x0c1c0404, 0x0c1c0414, 0x0c1c1404, 0x0c1c1c0c, 0x0c1c2434, 0x0c1c3434, 0x0c24040c,
-    0x0c24042c, 0x0c242c04, 0x0c2c1404, 0x0c2c1424, 0x0c2c2434, 0x0c2c3e0c, 0x0c34042c, 0x0c3e1414,
-    0x0c3e2404, 0x14040404, 0x14040414, 0x14040c0c, 0x14040c1c, 0x14041404, 0x14041414, 0x14041434,
-    0x14041c0c, 0x14042414, 0x140c040c, 0x140c041c, 0x140c042c, 0x140c0c04, 0x140c0c14, 0x140c140c,
-    0x140c1c04, 0x140c341c, 0x140c343e, 0x140c3e04, 0x14140404, 0x14140414, 0x14140c0c, 0x14140c3e,
-    0x14141404, 0x14141414, 0x14141c3e, 0x14142404, 0x14142c2c, 0x141c040c, 0x141c0c04, 0x141c0c24,
-    0x141c3e04, 0x141c3e24, 0x14241c2c, 0x14242c1c, 0x142c041c, 0x142c143e, 0x142c240c, 0x142c3e24,
-    0x143e040c, 0x143e041c, 0x143e0c34, 0x143e242c, 0x1c04040c, 0x1c040c04, 0x1c040c14, 0x1c04140c,
-    0x1c04141c, 0x1c042c04, 0x1c04342c, 0x1c043e14, 0x1c0c0404, 0x1c0c0414, 0x1c0c1404, 0x1c0c1c0c,
-    0x1c0c2424, 0x1c0c2434, 0x1c14040c, 0x1c14041c, 0x1c140c04, 0x1c14142c, 0x1c142c14, 0x1c143e14,
-    0x1c1c0c0c, 0x1c1c1c1c, 0x1c241c04, 0x1c24243e, 0x1c243e14, 0x1c2c0404, 0x1c2c0434, 0x1c2c1414,
-    0x1c2c2c2c, 0x1c340c24, 0x1c341c34, 0x1c34341c, 0x1c3e1c1c, 0x1c3e3404, 0x24040424, 0x24040c3e,
-    0x24041c2c, 0x24041c3e, 0x24042c1c, 0x24042c3e, 0x240c3e24, 0x24141404, 0x24141c3e, 0x24142404,
-    0x24143404, 0x24143434, 0x241c043e, 0x241c242c, 0x24240424, 0x24242c0c, 0x24243424, 0x242c142c,
-    0x242c241c, 0x242c3e04, 0x243e042c, 0x243e0c04, 0x243e0c14, 0x243e1c04, 0x2c040c14, 0x2c04240c,
-    0x2c043e04, 0x2c0c0404, 0x2c0c0434, 0x2c0c1434, 0x2c0c2c2c, 0x2c140c24, 0x2c141c14, 0x2c143e14,
-    0x2c1c0414, 0x2c1c2c1c, 0x2c240c04, 0x2c24141c, 0x2c24143e, 0x2c243e14, 0x2c2c0414, 0x2c2c1c0c,
-    0x2c342c04, 0x2c3e1424, 0x2c3e2414, 0x34041424, 0x34042424, 0x34042434, 0x34043424, 0x340c140c,
-    0x340c340c, 0x34140c3e, 0x34143424, 0x341c1c04, 0x341c1c34, 0x34242424, 0x342c042c, 0x342c2c14,
-    0x34341c1c, 0x343e041c, 0x343e140c, 0x3e04041c, 0x3e04042c, 0x3e04043e, 0x3e040c04, 0x3e041c14,
-    0x3e042c14, 0x3e0c1434, 0x3e0c2404, 0x3e140c14, 0x3e14242c, 0x3e142c14, 0x3e1c0404, 0x3e1c0c2c,
-    0x3e1c1c1c, 0x3e1c3404, 0x3e24140c, 0x3e24240c, 0x3e2c0404, 0x3e2c0414, 0x3e2c1424, 0x3e341c04,
-};
-
-constexpr constant static uint32_t iq3s_grid[512] = {
-    0x01010101, 0x01010103, 0x01010105, 0x0101010b, 0x0101010f, 0x01010301, 0x01010303, 0x01010305,
-    0x01010309, 0x0101030d, 0x01010501, 0x01010503, 0x0101050b, 0x01010707, 0x01010901, 0x01010905,
-    0x0101090b, 0x0101090f, 0x01010b03, 0x01010b07, 0x01010d01, 0x01010d05, 0x01010f03, 0x01010f09,
-    0x01010f0f, 0x01030101, 0x01030103, 0x01030105, 0x01030109, 0x01030301, 0x01030303, 0x0103030b,
-    0x01030501, 0x01030507, 0x0103050f, 0x01030703, 0x0103070b, 0x01030909, 0x01030d03, 0x01030d0b,
-    0x01030f05, 0x01050101, 0x01050103, 0x0105010b, 0x0105010f, 0x01050301, 0x01050307, 0x0105030d,
-    0x01050503, 0x0105050b, 0x01050701, 0x01050709, 0x01050905, 0x0105090b, 0x0105090f, 0x01050b03,
-    0x01050b07, 0x01050f01, 0x01050f07, 0x01070107, 0x01070303, 0x0107030b, 0x01070501, 0x01070505,
-    0x01070703, 0x01070707, 0x0107070d, 0x01070909, 0x01070b01, 0x01070b05, 0x01070d0f, 0x01070f03,
-    0x01070f0b, 0x01090101, 0x01090307, 0x0109030f, 0x01090503, 0x01090509, 0x01090705, 0x01090901,
-    0x01090907, 0x01090b03, 0x01090f01, 0x010b0105, 0x010b0109, 0x010b0501, 0x010b0505, 0x010b050d,
-    0x010b0707, 0x010b0903, 0x010b090b, 0x010b090f, 0x010b0d0d, 0x010b0f07, 0x010d010d, 0x010d0303,
-    0x010d0307, 0x010d0703, 0x010d0b05, 0x010d0f03, 0x010f0101, 0x010f0105, 0x010f0109, 0x010f0501,
-    0x010f0505, 0x010f050d, 0x010f0707, 0x010f0b01, 0x010f0b09, 0x03010101, 0x03010103, 0x03010105,
-    0x03010109, 0x03010301, 0x03010303, 0x03010307, 0x0301030b, 0x0301030f, 0x03010501, 0x03010505,
-    0x03010703, 0x03010709, 0x0301070d, 0x03010b09, 0x03010b0d, 0x03010d03, 0x03010f05, 0x03030101,
-    0x03030103, 0x03030107, 0x0303010d, 0x03030301, 0x03030309, 0x03030503, 0x03030701, 0x03030707,
-    0x03030903, 0x03030b01, 0x03030b05, 0x03030f01, 0x03030f0d, 0x03050101, 0x03050305, 0x0305030b,
-    0x0305030f, 0x03050501, 0x03050509, 0x03050705, 0x03050901, 0x03050907, 0x03050b0b, 0x03050d01,
-    0x03050f05, 0x03070103, 0x03070109, 0x0307010f, 0x03070301, 0x03070307, 0x03070503, 0x0307050f,
-    0x03070701, 0x03070709, 0x03070903, 0x03070d05, 0x03070f01, 0x03090107, 0x0309010b, 0x03090305,
-    0x03090309, 0x03090703, 0x03090707, 0x03090905, 0x0309090d, 0x03090b01, 0x03090b09, 0x030b0103,
-    0x030b0301, 0x030b0307, 0x030b0503, 0x030b0701, 0x030b0705, 0x030b0b03, 0x030d0501, 0x030d0509,
-    0x030d050f, 0x030d0909, 0x030d090d, 0x030f0103, 0x030f0107, 0x030f0301, 0x030f0305, 0x030f0503,
-    0x030f070b, 0x030f0903, 0x030f0d05, 0x030f0f01, 0x05010101, 0x05010103, 0x05010107, 0x0501010b,
-    0x0501010f, 0x05010301, 0x05010305, 0x05010309, 0x0501030d, 0x05010503, 0x05010507, 0x0501050f,
-    0x05010701, 0x05010705, 0x05010903, 0x05010907, 0x0501090b, 0x05010b01, 0x05010b05, 0x05010d0f,
-    0x05010f01, 0x05010f07, 0x05010f0b, 0x05030101, 0x05030105, 0x05030301, 0x05030307, 0x0503030f,
-    0x05030505, 0x0503050b, 0x05030703, 0x05030709, 0x05030905, 0x05030b03, 0x05050103, 0x05050109,
-    0x0505010f, 0x05050503, 0x05050507, 0x05050701, 0x0505070f, 0x05050903, 0x05050b07, 0x05050b0f,
-    0x05050f03, 0x05050f09, 0x05070101, 0x05070105, 0x0507010b, 0x05070303, 0x05070505, 0x05070509,
-    0x05070703, 0x05070707, 0x05070905, 0x05070b01, 0x05070d0d, 0x05090103, 0x0509010f, 0x05090501,
-    0x05090507, 0x05090705, 0x0509070b, 0x05090903, 0x05090f05, 0x05090f0b, 0x050b0109, 0x050b0303,
-    0x050b0505, 0x050b070f, 0x050b0901, 0x050b0b07, 0x050b0f01, 0x050d0101, 0x050d0105, 0x050d010f,
-    0x050d0503, 0x050d0b0b, 0x050d0d03, 0x050f010b, 0x050f0303, 0x050f050d, 0x050f0701, 0x050f0907,
-    0x050f0b01, 0x07010105, 0x07010303, 0x07010307, 0x0701030b, 0x0701030f, 0x07010505, 0x07010703,
-    0x07010707, 0x0701070b, 0x07010905, 0x07010909, 0x0701090f, 0x07010b03, 0x07010d07, 0x07010f03,
-    0x07030103, 0x07030107, 0x0703010b, 0x07030309, 0x07030503, 0x07030507, 0x07030901, 0x07030d01,
-    0x07030f05, 0x07030f0d, 0x07050101, 0x07050305, 0x07050501, 0x07050705, 0x07050709, 0x07050b01,
-    0x07070103, 0x07070301, 0x07070309, 0x07070503, 0x07070507, 0x0707050f, 0x07070701, 0x07070903,
-    0x07070907, 0x0707090f, 0x07070b0b, 0x07070f07, 0x07090107, 0x07090303, 0x0709030d, 0x07090505,
-    0x07090703, 0x07090b05, 0x07090d01, 0x07090d09, 0x070b0103, 0x070b0301, 0x070b0305, 0x070b050b,
-    0x070b0705, 0x070b0909, 0x070b0b0d, 0x070b0f07, 0x070d030d, 0x070d0903, 0x070f0103, 0x070f0107,
-    0x070f0501, 0x070f0505, 0x070f070b, 0x09010101, 0x09010109, 0x09010305, 0x09010501, 0x09010509,
-    0x0901050f, 0x09010705, 0x09010903, 0x09010b01, 0x09010f01, 0x09030105, 0x0903010f, 0x09030303,
-    0x09030307, 0x09030505, 0x09030701, 0x0903070b, 0x09030907, 0x09030b03, 0x09030b0b, 0x09050103,
-    0x09050107, 0x09050301, 0x0905030b, 0x09050503, 0x09050707, 0x09050901, 0x09050b0f, 0x09050d05,
-    0x09050f01, 0x09070109, 0x09070303, 0x09070307, 0x09070501, 0x09070505, 0x09070703, 0x0907070b,
-    0x09090101, 0x09090105, 0x09090509, 0x0909070f, 0x09090901, 0x09090f03, 0x090b010b, 0x090b010f,
-    0x090b0503, 0x090b0d05, 0x090d0307, 0x090d0709, 0x090d0d01, 0x090f0301, 0x090f030b, 0x090f0701,
-    0x090f0907, 0x090f0b03, 0x0b010105, 0x0b010301, 0x0b010309, 0x0b010505, 0x0b010901, 0x0b010909,
-    0x0b01090f, 0x0b010b05, 0x0b010d0d, 0x0b010f09, 0x0b030103, 0x0b030107, 0x0b03010b, 0x0b030305,
-    0x0b030503, 0x0b030705, 0x0b030f05, 0x0b050101, 0x0b050303, 0x0b050507, 0x0b050701, 0x0b05070d,
-    0x0b050b07, 0x0b070105, 0x0b07010f, 0x0b070301, 0x0b07050f, 0x0b070909, 0x0b070b03, 0x0b070d0b,
-    0x0b070f07, 0x0b090103, 0x0b090109, 0x0b090501, 0x0b090705, 0x0b09090d, 0x0b0b0305, 0x0b0b050d,
-    0x0b0b0b03, 0x0b0b0b07, 0x0b0d0905, 0x0b0f0105, 0x0b0f0109, 0x0b0f0505, 0x0d010303, 0x0d010307,
-    0x0d01030b, 0x0d010703, 0x0d010707, 0x0d010d01, 0x0d030101, 0x0d030501, 0x0d03050f, 0x0d030d09,
-    0x0d050305, 0x0d050709, 0x0d050905, 0x0d050b0b, 0x0d050d05, 0x0d050f01, 0x0d070101, 0x0d070309,
-    0x0d070503, 0x0d070901, 0x0d09050b, 0x0d090907, 0x0d090d05, 0x0d0b0101, 0x0d0b0107, 0x0d0b0709,
-    0x0d0b0d01, 0x0d0d010b, 0x0d0d0901, 0x0d0f0303, 0x0d0f0307, 0x0f010101, 0x0f010109, 0x0f01010f,
-    0x0f010501, 0x0f010505, 0x0f01070d, 0x0f010901, 0x0f010b09, 0x0f010d05, 0x0f030105, 0x0f030303,
-    0x0f030509, 0x0f030907, 0x0f03090b, 0x0f050103, 0x0f050109, 0x0f050301, 0x0f05030d, 0x0f050503,
-    0x0f050701, 0x0f050b03, 0x0f070105, 0x0f070705, 0x0f07070b, 0x0f070b07, 0x0f090103, 0x0f09010b,
-    0x0f090307, 0x0f090501, 0x0f090b01, 0x0f0b0505, 0x0f0b0905, 0x0f0d0105, 0x0f0d0703, 0x0f0f0101,
-};
-
-#define NGRID_IQ1S 512
-constexpr constant static uint64_t iq1s_grid[NGRID_IQ1S] = {
-    0xffffffffffff0101, 0xffffffffff01ff00, 0xffffffffff010100, 0xffffffff00000000,
-    0xffffffff01ff00ff, 0xffffffff01ff0001, 0xffffffff0101ffff, 0xffffffff0101ff01,
-    0xffffff00ff000000, 0xffffff000000ff00, 0xffffff00000000ff, 0xffffff0000000100,
-    0xffffff0000010000, 0xffffff0001000000, 0xffffff01ffff00ff, 0xffffff01ff01ff00,
-    0xffffff01ff010100, 0xffffff0100000001, 0xffffff0101ffff00, 0xffffff0101ff0101,
-    0xffffff0101010100, 0xffff00ffff00ff01, 0xffff00ffff0000ff, 0xffff00ff00ff0100,
-    0xffff00ff0100ff00, 0xffff00ff010001ff, 0xffff0000ff0101ff, 0xffff000000ffff00,
-    0xffff000000000000, 0xffff00000001ff01, 0xffff000001000101, 0xffff0000010100ff,
-    0xffff0001ffff0100, 0xffff00010000ff00, 0xffff000100010101, 0xffff000101000000,
-    0xffff01ffffff0000, 0xffff01ffff01ffff, 0xffff01ffff010100, 0xffff01ff00000000,
-    0xffff01ff01ffffff, 0xffff01ff01ff0001, 0xffff01ff0101ffff, 0xffff01ff01010001,
-    0xffff0100ffffff01, 0xffff01000000ffff, 0xffff010000000100, 0xffff010001ff01ff,
-    0xffff010001000000, 0xffff0101ff000000, 0xffff0101000101ff, 0xffff010101ffff01,
-    0xffff01010101ff00, 0xff00ffffff000000, 0xff00ffff00ffff00, 0xff00ffff00000001,
-    0xff00ffff000001ff, 0xff00ffff01010000, 0xff00ff00ffff0000, 0xff00ff00ff00ff00,
-    0xff00ff00ff0000ff, 0xff00ff00ff000100, 0xff00ff00ff010001, 0xff00ff0000ff0001,
-    0xff00ff000000ffff, 0xff00ff0000000000, 0xff00ff000001ff00, 0xff00ff0000010100,
-    0xff00ff0001ff0000, 0xff00ff000100ff00, 0xff00ff0001000100, 0xff00ff01ff000000,
-    0xff00ff0100ff0000, 0xff00ff01000001ff, 0xff00ff0101010001, 0xff0000ff00000000,
-    0xff0000ff0001ff00, 0xff0000ff00010100, 0xff000000ffff0101, 0xff000000ff000000,
-    0xff000000ff01ff00, 0xff00000000ff0000, 0xff0000000000ff00, 0xff000000000000ff,
-    0xff00000000000000, 0xff00000000000001, 0xff00000000000100, 0xff0000000001ffff,
-    0xff00000000010000, 0xff00000001000000, 0xff00000001010100, 0xff000001ff00ff01,
-    0xff000001ff0100ff, 0xff00000100000000, 0xff0000010001ff00, 0xff00000101ff0100,
-    0xff0000010100ff00, 0xff0001ff00ff00ff, 0xff0001ff00000101, 0xff0001ff000100ff,
-    0xff0001ff01000000, 0xff000100ff0001ff, 0xff0001000000ff01, 0xff00010000000000,
-    0xff00010000010001, 0xff00010000010100, 0xff00010001ffff00, 0xff00010001ff0101,
-    0xff00010001010000, 0xff000101ffffffff, 0xff000101ff000101, 0xff00010101ff00ff,
-    0xff00010101000001, 0xff000101010100ff, 0xff01ffffff000101, 0xff01ffffff01ffff,
-    0xff01ffffff01ff01, 0xff01ffffff0101ff, 0xff01ffff00000000, 0xff01ffff01ff0001,
-    0xff01ffff0101ff01, 0xff01ff00ff000000, 0xff01ff0000ff0100, 0xff01ff000000ff01,
-    0xff01ff0000010000, 0xff01ff00010000ff, 0xff01ff01ff01ff00, 0xff01ff0100000101,
-    0xff0100ffffff0000, 0xff0100ffff010000, 0xff0100ff01ff00ff, 0xff0100ff01000100,
-    0xff0100ff010100ff, 0xff010000ffffff01, 0xff01000000000000, 0xff0100000101ff00,
-    0xff010001ffff00ff, 0xff010001ff000100, 0xff01000100ffff00, 0xff01000100010001,
-    0xff01000101ff0001, 0xff010001010001ff, 0xff0101ffffffffff, 0xff0101ffff01ffff,
-    0xff0101ffff010101, 0xff0101ff0000ff00, 0xff0101ff01010001, 0xff010100ff000000,
-    0xff010100ff01ff01, 0xff01010000ff0001, 0xff01010000000100, 0xff01010001000000,
-    0xff0101010100ffff, 0x00ffffff0000ff01, 0x00ffffff000000ff, 0x00ffffff00000100,
-    0x00ffffff00010000, 0x00ffff00ffff0001, 0x00ffff00ff0000ff, 0x00ffff00ff000100,
-    0x00ffff0000000000, 0x00ffff0001000100, 0x00ffff0001010001, 0x00ffff01ff00ff01,
-    0x00ffff0100ff0100, 0x00ffff010000ff00, 0x00ffff01000100ff, 0x00ffff0101ff00ff,
-    0x00ffff010101ff00, 0x00ff00ffffffffff, 0x00ff00ffffff01ff, 0x00ff00ffff000101,
-    0x00ff00ff00000000, 0x00ff00ff000101ff, 0x00ff00ff01010101, 0x00ff0000ff000000,
-    0x00ff0000ff01ffff, 0x00ff000000ff0000, 0x00ff00000000ff00, 0x00ff0000000000ff,
-    0x00ff000000000000, 0x00ff000000000001, 0x00ff000000000100, 0x00ff000000010000,
-    0x00ff000001ffff01, 0x00ff000001000000, 0x00ff0001ff000101, 0x00ff000100ffffff,
-    0x00ff000100000000, 0x00ff0001010001ff, 0x00ff01ffff000000, 0x00ff01ff0001ff00,
-    0x00ff01ff01ff0100, 0x00ff0100ff01ff01, 0x00ff010000ff00ff, 0x00ff010000ff0101,
-    0x00ff010000000000, 0x00ff010000010101, 0x00ff01000100ff00, 0x00ff010001010000,
-    0x00ff0101ffffff00, 0x00ff01010000ff01, 0x00ff010100000100, 0x00ff010101ff0000,
-    0x0000ffffffff0100, 0x0000ffffff00ff00, 0x0000ffffff0000ff, 0x0000ffffff010000,
-    0x0000ffff00000000, 0x0000ffff00010101, 0x0000ffff01ffff01, 0x0000ffff01000100,
-    0x0000ff00ff000000, 0x0000ff00ff01ff00, 0x0000ff00ff0101ff, 0x0000ff0000ff0000,
-    0x0000ff000000ff00, 0x0000ff00000000ff, 0x0000ff0000000000, 0x0000ff0000000001,
-    0x0000ff0000000100, 0x0000ff0000010000, 0x0000ff0001ffffff, 0x0000ff0001ff01ff,
-    0x0000ff0001000000, 0x0000ff000101ffff, 0x0000ff01ffff0101, 0x0000ff01ff010000,
-    0x0000ff0100000000, 0x0000ff0101000101, 0x000000ffffff0001, 0x000000ffff000000,
-    0x000000ff00ff0000, 0x000000ff0000ff00, 0x000000ff000000ff, 0x000000ff00000000,
-    0x000000ff00000001, 0x000000ff00000100, 0x000000ff00010000, 0x000000ff01000000,
-    0x000000ff0101ff00, 0x00000000ffff0000, 0x00000000ff00ff00, 0x00000000ff0000ff,
-    0x00000000ff000000, 0x00000000ff000001, 0x00000000ff000100, 0x00000000ff010000,
-    0x0000000000ffff00, 0x0000000000ff00ff, 0x0000000000ff0000, 0x0000000000ff0001,
-    0x0000000000ff0100, 0x000000000000ffff, 0x000000000000ff00, 0x000000000000ff01,
-    0x00000000000000ff, 0x0000000000000001, 0x00000000000001ff, 0x0000000000000100,
-    0x0000000000000101, 0x000000000001ff00, 0x00000000000100ff, 0x0000000000010000,
-    0x0000000000010001, 0x0000000000010100, 0x0000000001ff0000, 0x000000000100ff00,
-    0x00000000010000ff, 0x0000000001000000, 0x0000000001000001, 0x0000000001000100,
-    0x0000000001010000, 0x00000001ffff01ff, 0x00000001ff000000, 0x0000000100ff0000,
-    0x000000010000ff00, 0x00000001000000ff, 0x0000000100000000, 0x0000000100000001,
-    0x0000000100000100, 0x0000000100010000, 0x0000000101000000, 0x000001ffff00ff00,
-    0x000001ffff010001, 0x000001ffff0101ff, 0x000001ff00ffff01, 0x000001ff0000ffff,
-    0x000001ff00000000, 0x000001ff010000ff, 0x000001ff01010100, 0x00000100ffff0100,
-    0x00000100ff000000, 0x0000010000ff0000, 0x000001000000ff00, 0x00000100000000ff,
-    0x0000010000000000, 0x0000010000000001, 0x0000010000000100, 0x0000010000010000,
-    0x0000010001000000, 0x000001000101ff01, 0x00000101ffff0001, 0x00000101ff01ffff,
-    0x0000010100000000, 0x0000010101010100, 0x0001ffffff000000, 0x0001ffff00ffffff,
-    0x0001ffff00000100, 0x0001ffff0001ff00, 0x0001ffff01000000, 0x0001ff00ffffff00,
-    0x0001ff00ffff01ff, 0x0001ff00ff010000, 0x0001ff0000000000, 0x0001ff0000010001,
-    0x0001ff0001ff0000, 0x0001ff0001010100, 0x0001ff01ff0000ff, 0x0001ff01ff000001,
-    0x0001ff0100ffffff, 0x0001ff010001ffff, 0x0001ff01000101ff, 0x0001ff010100ff01,
-    0x000100ffff00ffff, 0x000100ffff00ff01, 0x000100ffff000100, 0x000100ff00000000,
-    0x000100ff000101ff, 0x000100ff01ff0101, 0x000100ff0100ffff, 0x000100ff01010101,
-    0x00010000ff000000, 0x00010000ff010100, 0x0001000000ff0000, 0x000100000000ff00,
-    0x00010000000000ff, 0x0001000000000000, 0x0001000000000001, 0x0001000000000100,
-    0x0001000000010000, 0x0001000001ffff01, 0x0001000001000000, 0x0001000100ff0101,
-    0x0001000100000000, 0x00010001010100ff, 0x000101ffffff01ff, 0x000101ffffff0101,
-    0x000101ff00010000, 0x000101ff01ff0000, 0x000101ff0100ff01, 0x00010100ffff0000,
-    0x0001010000000000, 0x000101000001ffff, 0x0001010000010101, 0x00010100010001ff,
-    0x00010101ff00ff00, 0x00010101ff010001, 0x0001010100ffffff, 0x0001010100ff01ff,
-    0x00010101000101ff, 0x0001010101ff0000, 0x000101010100ff01, 0x0001010101000101,
-    0x01ffffffffff0101, 0x01ffffffff01ffff, 0x01ffffffff01ff01, 0x01ffffffff0101ff,
-    0x01ffffffff010101, 0x01ffffff00000000, 0x01ffffff01ff01ff, 0x01ffffff01000101,
-    0x01ffffff0101ff01, 0x01ffffff010100ff, 0x01ffff000000ff00, 0x01ffff0000000001,
-    0x01ffff00000001ff, 0x01ffff0000010000, 0x01ffff0001ff0000, 0x01ffff01ffffffff,
-    0x01ffff01ffff01ff, 0x01ffff01ff000000, 0x01ffff01ff01ffff, 0x01ffff01ff0101ff,
-    0x01ffff010100ffff, 0x01ff00ffffff0000, 0x01ff00ffff010000, 0x01ff00ff00ffff01,
-    0x01ff0000ff0000ff, 0x01ff000000000000, 0x01ff00000001ff01, 0x01ff000001ffffff,
-    0x01ff000001010100, 0x01ff0001ffffff01, 0x01ff0001ff010001, 0x01ff000101ff0100,
-    0x01ff000101000001, 0x01ff0001010100ff, 0x01ff01ffff00ffff, 0x01ff01ff00010001,
-    0x01ff01ff01000000, 0x01ff01ff010101ff, 0x01ff0100ff000001, 0x01ff010000ffff00,
-    0x01ff010000000100, 0x01ff010001ff01ff, 0x01ff01000101ffff, 0x01ff0101ffff00ff,
-    0x01ff0101ffff0101, 0x01ff0101ff0101ff, 0x01ff010100010000, 0x0100ffff00ff00ff,
-    0x0100ffff00ff0001, 0x0100ffff00000100, 0x0100ffff0100ff00, 0x0100ff00ffff0000,
-    0x0100ff00ff00ffff, 0x0100ff00ff00ff01, 0x0100ff00ff000100, 0x0100ff00ff010000,
-    0x0100ff0000000000, 0x0100ff00000100ff, 0x0100ff0001ff0101, 0x0100ff0001010101,
-    0x0100ff0100ff00ff, 0x0100ff0100ff0001, 0x0100ff0100000100, 0x0100ff0100010001,
-    0x0100ff0101000000, 0x010000ffff00ff00, 0x010000ff0000ffff, 0x010000ff00000000,
-    0x010000ff010001ff, 0x010000ff01010001, 0x01000000ffffff00, 0x01000000ffff0101,
-    0x01000000ff000000, 0x01000000ff0100ff, 0x01000000ff010101, 0x0100000000ff0000,
-    0x010000000000ff00, 0x01000000000000ff, 0x0100000000000000, 0x0100000000000001,
-    0x0100000000000100, 0x0100000000010000, 0x0100000001000000, 0x0100000100000000,
-    0x01000001000101ff, 0x0100000101ffff01, 0x010001ffff000101, 0x010001ff00ff0100,
-    0x010001ff0000ff00, 0x010001ff000100ff, 0x010001ff01ffffff, 0x01000100ffff0000,
-    0x01000100ff0001ff, 0x0100010000000000, 0x010001000001ff00, 0x0100010001ff0000,
-    0x01000100010000ff, 0x0100010001000101, 0x01000101ff00ff01, 0x0100010100ff0100,
-    0x010001010000ffff, 0x0100010101010001, 0x0101ffffffff0101, 0x0101ffffff0001ff,
-    0x0101ffffff01ffff, 0x0101ffffff010101, 0x0101ffff00000000, 0x0101ffff0101ffff,
-    0x0101ffff010101ff, 0x0101ff00ff000000, 0x0101ff0000ff0100, 0x0101ff000000ff00,
-    0x0101ff0000010000, 0x0101ff00010000ff, 0x0101ff0001000001, 0x0101ff01ff010101,
-    0x0101ff0100000000, 0x0101ff010101ff00, 0x010100ffffff0000, 0x010100ffff010000,
-    0x010100ff00ff01ff, 0x010100ff000000ff, 0x010100ff00000101, 0x010100ff01ffff00,
-    0x01010000ffffff01, 0x01010000ff000100, 0x01010000ff01ff01, 0x0101000000000000,
-    0x01010000000100ff, 0x010100000101ff01, 0x01010001ffff0000, 0x01010001ff00ffff,
-    0x01010001ff010000, 0x0101000101ffffff, 0x0101000101ff01ff, 0x0101000101010101,
-    0x010101ffff01ffff, 0x010101ff00000000, 0x010101ff0001ff01, 0x010101ff0101ffff,
-    0x010101ff010101ff, 0x01010100ffffffff, 0x01010100ff000001, 0x010101000000ff00,
-    0x0101010001010000, 0x0101010100ff0001, 0x010101010001ff01, 0x010101010101ffff,
-};
-
-constexpr constant static uint8_t ksigns_iq2xs[128] = {
-      0, 129, 130,   3, 132,   5,   6, 135, 136,   9,  10, 139,  12, 141, 142,  15,
-    144,  17,  18, 147,  20, 149, 150,  23,  24, 153, 154,  27, 156,  29,  30, 159,
-    160,  33,  34, 163,  36, 165, 166,  39,  40, 169, 170,  43, 172,  45,  46, 175,
-     48, 177, 178,  51, 180,  53,  54, 183, 184,  57,  58, 187,  60, 189, 190,  63,
-    192,  65,  66, 195,  68, 197, 198,  71,  72, 201, 202,  75, 204,  77,  78, 207,
-     80, 209, 210,  83, 212,  85,  86, 215, 216,  89,  90, 219,  92, 221, 222,  95,
-     96, 225, 226,  99, 228, 101, 102, 231, 232, 105, 106, 235, 108, 237, 238, 111,
-    240, 113, 114, 243, 116, 245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255,
-};
-
-constexpr constant static uint8_t kmask_iq2xs[8] = {1, 2, 4, 8, 16, 32, 64, 128};
-
 void kernel_mul_mv_iq2_xxs_f32_impl(
        device const  void * src0,
        device const float * src1,
@@ -1,9 +1,9 @@
 #pragma once

-#include "ggml-impl.h"
-
 // GGML internal header

+#include "ggml-impl.h"
+
 #include <stdint.h>
 #include <stddef.h>

@@ -261,6 +261,7 @@ void quantize_row_q4_K_reference(const float * GGML_RESTRICT x, block_q4_K * GGM
 void quantize_row_q5_K_reference(const float * GGML_RESTRICT x, block_q5_K * GGML_RESTRICT y, int k);
 void quantize_row_q6_K_reference(const float * GGML_RESTRICT x, block_q6_K * GGML_RESTRICT y, int k);
 void quantize_row_q8_K_reference(const float * GGML_RESTRICT x, block_q8_K * GGML_RESTRICT y, int k);
+
 void quantize_row_iq3_xxs_reference(const float * GGML_RESTRICT x, block_iq3_xxs * GGML_RESTRICT y, int k);
 void quantize_row_iq4_nl_reference (const float * GGML_RESTRICT x, block_iq4_nl  * GGML_RESTRICT y, int k);
 void quantize_row_iq4_xs_reference (const float * GGML_RESTRICT x, block_iq4_xs  * GGML_RESTRICT y, int k);
@@ -280,6 +281,7 @@ void quantize_row_q4_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, in
 void quantize_row_q5_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
 void quantize_row_q6_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
 void quantize_row_q8_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
+
 void quantize_row_iq3_xxs(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
 void quantize_row_iq4_nl (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
 void quantize_row_iq4_xs (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
@@ -300,6 +302,7 @@ void dequantize_row_q4_K(const block_q4_K * GGML_RESTRICT x, float * GGML_RESTRI
 void dequantize_row_q5_K(const block_q5_K * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
 void dequantize_row_q6_K(const block_q6_K * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
 void dequantize_row_q8_K(const block_q8_K * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
+
 void dequantize_row_iq2_xxs(const block_iq2_xxs * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
 void dequantize_row_iq2_xs (const block_iq2_xs  * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
 void dequantize_row_iq2_s  (const block_iq2_s   * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
@@ -321,6 +324,7 @@ void ggml_vec_dot_q3_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const voi
 void ggml_vec_dot_q4_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
 void ggml_vec_dot_q5_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
 void ggml_vec_dot_q6_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
+
 void ggml_vec_dot_iq2_xxs_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
 void ggml_vec_dot_iq2_xs_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
 void ggml_vec_dot_iq2_s_q8_K  (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
@@ -330,26 +334,26 @@ void ggml_vec_dot_iq4_nl_q8_0 (int n, float * GGML_RESTRICT s, size_t bs, const
 void ggml_vec_dot_iq4_xs_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
 void ggml_vec_dot_iq3_s_q8_K  (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);

-//
 // Quantization utilizing an importance matrix (a.k.a. "Activation aWare Quantization")
-//
-size_t quantize_iq2_xxs(const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_iq2_xs (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_iq2_s  (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_iq3_xxs(const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_iq1_s  (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_iq4_nl (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_iq4_xs (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_iq3_s  (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q2_K   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q3_K   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q4_K   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q5_K   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q6_K   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q4_0   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q4_1   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q5_0   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q5_1   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
+size_t quantize_iq2_xxs(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_iq2_xs (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_iq2_s  (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_iq3_xxs(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_iq1_s  (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_iq4_nl (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_iq4_xs (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_iq3_s  (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+
+size_t quantize_q2_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q3_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q4_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q5_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q6_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q4_0(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q4_1(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q5_0(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q5_1(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q8_0(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);

 void iq2xs_init_impl(enum ggml_type type);
 void iq2xs_free_impl(enum ggml_type type);
@@ -3144,6 +3144,8 @@ namespace dpct

 } // COPY from DPCT head files

+#define GGML_COMMON_IMPL_SYCL
+#include "ggml-common.h"

 static int g_ggml_sycl_debug=0;
 #define GGML_SYCL_DEBUG(...) do{if(g_ggml_sycl_debug) printf(__VA_ARGS__);}while(0)
@@ -3559,31 +3561,12 @@ class sycl_gpu_mgr {
        int work_group_size = 0;
        std::string gpus_list = "";

-        /*
-        Use all GPU with same top max compute units
-        */
        sycl_gpu_mgr() {
            detect_sycl_gpu_list_with_max_cu();
            get_allow_gpus();
            create_context_with_gpus();
        }

-        /*
-        Use the assigned GPU as only one
-        */
-        sycl_gpu_mgr(int main_gpu_id) {
-            sycl::device device = dpct::dev_mgr::instance().get_device(main_gpu_id);
-            dpct::device_info prop;
-            dpct::get_device_info(prop, device);
-            gpus.push_back(main_gpu_id);
-            devices.push_back(device);
-            work_group_size = prop.get_max_work_group_size();
-            max_compute_units = prop.get_max_compute_units();
-
-            get_allow_gpus();
-            create_context_with_gpus();
-        }
-
        void create_context_with_gpus() {
            sycl::context ctx = sycl::context(devices);
            assert(gpus.size() > 0);
@@ -3599,7 +3582,7 @@ class sycl_gpu_mgr {
                gpus_list += std::to_string(gpus[i]);
                gpus_list += ",";
            }
-            if (gpus_list.length() > 1) {
+            if (gpus_list.length() > 2) {
                gpus_list.pop_back();
            }
        }
@@ -3648,8 +3631,8 @@ class sycl_gpu_mgr {
                if (gpus[i] == id)
                    return i;
            }
-            printf("miss to get device index by id=%d\n", id);
-            GGML_ASSERT(false);
+            assert(false);
+            return -1;
        }

        int get_next_index(int id) {
@@ -3658,7 +3641,8 @@ class sycl_gpu_mgr {
                if (gpus[i] == id)
                    return i;
            }
-            GGML_ASSERT(false);
+            assert(false);
+            return -1;
        }
 };

@@ -3667,7 +3651,6 @@ static int g_device_count = -1;
 static int g_all_sycl_device_count = -1;
 static int g_main_device = -1;
 static int g_main_device_id = -1;
-static bool g_ggml_backend_sycl_buffer_type_initialized = false;

 static std::array<float, GGML_SYCL_MAX_DEVICES> g_default_tensor_split = {};

@@ -4764,388 +4747,6 @@ static void dequantize_block_q6_K(const void * __restrict__ vx, dst_t * __restri
 #endif
 }

-static dpct::global_memory<const uint64_t, 1>
-    iq2xxs_grid(sycl::range<1>(256),
-                {
-                    0x0808080808080808, 0x080808080808082b, 0x0808080808081919,
-                    0x0808080808082b08, 0x0808080808082b2b, 0x0808080808190819,
-                    0x0808080808191908, 0x08080808082b0808, 0x08080808082b082b,
-                    0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819,
-                    0x0808080819081908, 0x0808080819190808, 0x0808080819192b08,
-                    0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808,
-                    0x080808082b08082b, 0x080808082b082b2b, 0x080808082b2b082b,
-                    0x0808081908080819, 0x0808081908081908, 0x0808081908190808,
-                    0x0808081908191919, 0x0808081919080808, 0x080808192b081908,
-                    0x080808192b192b08, 0x0808082b08080808, 0x0808082b0808082b,
-                    0x0808082b082b082b, 0x0808082b2b08082b, 0x0808190808080819,
-                    0x0808190808081908, 0x0808190808190808, 0x08081908082b0819,
-                    0x08081908082b1908, 0x0808190819080808, 0x080819081908082b,
-                    0x0808190819082b08, 0x08081908192b0808, 0x080819082b080819,
-                    0x080819082b081908, 0x080819082b190808, 0x080819082b2b1908,
-                    0x0808191908080808, 0x080819190808082b, 0x0808191908082b08,
-                    0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19,
-                    0x080819192b080808, 0x080819192b190819, 0x0808192b08082b19,
-                    0x0808192b08190808, 0x0808192b19080808, 0x0808192b2b081908,
-                    0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919,
-                    0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08,
-                    0x08082b0819080819, 0x08082b0819081908, 0x08082b0819190808,
-                    0x08082b081919082b, 0x08082b082b082b08, 0x08082b1908081908,
-                    0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908,
-                    0x0819080808080819, 0x0819080808081908, 0x0819080808190808,
-                    0x08190808082b0819, 0x0819080819080808, 0x08190808192b0808,
-                    0x081908082b081908, 0x081908082b190808, 0x081908082b191919,
-                    0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808,
-                    0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808,
-                    0x0819082b082b1908, 0x0819082b19081919, 0x0819190808080808,
-                    0x0819190808082b08, 0x08191908082b0808, 0x08191908082b1919,
-                    0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08,
-                    0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b,
-                    0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808,
-                    0x08192b0819080808, 0x08192b082b080819, 0x08192b1908080808,
-                    0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819,
-                    0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b,
-                    0x082b080819081908, 0x082b0808192b0819, 0x082b08082b080808,
-                    0x082b08082b08082b, 0x082b0819082b2b19, 0x082b081919082b08,
-                    0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819,
-                    0x082b190808081908, 0x082b190808190808, 0x082b190819080808,
-                    0x082b19081919192b, 0x082b191908080808, 0x082b191919080819,
-                    0x082b1919192b1908, 0x082b192b2b190808, 0x082b2b0808082b08,
-                    0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908,
-                    0x1908080808080819, 0x1908080808081908, 0x1908080808190808,
-                    0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908,
-                    0x1908080819080808, 0x1908080819082b08, 0x190808081919192b,
-                    0x19080808192b0808, 0x190808082b080819, 0x190808082b081908,
-                    0x190808082b190808, 0x1908081908080808, 0x19080819082b0808,
-                    0x19080819192b0819, 0x190808192b080808, 0x190808192b081919,
-                    0x1908082b08080819, 0x1908082b08190808, 0x1908082b19082b08,
-                    0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808,
-                    0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808,
-                    0x190819082b192b19, 0x190819190819082b, 0x19081919082b1908,
-                    0x1908192b08080808, 0x19082b0808080819, 0x19082b0808081908,
-                    0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919,
-                    0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819,
-                    0x19082b192b08082b, 0x19082b2b19081919, 0x19082b2b2b190808,
-                    0x1919080808080808, 0x1919080808082b08, 0x1919080808190819,
-                    0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808,
-                    0x191908082b082b08, 0x1919081908081908, 0x191908191908082b,
-                    0x191908192b2b1908, 0x1919082b2b190819, 0x191919082b190808,
-                    0x191919082b19082b, 0x1919191908082b2b, 0x1919192b08080819,
-                    0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819,
-                    0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808,
-                    0x19192b2b08082b08, 0x192b080808081908, 0x192b080808190808,
-                    0x192b080819080808, 0x192b0808192b2b08, 0x192b081908080808,
-                    0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808,
-                    0x192b190808080808, 0x192b190808081919, 0x192b191908190808,
-                    0x192b19190819082b, 0x192b19192b081908, 0x192b2b081908082b,
-                    0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808082b2b,
-                    0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908,
-                    0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819,
-                    0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808,
-                    0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808,
-                    0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908,
-                    0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808,
-                    0x2b082b080808082b, 0x2b082b1908081908, 0x2b082b2b08190819,
-                    0x2b19080808081908, 0x2b19080808190808, 0x2b190808082b1908,
-                    0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b,
-                    0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808,
-                    0x2b191908082b082b, 0x2b19190819081908, 0x2b19191919190819,
-                    0x2b192b082b080819, 0x2b192b19082b0808, 0x2b2b08080808082b,
-                    0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19,
-                    0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808,
-                    0x2b2b2b1908081908,
-                });
-
-static dpct::global_memory<const uint64_t, 1>
-    iq2xs_grid(sycl::range<1>(512),
-               {
-                   0x0808080808080808, 0x080808080808082b, 0x0808080808081919,
-                   0x0808080808082b08, 0x0808080808082b2b, 0x0808080808190819,
-                   0x0808080808191908, 0x080808080819192b, 0x0808080808192b19,
-                   0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
-                   0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908,
-                   0x080808081908192b, 0x0808080819082b19, 0x0808080819190808,
-                   0x080808081919082b, 0x0808080819191919, 0x0808080819192b08,
-                   0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808,
-                   0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08,
-                   0x080808082b190819, 0x080808082b191908, 0x080808082b192b19,
-                   0x080808082b2b0808, 0x0808081908080819, 0x0808081908081908,
-                   0x080808190808192b, 0x0808081908082b19, 0x0808081908190808,
-                   0x080808190819082b, 0x0808081908191919, 0x0808081908192b08,
-                   0x0808081908192b2b, 0x08080819082b0819, 0x08080819082b1908,
-                   0x0808081919080808, 0x080808191908082b, 0x0808081919081919,
-                   0x0808081919082b08, 0x0808081919190819, 0x0808081919191908,
-                   0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819,
-                   0x080808192b081908, 0x080808192b190808, 0x0808082b08080808,
-                   0x0808082b0808082b, 0x0808082b08081919, 0x0808082b08082b08,
-                   0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808,
-                   0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808,
-                   0x0808082b19191919, 0x0808082b2b080808, 0x0808082b2b082b2b,
-                   0x0808190808080819, 0x0808190808081908, 0x080819080808192b,
-                   0x0808190808082b19, 0x0808190808190808, 0x080819080819082b,
-                   0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819,
-                   0x08081908082b1908, 0x0808190819080808, 0x080819081908082b,
-                   0x0808190819081919, 0x0808190819082b08, 0x0808190819190819,
-                   0x0808190819191908, 0x080819081919192b, 0x08081908192b0808,
-                   0x080819082b080819, 0x080819082b081908, 0x080819082b190808,
-                   0x0808191908080808, 0x080819190808082b, 0x0808191908081919,
-                   0x0808191908082b08, 0x0808191908190819, 0x0808191908191908,
-                   0x08081919082b0808, 0x0808191919080819, 0x0808191919081908,
-                   0x0808191919190808, 0x08081919192b0819, 0x080819192b080808,
-                   0x0808192b08080819, 0x0808192b08081908, 0x0808192b08190808,
-                   0x0808192b082b192b, 0x0808192b19080808, 0x0808192b1908082b,
-                   0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b,
-                   0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b,
-                   0x08082b0808190819, 0x08082b0808191908, 0x08082b08082b0808,
-                   0x08082b08082b1919, 0x08082b0819080819, 0x08082b0819081908,
-                   0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808,
-                   0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819,
-                   0x08082b1908081908, 0x08082b1908190808, 0x08082b1919080808,
-                   0x08082b192b080819, 0x08082b192b082b19, 0x08082b2b08080808,
-                   0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b,
-                   0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908,
-                   0x081908080808192b, 0x0819080808082b19, 0x0819080808190808,
-                   0x081908080819082b, 0x0819080808191919, 0x0819080808192b08,
-                   0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808,
-                   0x081908081908082b, 0x0819080819081919, 0x0819080819082b08,
-                   0x0819080819190819, 0x0819080819191908, 0x08190808192b0808,
-                   0x08190808192b2b2b, 0x081908082b080819, 0x081908082b081908,
-                   0x081908082b190808, 0x0819081908080808, 0x081908190808082b,
-                   0x0819081908081919, 0x0819081908082b08, 0x0819081908190819,
-                   0x0819081908191908, 0x08190819082b0808, 0x0819081919080819,
-                   0x0819081919081908, 0x0819081919190808, 0x081908192b080808,
-                   0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819,
-                   0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808,
-                   0x0819082b19080808, 0x0819082b192b0808, 0x0819190808080808,
-                   0x081919080808082b, 0x0819190808081919, 0x0819190808082b08,
-                   0x0819190808190819, 0x0819190808191908, 0x08191908082b0808,
-                   0x0819190819080819, 0x0819190819081908, 0x0819190819082b19,
-                   0x0819190819190808, 0x08191908192b1908, 0x081919082b080808,
-                   0x0819191908080819, 0x0819191908081908, 0x0819191908190808,
-                   0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908,
-                   0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908,
-                   0x08192b0808190808, 0x08192b080819082b, 0x08192b0819080808,
-                   0x08192b0819191908, 0x08192b082b08192b, 0x08192b1908080808,
-                   0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819,
-                   0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b,
-                   0x082b080808081919, 0x082b080808082b08, 0x082b080808082b2b,
-                   0x082b080808190819, 0x082b080808191908, 0x082b0808082b0808,
-                   0x082b080819080819, 0x082b080819081908, 0x082b080819190808,
-                   0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819,
-                   0x082b081908081908, 0x082b081908190808, 0x082b081919080808,
-                   0x082b081919082b08, 0x082b0819192b1919, 0x082b082b08080808,
-                   0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08,
-                   0x082b190808080819, 0x082b190808081908, 0x082b190808190808,
-                   0x082b1908082b2b19, 0x082b190819080808, 0x082b191908080808,
-                   0x082b191919080819, 0x082b19191919082b, 0x082b19192b192b19,
-                   0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b,
-                   0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b,
-                   0x082b2b08082b0808, 0x082b2b0819191919, 0x082b2b082b082b08,
-                   0x082b2b082b2b082b, 0x082b2b19192b2b08, 0x082b2b192b190808,
-                   0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b,
-                   0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819,
-                   0x1908080808081908, 0x190808080808192b, 0x1908080808082b19,
-                   0x1908080808190808, 0x190808080819082b, 0x1908080808191919,
-                   0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908,
-                   0x1908080819080808, 0x190808081908082b, 0x1908080819081919,
-                   0x1908080819082b08, 0x1908080819082b2b, 0x1908080819190819,
-                   0x1908080819191908, 0x19080808192b0808, 0x19080808192b1919,
-                   0x190808082b080819, 0x190808082b081908, 0x190808082b190808,
-                   0x1908081908080808, 0x190808190808082b, 0x1908081908081919,
-                   0x1908081908082b08, 0x1908081908190819, 0x1908081908191908,
-                   0x19080819082b0808, 0x1908081919080819, 0x1908081919081908,
-                   0x1908081919190808, 0x190808192b080808, 0x190808192b081919,
-                   0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908,
-                   0x1908082b08190808, 0x1908082b0819082b, 0x1908082b082b2b19,
-                   0x1908082b19080808, 0x1908190808080808, 0x190819080808082b,
-                   0x1908190808081919, 0x1908190808082b08, 0x1908190808190819,
-                   0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808,
-                   0x1908190819080819, 0x1908190819081908, 0x1908190819190808,
-                   0x190819082b080808, 0x190819082b191908, 0x1908191908080819,
-                   0x1908191908081908, 0x1908191908190808, 0x19081919082b1908,
-                   0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808,
-                   0x1908192b08082b2b, 0x1908192b19081908, 0x1908192b19190808,
-                   0x19082b0808080819, 0x19082b0808081908, 0x19082b0808190808,
-                   0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908,
-                   0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819,
-                   0x19082b1919081908, 0x19082b1919190808, 0x19082b19192b2b19,
-                   0x19082b2b08081908, 0x1919080808080808, 0x191908080808082b,
-                   0x1919080808081919, 0x1919080808082b08, 0x1919080808190819,
-                   0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08,
-                   0x1919080819080819, 0x1919080819081908, 0x1919080819190808,
-                   0x191908082b080808, 0x1919081908080819, 0x1919081908081908,
-                   0x1919081908190808, 0x1919081908191919, 0x1919081919080808,
-                   0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908,
-                   0x1919082b2b2b2b2b, 0x1919190808080819, 0x1919190808081908,
-                   0x1919190808190808, 0x19191908082b0819, 0x1919190819080808,
-                   0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819,
-                   0x1919191908080808, 0x1919191908082b08, 0x191919192b080808,
-                   0x191919192b082b08, 0x1919192b082b0819, 0x1919192b192b2b08,
-                   0x1919192b2b2b0819, 0x19192b0808080808, 0x19192b0808191908,
-                   0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19,
-                   0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b,
-                   0x19192b2b2b081919, 0x192b080808080819, 0x192b080808081908,
-                   0x192b080808190808, 0x192b080819080808, 0x192b080819191908,
-                   0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19,
-                   0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b,
-                   0x192b082b2b19082b, 0x192b190808080808, 0x192b19080819192b,
-                   0x192b191908190808, 0x192b191919080808, 0x192b191919081919,
-                   0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b,
-                   0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908,
-                   0x192b2b2b192b082b, 0x2b08080808080808, 0x2b0808080808082b,
-                   0x2b08080808081919, 0x2b08080808082b08, 0x2b08080808190819,
-                   0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b,
-                   0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808,
-                   0x2b0808082b080808, 0x2b0808082b08082b, 0x2b0808082b2b2b08,
-                   0x2b0808082b2b2b2b, 0x2b08081908080819, 0x2b08081908081908,
-                   0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808,
-                   0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808,
-                   0x2b08082b082b0808, 0x2b08082b2b080808, 0x2b08082b2b08082b,
-                   0x2b08082b2b2b0808, 0x2b08082b2b2b2b08, 0x2b08190808080819,
-                   0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b,
-                   0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808,
-                   0x2b0819082b082b19, 0x2b08191908080808, 0x2b08191919081908,
-                   0x2b0819192b2b1919, 0x2b08192b08192b08, 0x2b08192b192b2b2b,
-                   0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919,
-                   0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b,
-                   0x2b082b082b2b2b08, 0x2b082b190808192b, 0x2b082b2b082b082b,
-                   0x2b082b2b2b080808, 0x2b082b2b2b082b08, 0x2b082b2b2b19192b,
-                   0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908,
-                   0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b,
-                   0x2b1908082b081908, 0x2b19081908080808, 0x2b190819082b082b,
-                   0x2b190819192b1908, 0x2b19082b1919192b, 0x2b19082b2b082b19,
-                   0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908,
-                   0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19,
-                   0x2b1919192b190808, 0x2b1919192b19082b, 0x2b19192b19080819,
-                   0x2b192b0819190819, 0x2b192b082b2b192b, 0x2b192b1919082b19,
-                   0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808,
-                   0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b,
-                   0x2b2b0808082b0808, 0x2b2b0808082b2b2b, 0x2b2b08082b2b0808,
-                   0x2b2b081919190819, 0x2b2b081919192b19, 0x2b2b08192b2b192b,
-                   0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08,
-                   0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808,
-                   0x2b2b190819080808, 0x2b2b19082b191919, 0x2b2b192b192b1919,
-                   0x2b2b192b2b192b08, 0x2b2b2b0808082b2b, 0x2b2b2b08082b0808,
-                   0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808,
-                   0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908,
-                   0x2b2b2b192b08192b, 0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b,
-                   0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b,
-               });
-
-static dpct::global_memory<const uint32_t, 1> iq3xxs_grid(
-    sycl::range<1>(256),
-    {
-        0x04040404, 0x04040414, 0x04040424, 0x04040c0c, 0x04040c1c, 0x04040c3e,
-        0x04041404, 0x04041414, 0x04041c0c, 0x04042414, 0x04043e1c, 0x04043e2c,
-        0x040c040c, 0x040c041c, 0x040c0c04, 0x040c0c14, 0x040c140c, 0x040c142c,
-        0x040c1c04, 0x040c1c14, 0x040c240c, 0x040c2c24, 0x040c3e04, 0x04140404,
-        0x04140414, 0x04140424, 0x04140c0c, 0x04141404, 0x04141414, 0x04141c0c,
-        0x04141c1c, 0x04141c3e, 0x04142c0c, 0x04142c3e, 0x04143e2c, 0x041c040c,
-        0x041c043e, 0x041c0c04, 0x041c0c14, 0x041c142c, 0x041c3e04, 0x04240c1c,
-        0x04241c3e, 0x04242424, 0x04242c3e, 0x04243e1c, 0x04243e2c, 0x042c040c,
-        0x042c043e, 0x042c1c14, 0x042c2c14, 0x04341c2c, 0x04343424, 0x043e0c04,
-        0x043e0c24, 0x043e0c34, 0x043e241c, 0x043e340c, 0x0c04040c, 0x0c04041c,
-        0x0c040c04, 0x0c040c14, 0x0c04140c, 0x0c04141c, 0x0c041c04, 0x0c041c14,
-        0x0c041c24, 0x0c04243e, 0x0c042c04, 0x0c0c0404, 0x0c0c0414, 0x0c0c0c0c,
-        0x0c0c1404, 0x0c0c1414, 0x0c14040c, 0x0c14041c, 0x0c140c04, 0x0c140c14,
-        0x0c14140c, 0x0c141c04, 0x0c143e14, 0x0c1c0404, 0x0c1c0414, 0x0c1c1404,
-        0x0c1c1c0c, 0x0c1c2434, 0x0c1c3434, 0x0c24040c, 0x0c24042c, 0x0c242c04,
-        0x0c2c1404, 0x0c2c1424, 0x0c2c2434, 0x0c2c3e0c, 0x0c34042c, 0x0c3e1414,
-        0x0c3e2404, 0x14040404, 0x14040414, 0x14040c0c, 0x14040c1c, 0x14041404,
-        0x14041414, 0x14041434, 0x14041c0c, 0x14042414, 0x140c040c, 0x140c041c,
-        0x140c042c, 0x140c0c04, 0x140c0c14, 0x140c140c, 0x140c1c04, 0x140c341c,
-        0x140c343e, 0x140c3e04, 0x14140404, 0x14140414, 0x14140c0c, 0x14140c3e,
-        0x14141404, 0x14141414, 0x14141c3e, 0x14142404, 0x14142c2c, 0x141c040c,
-        0x141c0c04, 0x141c0c24, 0x141c3e04, 0x141c3e24, 0x14241c2c, 0x14242c1c,
-        0x142c041c, 0x142c143e, 0x142c240c, 0x142c3e24, 0x143e040c, 0x143e041c,
-        0x143e0c34, 0x143e242c, 0x1c04040c, 0x1c040c04, 0x1c040c14, 0x1c04140c,
-        0x1c04141c, 0x1c042c04, 0x1c04342c, 0x1c043e14, 0x1c0c0404, 0x1c0c0414,
-        0x1c0c1404, 0x1c0c1c0c, 0x1c0c2424, 0x1c0c2434, 0x1c14040c, 0x1c14041c,
-        0x1c140c04, 0x1c14142c, 0x1c142c14, 0x1c143e14, 0x1c1c0c0c, 0x1c1c1c1c,
-        0x1c241c04, 0x1c24243e, 0x1c243e14, 0x1c2c0404, 0x1c2c0434, 0x1c2c1414,
-        0x1c2c2c2c, 0x1c340c24, 0x1c341c34, 0x1c34341c, 0x1c3e1c1c, 0x1c3e3404,
-        0x24040424, 0x24040c3e, 0x24041c2c, 0x24041c3e, 0x24042c1c, 0x24042c3e,
-        0x240c3e24, 0x24141404, 0x24141c3e, 0x24142404, 0x24143404, 0x24143434,
-        0x241c043e, 0x241c242c, 0x24240424, 0x24242c0c, 0x24243424, 0x242c142c,
-        0x242c241c, 0x242c3e04, 0x243e042c, 0x243e0c04, 0x243e0c14, 0x243e1c04,
-        0x2c040c14, 0x2c04240c, 0x2c043e04, 0x2c0c0404, 0x2c0c0434, 0x2c0c1434,
-        0x2c0c2c2c, 0x2c140c24, 0x2c141c14, 0x2c143e14, 0x2c1c0414, 0x2c1c2c1c,
-        0x2c240c04, 0x2c24141c, 0x2c24143e, 0x2c243e14, 0x2c2c0414, 0x2c2c1c0c,
-        0x2c342c04, 0x2c3e1424, 0x2c3e2414, 0x34041424, 0x34042424, 0x34042434,
-        0x34043424, 0x340c140c, 0x340c340c, 0x34140c3e, 0x34143424, 0x341c1c04,
-        0x341c1c34, 0x34242424, 0x342c042c, 0x342c2c14, 0x34341c1c, 0x343e041c,
-        0x343e140c, 0x3e04041c, 0x3e04042c, 0x3e04043e, 0x3e040c04, 0x3e041c14,
-        0x3e042c14, 0x3e0c1434, 0x3e0c2404, 0x3e140c14, 0x3e14242c, 0x3e142c14,
-        0x3e1c0404, 0x3e1c0c2c, 0x3e1c1c1c, 0x3e1c3404, 0x3e24140c, 0x3e24240c,
-        0x3e2c0404, 0x3e2c0414, 0x3e2c1424, 0x3e341c04,
-    });
-
-static dpct::global_memory<const uint8_t, 1> ksigns_iq2xs(
-    sycl::range<1>(128),
-    {
-        0,   129, 130, 3,   132, 5,   6,   135, 136, 9,   10,  139, 12,
-        141, 142, 15,  144, 17,  18,  147, 20,  149, 150, 23,  24,  153,
-        154, 27,  156, 29,  30,  159, 160, 33,  34,  163, 36,  165, 166,
-        39,  40,  169, 170, 43,  172, 45,  46,  175, 48,  177, 178, 51,
-        180, 53,  54,  183, 184, 57,  58,  187, 60,  189, 190, 63,  192,
-        65,  66,  195, 68,  197, 198, 71,  72,  201, 202, 75,  204, 77,
-        78,  207, 80,  209, 210, 83,  212, 85,  86,  215, 216, 89,  90,
-        219, 92,  221, 222, 95,  96,  225, 226, 99,  228, 101, 102, 231,
-        232, 105, 106, 235, 108, 237, 238, 111, 240, 113, 114, 243, 116,
-        245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255,
-    });
-
-static dpct::global_memory<const uint64_t, 1>
-    ksigns64(sycl::range<1>(128),
-             {
-                 0x0000000000000000, 0xff000000000000ff, 0xff0000000000ff00,
-                 0x000000000000ffff, 0xff00000000ff0000, 0x0000000000ff00ff,
-                 0x0000000000ffff00, 0xff00000000ffffff, 0xff000000ff000000,
-                 0x00000000ff0000ff, 0x00000000ff00ff00, 0xff000000ff00ffff,
-                 0x00000000ffff0000, 0xff000000ffff00ff, 0xff000000ffffff00,
-                 0x00000000ffffffff, 0xff0000ff00000000, 0x000000ff000000ff,
-                 0x000000ff0000ff00, 0xff0000ff0000ffff, 0x000000ff00ff0000,
-                 0xff0000ff00ff00ff, 0xff0000ff00ffff00, 0x000000ff00ffffff,
-                 0x000000ffff000000, 0xff0000ffff0000ff, 0xff0000ffff00ff00,
-                 0x000000ffff00ffff, 0xff0000ffffff0000, 0x000000ffffff00ff,
-                 0x000000ffffffff00, 0xff0000ffffffffff, 0xff00ff0000000000,
-                 0x0000ff00000000ff, 0x0000ff000000ff00, 0xff00ff000000ffff,
-                 0x0000ff0000ff0000, 0xff00ff0000ff00ff, 0xff00ff0000ffff00,
-                 0x0000ff0000ffffff, 0x0000ff00ff000000, 0xff00ff00ff0000ff,
-                 0xff00ff00ff00ff00, 0x0000ff00ff00ffff, 0xff00ff00ffff0000,
-                 0x0000ff00ffff00ff, 0x0000ff00ffffff00, 0xff00ff00ffffffff,
-                 0x0000ffff00000000, 0xff00ffff000000ff, 0xff00ffff0000ff00,
-                 0x0000ffff0000ffff, 0xff00ffff00ff0000, 0x0000ffff00ff00ff,
-                 0x0000ffff00ffff00, 0xff00ffff00ffffff, 0xff00ffffff000000,
-                 0x0000ffffff0000ff, 0x0000ffffff00ff00, 0xff00ffffff00ffff,
-                 0x0000ffffffff0000, 0xff00ffffffff00ff, 0xff00ffffffffff00,
-                 0x0000ffffffffffff, 0xffff000000000000, 0x00ff0000000000ff,
-                 0x00ff00000000ff00, 0xffff00000000ffff, 0x00ff000000ff0000,
-                 0xffff000000ff00ff, 0xffff000000ffff00, 0x00ff000000ffffff,
-                 0x00ff0000ff000000, 0xffff0000ff0000ff, 0xffff0000ff00ff00,
-                 0x00ff0000ff00ffff, 0xffff0000ffff0000, 0x00ff0000ffff00ff,
-                 0x00ff0000ffffff00, 0xffff0000ffffffff, 0x00ff00ff00000000,
-                 0xffff00ff000000ff, 0xffff00ff0000ff00, 0x00ff00ff0000ffff,
-                 0xffff00ff00ff0000, 0x00ff00ff00ff00ff, 0x00ff00ff00ffff00,
-                 0xffff00ff00ffffff, 0xffff00ffff000000, 0x00ff00ffff0000ff,
-                 0x00ff00ffff00ff00, 0xffff00ffff00ffff, 0x00ff00ffffff0000,
-                 0xffff00ffffff00ff, 0xffff00ffffffff00, 0x00ff00ffffffffff,
-                 0x00ffff0000000000, 0xffffff00000000ff, 0xffffff000000ff00,
-                 0x00ffff000000ffff, 0xffffff0000ff0000, 0x00ffff0000ff00ff,
-                 0x00ffff0000ffff00, 0xffffff0000ffffff, 0xffffff00ff000000,
-                 0x00ffff00ff0000ff, 0x00ffff00ff00ff00, 0xffffff00ff00ffff,
-                 0x00ffff00ffff0000, 0xffffff00ffff00ff, 0xffffff00ffffff00,
-                 0x00ffff00ffffffff, 0xffffffff00000000, 0x00ffffff000000ff,
-                 0x00ffffff0000ff00, 0xffffffff0000ffff, 0x00ffffff00ff0000,
-                 0xffffffff00ff00ff, 0xffffffff00ffff00, 0x00ffffff00ffffff,
-                 0x00ffffffff000000, 0xffffffffff0000ff, 0xffffffffff00ff00,
-                 0x00ffffffff00ffff, 0xffffffffffff0000, 0x00ffffffffff00ff,
-                 0x00ffffffffffff00, 0xffffffffffffffff,
-             });
-//#endif
-
-static dpct::global_memory<const uint8_t, 1>
-    kmask_iq2xs(sycl::range<1>(8), {1, 2, 4, 8, 16, 32, 64, 128});
-
 template<typename dst_t>
 static void dequantize_block_iq2_xxs(const void * __restrict__ vx, dst_t * __restrict__ yy,
                                     const sycl::nd_item<3> &item_ct1,
@@ -13244,7 +12845,7 @@ void ggml_backend_sycl_print_sycl_devices() {
 }

 void print_gpu_device_list() {
-    fprintf(stderr, "detect %d SYCL GPUs: [%s] with top Max compute units:%d\n",
+    fprintf(stderr, "detect %d SYCL GPUs: [%s] with Max compute units:%d\n",
            g_sycl_gpu_mgr->get_gpu_count(),
            g_sycl_gpu_mgr->gpus_list.c_str(),
            g_sycl_gpu_mgr->max_compute_units);
@@ -13283,15 +12884,6 @@ void ggml_init_sycl() try {
 #else
        fprintf(stderr, "%s: GGML_SYCL_F16: no\n", __func__);
 #endif
-
-/* NOT REMOVE, keep it for next optimize for XMX.
-#if defined(SYCL_USE_XMX)
-        fprintf(stderr, "%s: SYCL_USE_XMX: yes\n", __func__);
-#else
-        fprintf(stderr, "%s: SYCL_USE_XMX: no\n", __func__);
-#endif
-*/
-
        if (CHECK_TRY_ERROR(g_all_sycl_device_count =
                            dpct::dev_mgr::instance().device_count()) != 0) {
            initialized = true;
@@ -13300,61 +12892,68 @@ void ggml_init_sycl() try {
        }
        GGML_ASSERT(g_all_sycl_device_count <= GGML_SYCL_MAX_DEVICES);
        ggml_backend_sycl_print_sycl_devices();
+
        if (!g_sycl_gpu_mgr) g_sycl_gpu_mgr = new sycl_gpu_mgr();
+
+        g_device_count = g_sycl_gpu_mgr->get_gpu_count();
+        g_work_group_size = g_sycl_gpu_mgr->work_group_size;
+
        print_gpu_device_list();
-        initialized = true;
-        g_sycl_loaded = true;
-    }

+        int64_t total_vram = 0;

-
-    g_device_count = g_sycl_gpu_mgr->get_gpu_count();
-    g_work_group_size = g_sycl_gpu_mgr->work_group_size;
-
-    int64_t total_vram = 0;
-
-
-    for (int id = 0; id < GGML_SYCL_MAX_DEVICES; ++id) {
-        g_device_caps[id].vmm = 0;
-        g_device_caps[id].device_id = -1;
-        g_device_caps[id].cc = 0;
-        g_tensor_split[id] = 0;
-        g_default_tensor_split[id] = 0;
-    }
-
-    for (int i = 0; i < g_device_count; ++i) {
-        int device_id = g_sycl_gpu_mgr->gpus[i];
-        g_device_caps[i].vmm = 0;
-
-        dpct::device_info prop;
-        SYCL_CHECK(CHECK_TRY_ERROR(dpct::get_device_info(
-            prop, dpct::dev_mgr::instance().get_device(device_id))));
-
-        g_default_tensor_split[i] = total_vram;
-        total_vram += prop.get_global_mem_size();
-
-        g_device_caps[i].cc =
-            100 * prop.get_major_version() + 10 * prop.get_minor_version();
-    }
-
-    for (int i = 0; i < g_device_count; ++i) {
-        g_default_tensor_split[i] /= total_vram;
-    }
-
-    for (int i = 0; i < g_device_count; ++i) {
-        SYCL_CHECK(ggml_sycl_set_device(i));
-
-        // create sycl streams
-        for (int is = 0; is < MAX_STREAMS; ++is) {
-            SYCL_CHECK(CHECK_TRY_ERROR(
-                g_syclStreams[i][is] =
-                    dpct::get_current_device().create_queue(
-                        g_sycl_gpu_mgr->get_co_ctx(), dpct::get_current_device())));
+/* NOT REMOVE, keep it for next optimize for XMX.
+#if defined(SYCL_USE_XMX)
+        fprintf(stderr, "%s: SYCL_USE_XMX: yes\n", __func__);
+#else
+        fprintf(stderr, "%s: SYCL_USE_XMX: no\n", __func__);
+#endif
+*/
+        for (int id = 0; id < GGML_SYCL_MAX_DEVICES; ++id) {
+            g_device_caps[id].vmm = 0;
+            g_device_caps[id].device_id = -1;
+            g_device_caps[id].cc = 0;
+            g_tensor_split[id] = 0;
+            g_default_tensor_split[id] = 0;
        }

-        const dpct::queue_ptr stream = g_syclStreams[i][0];
-        // create sycl handle
-        SYCL_CHECK(CHECK_TRY_ERROR(g_sycl_handles[i] = stream));
+        for (int i = 0; i < g_device_count; ++i) {
+            int device_id = g_sycl_gpu_mgr->gpus[i];
+            g_device_caps[i].vmm = 0;
+
+            dpct::device_info prop;
+            SYCL_CHECK(CHECK_TRY_ERROR(dpct::get_device_info(
+                prop, dpct::dev_mgr::instance().get_device(device_id))));
+
+            g_default_tensor_split[i] = total_vram;
+            total_vram += prop.get_global_mem_size();
+
+            g_device_caps[i].cc =
+                100 * prop.get_major_version() + 10 * prop.get_minor_version();
+        }
+
+        for (int i = 0; i < g_device_count; ++i) {
+            g_default_tensor_split[i] /= total_vram;
+        }
+
+        for (int i = 0; i < g_device_count; ++i) {
+            SYCL_CHECK(ggml_sycl_set_device(i));
+
+            // create sycl streams
+            for (int is = 0; is < MAX_STREAMS; ++is) {
+                SYCL_CHECK(CHECK_TRY_ERROR(
+                    g_syclStreams[i][is] =
+                        dpct::get_current_device().create_queue(
+                            g_sycl_gpu_mgr->get_co_ctx(), dpct::get_current_device())));
+            }
+
+            const dpct::queue_ptr stream = g_syclStreams[i][0];
+            // create sycl handle
+            SYCL_CHECK(CHECK_TRY_ERROR(g_sycl_handles[i] = stream));
+        }
+
+        initialized = true;
+        g_sycl_loaded = true;
    }
 }
 catch (sycl::exception const &exc) {
@@ -16753,24 +16352,22 @@ static ggml_backend_buffer_type_i ggml_backend_sycl_buffer_type_interface = {
    /* .is_host          = */ nullptr,
 };

-ggml_backend_buffer_type_t ggml_backend_sycl_buffer_type(int device_index) {
-    if (device_index>=g_device_count or device_index<0) {
-        printf("ggml_backend_sycl_buffer_type error: device_index:%d is out of range [0, %d], miss to call ggml_backend_sycl_set_single_device()\n",
-            device_index, g_device_count-1);
-        GGML_ASSERT(device_index<g_device_count);
-    }
+ggml_backend_buffer_type_t ggml_backend_sycl_buffer_type(int device) {
    static struct ggml_backend_buffer_type ggml_backend_sycl_buffer_types[GGML_SYCL_MAX_DEVICES];

-    if (!g_ggml_backend_sycl_buffer_type_initialized) {
+    static bool ggml_backend_sycl_buffer_type_initialized = false;
+
+    if (!ggml_backend_sycl_buffer_type_initialized) {
        for (int i = 0; i < g_device_count; i++) {
            ggml_backend_sycl_buffer_types[i] = {
                /* .iface    = */ ggml_backend_sycl_buffer_type_interface,
                /* .context  = */ new ggml_backend_sycl_buffer_type_context{i, GGML_SYCL_NAME + std::to_string(g_sycl_gpu_mgr->gpus[i])},
            };
        }
-        g_ggml_backend_sycl_buffer_type_initialized = true;
+        ggml_backend_sycl_buffer_type_initialized = true;
    }
-    return &ggml_backend_sycl_buffer_types[device_index];
+
+    return &ggml_backend_sycl_buffer_types[device];
 }

 // sycl split buffer type
@@ -17519,17 +17116,6 @@ GGML_API GGML_CALL int ggml_backend_sycl_get_device_index(int device_id) {
    return g_sycl_gpu_mgr->get_index(device_id);
 }

-GGML_API GGML_CALL void ggml_backend_sycl_set_single_device(int main_gpu_id) {
-    GGML_ASSERT(main_gpu_id<g_all_sycl_device_count);
-    printf("ggml_backend_sycl_set_single_device: use single device: %d\n", main_gpu_id);
-    if (g_sycl_gpu_mgr) {
-        delete g_sycl_gpu_mgr;
-    }
-    g_sycl_gpu_mgr = new sycl_gpu_mgr(main_gpu_id);
-    ggml_init_sycl();
-    g_ggml_backend_sycl_buffer_type_initialized = false;
-}
-
 extern "C" int ggml_backend_sycl_reg_devices();

 int ggml_backend_sycl_reg_devices() {
@@ -28,7 +28,6 @@ GGML_API GGML_CALL int   ggml_backend_sycl_get_device_count();
 GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_sycl_split_buffer_type(const float * tensor_split);
 GGML_API GGML_CALL void ggml_backend_sycl_get_device_memory(int device, size_t *free, size_t *total);
 GGML_API GGML_CALL int ggml_backend_sycl_get_device_index(int device_id);
-GGML_API GGML_CALL void ggml_backend_sycl_set_single_device(int main_gpu);

 #ifdef  __cplusplus
 }
@@ -4102,45 +4102,7 @@ static void ggml_vk_test_transfer(ggml_backend_vk_context * ctx, size_t ne, bool
 }

 static void ggml_vk_quantize_data(const float * from, void * to, size_t ne, ggml_type quant) {
-    std::vector<int64_t> hist_cur(1 << 4, 0);
-
-    switch(quant) {
-    case GGML_TYPE_F32:
-        memcpy(to, from, sizeof(float) * ne);
-        break;
-    case GGML_TYPE_Q4_0:
-        ggml_quantize_q4_0(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q4_1:
-        ggml_quantize_q4_1(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q5_0:
-        ggml_quantize_q5_0(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q5_1:
-        ggml_quantize_q5_1(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q8_0:
-        ggml_quantize_q8_0(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q2_K:
-        ggml_quantize_q2_K(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q3_K:
-        ggml_quantize_q3_K(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q4_K:
-        ggml_quantize_q4_K(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q5_K:
-        ggml_quantize_q5_K(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q6_K:
-        ggml_quantize_q6_K(from, to, ne, ne, hist_cur.data());
-        break;
-    default:
-        GGML_ASSERT(false);
-    }
+    ggml_quantize_chunk(quant, from, to, 0, 1, ne, nullptr);
 }

 static void ggml_vk_test_dequant(ggml_backend_vk_context * ctx, size_t ne, ggml_type quant) {
@@ -1841,6 +1841,8 @@ static const char * GGML_OP_NAME[GGML_OP_COUNT] = {
    "FLASH_ATTN",
    "FLASH_FF",
    "FLASH_ATTN_BACK",
+    "SSM_CONV",
+    "SSM_SCAN",
    "WIN_PART",
    "WIN_UNPART",
    "GET_REL_POS",
@@ -1863,7 +1865,7 @@ static const char * GGML_OP_NAME[GGML_OP_COUNT] = {
    "CROSS_ENTROPY_LOSS_BACK",
 };

-static_assert(GGML_OP_COUNT == 74, "GGML_OP_COUNT != 74");
+static_assert(GGML_OP_COUNT == 76, "GGML_OP_COUNT != 76");

 static const char * GGML_OP_SYMBOL[GGML_OP_COUNT] = {
    "none",
@@ -1929,6 +1931,8 @@ static const char * GGML_OP_SYMBOL[GGML_OP_COUNT] = {
    "flash_attn(x)",
    "flash_ff(x)",
    "flash_attn_back(x)",
+    "ssm_conv(x)",
+    "ssm_scan(x)",
    "win_part(x)",
    "win_unpart(x)",
    "get_rel_pos(x)",
@@ -1951,7 +1955,7 @@ static const char * GGML_OP_SYMBOL[GGML_OP_COUNT] = {
    "cross_entropy_loss_back(x,y)",
 };

-static_assert(GGML_OP_COUNT == 74, "GGML_OP_COUNT != 74");
+static_assert(GGML_OP_COUNT == 76, "GGML_OP_COUNT != 76");

 static_assert(GGML_OP_POOL_COUNT == 2, "GGML_OP_POOL_COUNT != 2");

@@ -6154,6 +6158,108 @@ struct ggml_tensor * ggml_flash_attn_back(
    return result;
 }

+// ggml_ssm_conv
+
+struct ggml_tensor * ggml_ssm_conv(
+        struct ggml_context * ctx,
+        struct ggml_tensor  * s,
+        struct ggml_tensor  * x,
+        struct ggml_tensor  * c,
+        struct ggml_tensor  * sq) {
+    GGML_ASSERT(ggml_is_3d(s));
+    GGML_ASSERT(ggml_is_matrix(x));
+    GGML_ASSERT(ggml_is_matrix(c));
+    GGML_ASSERT(ggml_is_matrix(sq));
+    GGML_ASSERT(sq->type == GGML_TYPE_I32);
+
+    const int64_t d_conv   = c->ne[0];
+    const int64_t d_inner  = c->ne[1];
+    const int64_t n_tokens = x->ne[1];
+    const int64_t n_kv     = s->ne[2];
+
+    GGML_ASSERT( s->ne[0] == d_conv - 1);
+    GGML_ASSERT( s->ne[1] == d_inner);
+    GGML_ASSERT( x->ne[0] == d_inner);
+    GGML_ASSERT(sq->ne[0] == n_kv);
+    GGML_ASSERT(sq->ne[1] == n_tokens);
+
+    bool is_node = false;
+
+    if (s->grad || x->grad || c->grad || sq->grad) {
+        GGML_ASSERT(false); // TODO: implement
+        is_node = true;
+    }
+
+    // 2-in-1 concatenated x and conv_states, {d_inner, n_tokens} with {d_conv, d_inner, n_kv}
+    struct ggml_tensor * result = ggml_new_tensor_1d(ctx, GGML_TYPE_F32, (d_inner*n_tokens) + (d_conv*d_inner*n_kv));
+
+    result->op   = GGML_OP_SSM_CONV;
+    result->grad = is_node ? ggml_dup_tensor(ctx, result) : NULL;
+    result->src[0] = s;
+    result->src[1] = x;
+    result->src[2] = c;
+    result->src[3] = sq;
+
+    return result;
+}
+
+// ggml_ssm_scan
+
+struct ggml_tensor * ggml_ssm_scan(
+        struct ggml_context * ctx,
+        struct ggml_tensor  * s,
+        struct ggml_tensor  * x,
+        struct ggml_tensor  * dt,
+        struct ggml_tensor  * A,
+        struct ggml_tensor  * B,
+        struct ggml_tensor  * C,
+        struct ggml_tensor  * sq) {
+    GGML_ASSERT(ggml_is_contiguous(s));
+    GGML_ASSERT(ggml_is_contiguous(x));
+    GGML_ASSERT(ggml_is_contiguous(dt));
+    GGML_ASSERT(ggml_is_contiguous(A));
+    GGML_ASSERT(sq->type == GGML_TYPE_I32);
+    GGML_ASSERT(B->nb[0] == ggml_type_size(B->type));
+    GGML_ASSERT(C->nb[0] == ggml_type_size(C->type));
+    GGML_ASSERT(ggml_are_same_shape(x, dt));
+
+    {
+        const int64_t d_state  = s->ne[0];
+        const int64_t d_inner  = s->ne[1];
+        const int64_t n_tokens = x->ne[1];
+
+        GGML_ASSERT(x->ne[0] == d_inner);
+        GGML_ASSERT(A->ne[0] == d_state);
+        GGML_ASSERT(A->ne[1] == d_inner);
+        GGML_ASSERT(B->ne[0] == d_state);
+        GGML_ASSERT(B->ne[1] == n_tokens);
+        GGML_ASSERT(C->ne[0] == d_state);
+        GGML_ASSERT(C->ne[1] == n_tokens);
+    }
+
+    bool is_node = false;
+
+    if (s->grad || x->grad || dt->grad || A->grad || B->grad || C->grad || sq->grad) {
+        GGML_ASSERT(false); // TODO: implement
+        is_node = true;
+    }
+
+    // 2-in-1 concatenated y and ssm_states, {d_inner, n_tokens} with {d_state, d_inner, n_kv}
+    struct ggml_tensor * result = ggml_new_tensor_1d(ctx, GGML_TYPE_F32, ggml_nelements(x) + ggml_nelements(s));
+
+    result->op   = GGML_OP_SSM_SCAN;
+    result->grad = is_node ? ggml_dup_tensor(ctx, result) : NULL;
+    result->src[0] = s;
+    result->src[1] = x;
+    result->src[2] = dt;
+    result->src[3] = A;
+    result->src[4] = B;
+    result->src[5] = C;
+    result->src[6] = sq;
+
+    return result;
+}
+
 // ggml_win_part

 struct ggml_tensor * ggml_win_part(
@@ -14771,6 +14877,257 @@ static void ggml_compute_forward_flash_attn_back(
    }
 }

+// ggml_compute_forward_ssm_conv
+
+static void ggml_compute_forward_ssm_conv_f32(
+        const struct ggml_compute_params * params,
+        struct ggml_tensor * dst) {
+    if (params->type == GGML_TASK_TYPE_INIT || params->type == GGML_TASK_TYPE_FINALIZE) {
+        return;
+    }
+
+    const struct ggml_tensor * src0 = dst->src[0]; // conv_state
+    const struct ggml_tensor * src1 = dst->src[1]; // x
+    const struct ggml_tensor * src2 = dst->src[2]; // conv1d.weight
+    const struct ggml_tensor * src3 = dst->src[3]; // state_seq
+
+    const int ith = params->ith;
+    const int nth = params->nth;
+
+    const int nc   = src2->ne[0]; // d_conv
+    const int nr   = src0->ne[1]; // d_inner
+    const int n_t  = src1->ne[1]; // n_tokens
+    const int n_kv = src0->ne[2]; // max number of sequences in the batch
+
+    GGML_ASSERT((nr*n_t) + (nc*nr*n_kv) == ggml_nelements(dst));
+    GGML_ASSERT(src0->nb[0] == sizeof(float));
+    GGML_ASSERT(src1->nb[0] == sizeof(float));
+    GGML_ASSERT(src2->nb[0] == sizeof(float));
+    GGML_ASSERT(src3->nb[0] == sizeof(int32_t));
+    GGML_ASSERT(src0->nb[1] == src0->ne[0]*sizeof(float));
+    // for use with the destination state offset between sequences
+    GGML_ASSERT(src2->nb[2] == src2->ne[1]*src2->ne[0]*sizeof(float));
+
+    // rows per thread
+    const int dr = (nr + nth - 1)/nth;
+
+    // row range for this thread
+    const int ir0 = dr*ith;
+    const int ir1 = MIN(ir0 + dr, nr);
+    const int ir  = ir1 - ir0;
+
+    if (n_kv > 1) {
+        // multiple sequences means it's hard to know when it's the first time a state is read,
+        // so copy them all over to the destination, just to be sure.
+        for (int i3 = 0; i3 < n_kv; ++i3) {
+            float * s0 = (float *) ((char *) src0->data + ir0*(src0->nb[1]) + i3*(src0->nb[2]));
+            float * s  = (float *) ((char *)  dst->data + ir0*(src2->nb[1]) + i3*(src2->nb[2]) + nr*n_t*sizeof(float));
+            // can't use memcpy because of d_conv vs d_conv - 1
+            for (int i1 = 0; i1 < ir; ++i1) {
+                for (int i0 = 0; i0 < nc - 1; ++i0) {
+                    // copy s0 to last (d_conv - 1) columns of s
+                    s[1 + i0 + i1*nc] = s0[i0 + i1*(nc - 1)];
+                }
+            }
+        }
+    }
+
+    for (int i2 = 0; i2 < n_t; ++i2) {
+        int32_t * sq = (int32_t *) ((char *) src3->data +  i2*(src3->nb[1])); // {n_kv, n_tokens}
+        float *   x  = (float *)   ((char *)  dst->data + ir0*sizeof(float) + i2*(nr*sizeof(float))); // {d_inner, n_tokens}
+        float *   s  = (float *)   ((char *)  dst->data + ir0*(src2->nb[1]) + sq[0]*(src2->nb[2]) + nr*n_t*sizeof(float)); // {d_conv, d_inner, n_kv}
+        float *   s0; // {d_conv - 1, d_inner, n_kv}
+        float *   x0 = (float *)   ((char *) src1->data + ir0*(src1->nb[0]) + i2*(src1->nb[1])); // {d_inner, n_tokens}
+        float *   c  = (float *)   ((char *) src2->data + ir0*(src2->nb[1])); // {d_conv, d_inner}
+        int ne0s0;
+
+        GGML_ASSERT(0 <= sq[0] && sq[0] < n_kv);
+
+        // avoid needing to copy the state for the first token
+        if (i2 == 0) {
+            s0 = (float *) ((char *) src0->data + ir0*(src0->nb[1]) + sq[0]*(src0->nb[2])); // {d_conv - 1, d_inner, n_kv}
+            ne0s0 = src0->ne[0];
+        } else {
+            // the source is the last (d_conv - 1) columns of the destination
+            s0 = s + 1;
+            ne0s0 = nc;
+        }
+
+        // d_inner
+        for (int i1 = 0; i1 < ir; ++i1) {
+            // shift state left
+            for (int i0 = 0; i0 < nc - 1; ++i0) {
+                s[i0 + i1*nc] = s0[i0 + i1*ne0s0];
+            }
+            // insert x on the last column
+            s[(nc - 1) + i1*nc] = x0[i1];
+        }
+
+        // handle copies when there are multiple output states
+        for (int i3 = 1; i3 < n_kv; ++i3) {
+            int32_t seq = sq[i3];
+            if (0 <= seq && seq < n_kv) {
+                float * s1 = s + (seq - sq[0])*nc*nr;
+                memcpy(s1, s, nc*ir*sizeof(float));
+            } else {
+                // stop at negative or too big seq_ids
+                break;
+            }
+        }
+
+        // it seems a little faster when this is separate from the state shift
+        for (int i1 = 0; i1 < ir; ++i1) {
+            // rowwise dot product
+            float sumf = 0.0f;
+            for (int i0 = 0; i0 < nc; ++i0) {
+                int i = i0 + i1*nc;
+                sumf += s[i] * c[i];
+            }
+            x[i1] = sumf;
+        }
+    }
+}
+
+static void ggml_compute_forward_ssm_conv(
+        const struct ggml_compute_params * params,
+        struct ggml_tensor * dst) {
+    switch (dst->src[0]->type) {
+        case GGML_TYPE_F32:
+            {
+                ggml_compute_forward_ssm_conv_f32(params, dst);
+            } break;
+        default:
+            {
+                GGML_ASSERT(false);
+            } break;
+    }
+}
+
+// ggml_compute_forward_ssm_scan
+
+static void ggml_compute_forward_ssm_scan_f32(
+        const struct ggml_compute_params * params,
+        struct ggml_tensor * dst) {
+    if (params->type == GGML_TASK_TYPE_INIT || params->type == GGML_TASK_TYPE_FINALIZE) {
+        return;
+    }
+
+    const struct ggml_tensor * src0 = dst->src[0]; // s
+    const struct ggml_tensor * src1 = dst->src[1]; // x
+    const struct ggml_tensor * src2 = dst->src[2]; // dt
+    const struct ggml_tensor * src3 = dst->src[3]; // A
+    const struct ggml_tensor * src4 = dst->src[4]; // B
+    const struct ggml_tensor * src5 = dst->src[5]; // C
+    const struct ggml_tensor * src6 = dst->src[6]; // sq
+
+    const int ith = params->ith;
+    const int nth = params->nth;
+
+    const int64_t nc   = src0->ne[0]; // d_state
+    const int64_t nr   = src0->ne[1]; // d_inner
+    const int64_t n_t  = src1->ne[1]; // number of tokens in the batch
+    const int64_t n_kv = src0->ne[2]; // max number of sequences in the batch
+
+    GGML_ASSERT(ggml_nelements(src1) + ggml_nelements(src0) == ggml_nelements(dst));
+    GGML_ASSERT(src0->nb[0] == sizeof(float));
+    GGML_ASSERT(src1->nb[0] == sizeof(float));
+    GGML_ASSERT(src2->nb[0] == sizeof(float));
+    GGML_ASSERT(src3->nb[0] == sizeof(float));
+    GGML_ASSERT(src4->nb[0] == sizeof(float));
+    GGML_ASSERT(src5->nb[0] == sizeof(float));
+    // required for the dot product between s and C, and when copying the states
+    GGML_ASSERT(src0->nb[1] == src0->ne[0]*sizeof(float));
+    // required for per-sequence offsets for states
+    GGML_ASSERT(src0->nb[2] == src0->ne[0]*src0->ne[1]*sizeof(float));
+    // required to get correct offset for state destination (i.e. src1->nb[2])
+    GGML_ASSERT(src1->nb[2] == src1->ne[0]*src1->ne[1]*sizeof(float));
+
+    // rows per thread
+    const int dr = (nr + nth - 1)/nth;
+
+    // row range for this thread
+    const int ir0 = dr*ith;
+    const int ir1 = MIN(ir0 + dr, nr);
+    const int ir  = ir1 - ir0;
+
+    if (n_kv > 1) {
+        // it's hard to know if the source states have already been copied
+        // when there are multiple, so copy them already.
+        for (int i3 = 0; i3 < n_kv; ++i3) {
+            float * s0 = (float *) ((char *) src0->data + ir0*(src0->nb[1]) + i3*(src0->nb[2]));
+            float * s  = (float *) ((char *)  dst->data + ir0*(src0->nb[1]) + i3*(src0->nb[2]) + src1->nb[2]);
+            memcpy(s, s0, nc*ir*sizeof(float));
+        }
+    }
+
+    for (int i2 = 0; i2 < n_t; ++i2) {
+        int32_t * sq = (int32_t *) ((char *) src6->data +  i2*(src6->nb[1])); // {n_kv, n_tokens}
+        float *   y  = (float *)   ((char *)  dst->data + ir0*(src1->nb[0]) +    i2*(src1->nb[1])); // {d_inner, n_tokens}
+        float *   s  = (float *)   ((char *)  dst->data + ir0*(src0->nb[1]) + sq[0]*(src0->nb[2]) + src1->nb[2]); // {d_state, d_inner, n_kv}
+        float *   s0;
+        float *   x  = (float *)   ((char *) src1->data + ir0*(src1->nb[0]) + i2*(src1->nb[1])); // {d_inner, n_tokens}
+        float *   dt = (float *)   ((char *) src2->data + ir0*(src2->nb[0]) + i2*(src2->nb[1])); // {d_inner, n_tokens}
+        float *   A  = (float *)   ((char *) src3->data + ir0*(src3->nb[1])); // {d_state, d_inner}
+        float *   B  = (float *)   ((char *) src4->data +  i2*(src4->nb[1])); // {d_state, n_tokens}
+        float *   C  = (float *)   ((char *) src5->data +  i2*(src5->nb[1])); // {d_state, n_tokens}
+
+        GGML_ASSERT(0 <= sq[0] && sq[0] < n_kv);
+
+        // avoid needing to copy the state for the first token
+        if (i2 == 0) {
+            s0 = (float *) ((char *) src0->data + ir0*(src0->nb[1]) + sq[0]*(src0->nb[2])); // {d_state, d_inner, n_kv}
+        } else {
+            // otherwise the source is the same as the destination
+            s0 = s;
+        }
+
+        // d_inner
+        for (int i1 = 0; i1 < ir; ++i1) {
+            // ref: https://github.com/state-spaces/mamba/blob/34076d664838588a3c97727b263478ab9f621a07/mamba_ssm/ops/triton/selective_state_update.py#L78
+            float dt_soft_plus = dt[i1] <= 20.0f ? log1pf(expf(dt[i1])) : dt[i1];
+            float x_dt = x[i1] * dt_soft_plus;
+            float sumf = 0.0f;
+            // d_state
+            for (int i0 = 0; i0 < nc; ++i0) {
+                int i = i0 + i1*nc;
+                // state = prev_state * dA + dB * x
+                float state = (s0[i] * expf(dt_soft_plus * A[i])) + (B[i0] * x_dt);
+                // y = rowwise_dotprod(state, C)
+                sumf += state * C[i0];
+                s[i] = state;
+            }
+            y[i1] = sumf;
+        }
+
+        // handle copies when there are multiple output states
+        for (int i3 = 1; i3 < n_kv; ++i3) {
+            int32_t seq = sq[i3];
+            if (0 <= seq && seq < n_kv) {
+                float * s1 = s + (seq - sq[0])*nc*nr;
+                memcpy(s1, s, nc*ir*sizeof(float));
+            } else {
+                // stop at negative or too big seq_ids
+                break;
+            }
+        }
+    }
+}
+
+static void ggml_compute_forward_ssm_scan(
+        const struct ggml_compute_params * params,
+        struct ggml_tensor * dst) {
+    switch (dst->src[0]->type) {
+        case GGML_TYPE_F32:
+            {
+                ggml_compute_forward_ssm_scan_f32(params, dst);
+            } break;
+        default:
+            {
+                GGML_ASSERT(false);
+            } break;
+    }
+}
+
 // ggml_compute_forward_win_part

 static void ggml_compute_forward_win_part_f32(
@@ -15830,6 +16187,14 @@ static void ggml_compute_forward(struct ggml_compute_params * params, struct ggm
                bool masked = t != 0;
                ggml_compute_forward_flash_attn_back(params, masked, tensor);
            } break;
+        case GGML_OP_SSM_CONV:
+            {
+                ggml_compute_forward_ssm_conv(params, tensor);
+            } break;
+        case GGML_OP_SSM_SCAN:
+            {
+                ggml_compute_forward_ssm_scan(params, tensor);
+            } break;
        case GGML_OP_WIN_PART:
            {
                ggml_compute_forward_win_part(params, tensor);
@@ -16884,6 +17249,11 @@ static void ggml_compute_backward(struct ggml_context * ctx, struct ggml_tensor
            {
                GGML_ASSERT(false); // not supported
            } break;
+        case GGML_OP_SSM_CONV:
+        case GGML_OP_SSM_SCAN:
+            {
+                GGML_ASSERT(false); // TODO: not implemented
+            } break;
        case GGML_OP_WIN_PART:
        case GGML_OP_WIN_UNPART:
        case GGML_OP_UNARY:
@@ -17590,6 +17960,11 @@ static int ggml_get_n_tasks(struct ggml_tensor * node, int n_threads) {
            {
                n_tasks = n_threads;
            } break;
+        case GGML_OP_SSM_CONV:
+        case GGML_OP_SSM_SCAN:
+            {
+                n_tasks = n_threads;
+            } break;
        case GGML_OP_WIN_PART:
        case GGML_OP_WIN_UNPART:
        case GGML_OP_GET_REL_POS:
@@ -19784,133 +20159,6 @@ void ggml_quantize_free(void) {
    ggml_critical_section_end();
 }

-size_t ggml_quantize_q4_0(const float * src, void * dst, int n, int k, int64_t * hist) {
-    assert(k % QK4_0 == 0);
-    const int nb = k / QK4_0;
-
-    for (int b = 0; b < n; b += k) {
-        block_q4_0 * restrict y = (block_q4_0 *) dst + b/QK4_0;
-
-        quantize_row_q4_0_reference(src + b, y, k);
-
-        for (int i = 0; i < nb; i++) {
-            for (int j = 0; j < QK4_0; j += 2) {
-                const uint8_t vi0 = y[i].qs[j/2] & 0x0F;
-                const uint8_t vi1 = y[i].qs[j/2] >> 4;
-
-                hist[vi0]++;
-                hist[vi1]++;
-            }
-        }
-    }
-
-    return (n/QK4_0*sizeof(block_q4_0));
-}
-
-size_t ggml_quantize_q4_1(const float * src, void * dst, int n, int k, int64_t * hist) {
-    assert(k % QK4_1 == 0);
-    const int nb = k / QK4_1;
-
-    for (int b = 0; b < n; b += k) {
-        block_q4_1 * restrict y = (block_q4_1 *) dst + b/QK4_1;
-
-        quantize_row_q4_1_reference(src + b, y, k);
-
-        for (int i = 0; i < nb; i++) {
-            for (int j = 0; j < QK4_1; j += 2) {
-                const uint8_t vi0 = y[i].qs[j/2] & 0x0F;
-                const uint8_t vi1 = y[i].qs[j/2] >> 4;
-
-                hist[vi0]++;
-                hist[vi1]++;
-            }
-        }
-    }
-
-    return (n/QK4_1*sizeof(block_q4_1));
-}
-
-size_t ggml_quantize_q5_0(const float * src, void * dst, int n, int k, int64_t * hist) {
-    assert(k % QK5_0 == 0);
-    const int nb = k / QK5_0;
-
-    for (int b = 0; b < n; b += k) {
-        block_q5_0 * restrict y = (block_q5_0 *)dst + b/QK5_0;
-
-        quantize_row_q5_0_reference(src + b, y, k);
-
-        for (int i = 0; i < nb; i++) {
-            uint32_t qh;
-            memcpy(&qh, &y[i].qh, sizeof(qh));
-
-            for (int j = 0; j < QK5_0; j += 2) {
-                const uint8_t vh0 = ((qh & (1u << (j/2 + 0 ))) >> (j/2 + 0 )) << 4;
-                const uint8_t vh1 = ((qh & (1u << (j/2 + 16))) >> (j/2 + 12));
-
-                // cast to 16 bins
-                const uint8_t vi0 = ((y[i].qs[j/2] & 0x0F) | vh0) / 2;
-                const uint8_t vi1 = ((y[i].qs[j/2] >>   4) | vh1) / 2;
-
-                hist[vi0]++;
-                hist[vi1]++;
-            }
-        }
-    }
-
-    return (n/QK5_0*sizeof(block_q5_0));
-}
-
-size_t ggml_quantize_q5_1(const float * src, void * dst, int n, int k, int64_t * hist) {
-    assert(k % QK5_1 == 0);
-    const int nb = k / QK5_1;
-
-    for (int b = 0; b < n; b += k) {
-        block_q5_1 * restrict y = (block_q5_1 *)dst + b/QK5_1;
-
-        quantize_row_q5_1_reference(src + b, y, k);
-
-        for (int i = 0; i < nb; i++) {
-            uint32_t qh;
-            memcpy(&qh, &y[i].qh, sizeof(qh));
-
-            for (int j = 0; j < QK5_1; j += 2) {
-                const uint8_t vh0 = ((qh & (1u << (j/2 + 0 ))) >> (j/2 + 0 )) << 4;
-                const uint8_t vh1 = ((qh & (1u << (j/2 + 16))) >> (j/2 + 12));
-
-                // cast to 16 bins
-                const uint8_t vi0 = ((y[i].qs[j/2] & 0x0F) | vh0) / 2;
-                const uint8_t vi1 = ((y[i].qs[j/2] >>   4) | vh1) / 2;
-
-                hist[vi0]++;
-                hist[vi1]++;
-            }
-        }
-    }
-
-    return (n/QK5_1*sizeof(block_q5_1));
-}
-
-size_t ggml_quantize_q8_0(const float * src, void * dst, int n, int k, int64_t * hist) {
-    assert(k % QK8_0 == 0);
-    const int nb = k / QK8_0;
-
-    for (int b = 0; b < n; b += k) {
-        block_q8_0 * restrict y = (block_q8_0 *)dst + b/QK8_0;
-
-        quantize_row_q8_0_reference(src + b, y, k);
-
-        for (int i = 0; i < nb; i++) {
-            for (int j = 0; j < QK8_0; ++j) {
-                const int8_t vi = y[i].qs[j];
-
-                hist[vi/16 + 8]++;
-            }
-        }
-    }
-
-    return (n/QK8_0*sizeof(block_q8_0));
-}
-
 bool ggml_quantize_requires_imatrix(enum ggml_type type) {
    return
        type == GGML_TYPE_IQ2_XXS ||
@@ -19918,177 +20166,52 @@ bool ggml_quantize_requires_imatrix(enum ggml_type type) {
        type == GGML_TYPE_IQ1_S;
 }

-size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst, int start,
-        int nrows, int n_per_row, int64_t * hist, const float * imatrix) {
+size_t ggml_quantize_chunk(
+        enum ggml_type   type,
+           const float * src,
+                  void * dst,
+                   int   start,
+                   int   nrows,
+                   int   n_per_row,
+           const float * imatrix) {
+    const int n = nrows * n_per_row;
+
+    if (ggml_quantize_requires_imatrix(type)) {
+        GGML_ASSERT(imatrix != NULL);
+    }
+
+    GGML_ASSERT(start % type_traits[type].blck_size == 0);
+    GGML_ASSERT(start % n_per_row == 0);
+
    ggml_quantize_init(type); // this is noop if already initialized
+
+    const size_t start_row = start / n_per_row;
+    const size_t row_size  = ggml_row_size(type, n_per_row);
+
    size_t result = 0;
-    int n = nrows * n_per_row;
+
    switch (type) {
-        case GGML_TYPE_Q4_0:
-            {
-                GGML_ASSERT(start % QK4_0 == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q4_0(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_Q4_1:
-            {
-                GGML_ASSERT(start % QK4_1 == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q4_1(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_Q5_0:
-            {
-                GGML_ASSERT(start % QK5_0 == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q5_0(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_Q5_1:
-            {
-                GGML_ASSERT(start % QK5_1 == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q5_1(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_Q8_0:
-            {
-                GGML_ASSERT(start % QK8_0 == 0);
-                block_q8_0 * block = (block_q8_0*)dst + start / QK8_0;
-                result = ggml_quantize_q8_0(src + start, block, n, n, hist);
-            } break;
-        case GGML_TYPE_Q2_K:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q2_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_Q3_K:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q3_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_Q4_K:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q4_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_Q5_K:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q5_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_Q6_K:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q6_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_IQ2_XXS:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                GGML_ASSERT(imatrix);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_iq2_xxs(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_IQ2_XS:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                GGML_ASSERT(imatrix);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_iq2_xs(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_IQ3_XXS:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_iq3_xxs(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_IQ3_S:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_iq3_s(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_IQ2_S:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_iq2_s(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_IQ1_S:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_iq1_s(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_IQ4_NL:
+        case GGML_TYPE_Q4_0:    result = quantize_q4_0(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q4_1:    result = quantize_q4_1(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q5_0:    result = quantize_q5_0(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q5_1:    result = quantize_q5_1(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q8_0:    result = quantize_q8_0(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q2_K:    result = quantize_q2_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q3_K:    result = quantize_q3_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q4_K:    result = quantize_q4_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q5_K:    result = quantize_q5_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q6_K:    result = quantize_q6_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_IQ2_XXS: result = quantize_iq2_xxs(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_IQ2_XS:  result = quantize_iq2_xs (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_IQ3_XXS: result = quantize_iq3_xxs(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_IQ3_S:   result = quantize_iq3_s  (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_IQ2_S:   result = quantize_iq2_s  (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_IQ1_S:   result = quantize_iq1_s  (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_IQ4_NL:  result = quantize_iq4_nl (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
 #if QK_K == 64
-        case GGML_TYPE_IQ4_XS:
-#endif
-            {
-                GGML_ASSERT(start % QK4_NL == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_iq4_nl(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-#if QK_K != 64
-        case GGML_TYPE_IQ4_XS:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_iq4_xs(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
+        case GGML_TYPE_IQ4_XS:  result = quantize_iq4_nl (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+#else
+        case GGML_TYPE_IQ4_XS:  result = quantize_iq4_xs (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
 #endif
        case GGML_TYPE_F16:
            {
@@ -20105,6 +20228,9 @@ size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst, i
        default:
            assert(false);
    }
+
+    GGML_ASSERT(result == nrows * row_size);
+
    return result;
 }

@@ -472,6 +472,8 @@ extern "C" {
        GGML_OP_FLASH_ATTN,
        GGML_OP_FLASH_FF,
        GGML_OP_FLASH_ATTN_BACK,
+        GGML_OP_SSM_CONV,
+        GGML_OP_SSM_SCAN,
        GGML_OP_WIN_PART,
        GGML_OP_WIN_UNPART,
        GGML_OP_GET_REL_POS,
@@ -1728,6 +1730,23 @@ extern "C" {
            struct ggml_tensor  * c0,
            struct ggml_tensor  * c1);

+    GGML_API struct ggml_tensor * ggml_ssm_conv(
+            struct ggml_context * ctx,
+            struct ggml_tensor  * s,
+            struct ggml_tensor  * x,
+            struct ggml_tensor  * c,
+            struct ggml_tensor  * sq);
+
+    GGML_API struct ggml_tensor * ggml_ssm_scan(
+            struct ggml_context * ctx,
+            struct ggml_tensor  * s,
+            struct ggml_tensor  * x,
+            struct ggml_tensor  * dt,
+            struct ggml_tensor  * A,
+            struct ggml_tensor  * B,
+            struct ggml_tensor  * C,
+            struct ggml_tensor  * sq);
+
    // partition into non-overlapping windows with padding if needed
    // example:
    // a:   768   64   64    1
@@ -2175,25 +2194,18 @@ extern "C" {
    GGML_API void ggml_quantize_init(enum ggml_type type);
    GGML_API void ggml_quantize_free(void);

-    // TODO: these would probably get removed in favor of the more general ggml_quantize_chunk
-    GGML_API size_t ggml_quantize_q4_0(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_q4_1(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_q5_0(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_q5_1(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_q8_0(const float * src, void * dst, int n, int k, int64_t * hist);
-
-    GGML_API size_t ggml_quantize_q2_K(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_q3_K(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_q4_K(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_q5_K(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_q6_K(const float * src, void * dst, int n, int k, int64_t * hist);
-
    // some quantization type cannot be used without an importance matrix
    GGML_API bool ggml_quantize_requires_imatrix(enum ggml_type type);

    // calls ggml_quantize_init internally (i.e. can allocate memory)
-    GGML_API size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst,
-            int start, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
+    GGML_API size_t ggml_quantize_chunk(
+            enum ggml_type   type,
+               const float * src,
+                      void * dst,
+                       int   start,
+                       int   nrows,
+                       int   n_per_row,
+               const float * imatrix);

    //
    // gguf
@@ -61,6 +61,12 @@ class Keys:
        SCALING_ORIG_CTX_LEN = "{arch}.rope.scaling.original_context_length"
        SCALING_FINETUNED    = "{arch}.rope.scaling.finetuned"

+    class SSM:
+        CONV_KERNEL    = "{arch}.ssm.conv_kernel"
+        INNER_SIZE     = "{arch}.ssm.inner_size"
+        STATE_SIZE     = "{arch}.ssm.state_size"
+        TIME_STEP_RANK = "{arch}.ssm.time_step_rank"
+
    class Tokenizer:
        MODEL            = "tokenizer.ggml.model"
        LIST             = "tokenizer.ggml.tokens"
@@ -113,6 +119,7 @@ class MODEL_ARCH(IntEnum):
    MINICPM    = auto()
    GEMMA      = auto()
    STARCODER2 = auto()
+    MAMBA      = auto()


 class MODEL_TENSOR(IntEnum):
@@ -144,6 +151,13 @@ class MODEL_TENSOR(IntEnum):
    ATTN_Q_NORM     = auto()
    ATTN_K_NORM     = auto()
    LAYER_OUT_NORM  = auto()
+    SSM_IN          = auto()
+    SSM_CONV1D      = auto()
+    SSM_X           = auto()
+    SSM_DT          = auto()
+    SSM_A           = auto()
+    SSM_D           = auto()
+    SSM_OUT         = auto()


 MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
@@ -171,6 +185,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
    MODEL_ARCH.MINICPM:        "minicpm",
    MODEL_ARCH.GEMMA:          "gemma",
    MODEL_ARCH.STARCODER2:     "starcoder2",
+    MODEL_ARCH.MAMBA:          "mamba",
 }

 TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
@@ -202,6 +217,13 @@ TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
    MODEL_TENSOR.FFN_DOWN_EXP:    "blk.{bid}.ffn_down.{xid}",
    MODEL_TENSOR.FFN_UP_EXP:      "blk.{bid}.ffn_up.{xid}",
    MODEL_TENSOR.LAYER_OUT_NORM:  "blk.{bid}.layer_output_norm",
+    MODEL_TENSOR.SSM_IN:          "blk.{bid}.ssm_in",
+    MODEL_TENSOR.SSM_CONV1D:      "blk.{bid}.ssm_conv1d",
+    MODEL_TENSOR.SSM_X:           "blk.{bid}.ssm_x",
+    MODEL_TENSOR.SSM_DT:          "blk.{bid}.ssm_dt",
+    MODEL_TENSOR.SSM_A:           "blk.{bid}.ssm_a",
+    MODEL_TENSOR.SSM_D:           "blk.{bid}.ssm_d",
+    MODEL_TENSOR.SSM_OUT:         "blk.{bid}.ssm_out",
 }

 MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
@@ -543,6 +565,19 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
        MODEL_TENSOR.FFN_DOWN,
        MODEL_TENSOR.FFN_UP,
    ],
+    MODEL_ARCH.MAMBA: [
+        MODEL_TENSOR.TOKEN_EMBD,
+        MODEL_TENSOR.OUTPUT_NORM,
+        MODEL_TENSOR.OUTPUT,
+        MODEL_TENSOR.ATTN_NORM,
+        MODEL_TENSOR.SSM_IN,
+        MODEL_TENSOR.SSM_CONV1D,
+        MODEL_TENSOR.SSM_X,
+        MODEL_TENSOR.SSM_DT,
+        MODEL_TENSOR.SSM_A,
+        MODEL_TENSOR.SSM_D,
+        MODEL_TENSOR.SSM_OUT,
+    ],
    # TODO
 }

@@ -734,6 +769,12 @@ KEY_ROPE_SCALING_FACTOR       = Keys.Rope.SCALING_FACTOR
 KEY_ROPE_SCALING_ORIG_CTX_LEN = Keys.Rope.SCALING_ORIG_CTX_LEN
 KEY_ROPE_SCALING_FINETUNED    = Keys.Rope.SCALING_FINETUNED

+# SSM
+KEY_SSM_CONV_KERNEL    = Keys.SSM.CONV_KERNEL
+KEY_SSM_INNER_SIZE     = Keys.SSM.INNER_SIZE
+KEY_SSM_STATE_SIZE     = Keys.SSM.STATE_SIZE
+KEY_SSM_TIME_STEP_RANK = Keys.SSM.TIME_STEP_RANK
+
 # tokenization
 KEY_TOKENIZER_MODEL      = Keys.Tokenizer.MODEL
 KEY_TOKENIZER_LIST       = Keys.Tokenizer.LIST
@@ -382,6 +382,18 @@ class GGUFWriter:
    def add_rope_scaling_finetuned(self, value: bool) -> None:
        self.add_bool(Keys.Rope.SCALING_FINETUNED.format(arch=self.arch), value)

+    def add_ssm_conv_kernel(self, value: int) -> None:
+        self.add_uint32(Keys.SSM.CONV_KERNEL.format(arch=self.arch), value)
+
+    def add_ssm_inner_size(self, value: int) -> None:
+        self.add_uint32(Keys.SSM.INNER_SIZE.format(arch=self.arch), value)
+
+    def add_ssm_state_size(self, value: int) -> None:
+        self.add_uint32(Keys.SSM.STATE_SIZE.format(arch=self.arch), value)
+
+    def add_ssm_time_step_rank(self, value: int) -> None:
+        self.add_uint32(Keys.SSM.TIME_STEP_RANK.format(arch=self.arch), value)
+
    def add_tokenizer_model(self, model: str) -> None:
        self.add_string(Keys.Tokenizer.MODEL, model)

@@ -20,6 +20,9 @@ class TensorNameMap:
            "wte",                                       # gpt2
            "transformer.embd.wte",                      # phi2
            "model.tok_embeddings",                      # internlm2
+            "model.embedding",                           # mamba-qbert
+            "backbone.embedding",                        # mamba
+            "backbone.embeddings",                       # mamba-hf
        ),

        # Token type embeddings
@@ -44,7 +47,7 @@ class TensorNameMap:
        # Output
        MODEL_TENSOR.OUTPUT: (
            "embed_out",                 # gptneox
-            "lm_head",                   # gpt2 mpt falcon llama-hf baichuan qwen
+            "lm_head",                   # gpt2 mpt falcon llama-hf baichuan qwen mamba
            "output",                    # llama-pth bloom internlm2
            "word_embeddings_for_head",  # persimmon
            "lm_head.linear",            # phi2
@@ -61,6 +64,8 @@ class TensorNameMap:
            "language_model.encoder.final_layernorm",  # persimmon
            "model.final_layernorm",                   # persimmon
            "lm_head.ln",                              # phi2
+            "model.norm_f",                            # mamba-qbert
+            "backbone.norm_f",                         # mamba
        ),

        # Rope frequencies
@@ -86,6 +91,8 @@ class TensorNameMap:
            "transformer.h.{bid}.ln",                               # phi2
            "model.layers.layers.{bid}.norm",                       # plamo
            "model.layers.{bid}.attention_norm",                    # internlm2
+            "model.layers.{bid}.norm",                              # mamba-qbert
+            "backbone.layers.{bid}.norm",                           # mamba
        ),

        # Attention norm 2
@@ -282,7 +289,42 @@ class TensorNameMap:
        MODEL_TENSOR.LAYER_OUT_NORM: (
            "encoder.layer.{bid}.output.LayerNorm",  # bert
            "encoder.layers.{bid}.norm2",            # nomic-bert
-        )
+        ),
+
+        MODEL_TENSOR.SSM_IN: (
+            "model.layers.{bid}.in_proj",
+            "backbone.layers.{bid}.mixer.in_proj",
+        ),
+
+        MODEL_TENSOR.SSM_CONV1D: (
+            "model.layers.{bid}.conv1d",
+            "backbone.layers.{bid}.mixer.conv1d",
+        ),
+
+        MODEL_TENSOR.SSM_X: (
+            "model.layers.{bid}.x_proj",
+            "backbone.layers.{bid}.mixer.x_proj",
+        ),
+
+        MODEL_TENSOR.SSM_DT: (
+            "model.layers.{bid}.dt_proj",
+            "backbone.layers.{bid}.mixer.dt_proj",
+        ),
+
+        MODEL_TENSOR.SSM_A: (
+            "model.layers.{bid}.A_log",
+            "backbone.layers.{bid}.mixer.A_log",
+        ),
+
+        MODEL_TENSOR.SSM_D: (
+            "model.layers.{bid}.D",
+            "backbone.layers.{bid}.mixer.D",
+        ),
+
+        MODEL_TENSOR.SSM_OUT: (
+            "model.layers.{bid}.out_proj",
+            "backbone.layers.{bid}.mixer.out_proj",
+        ),
    }

    mapping: dict[str, tuple[MODEL_TENSOR, str]]
@@ -235,6 +235,7 @@ extern "C" {
        uint32_t seed;              // RNG seed, -1 for random
        uint32_t n_ctx;             // text context, 0 = from model
        uint32_t n_batch;           // prompt processing maximum batch size
+        uint32_t n_parallel;        // number of parallel sequences (i.e. distinct states for recurrent models)
        uint32_t n_threads;         // number of threads to use for generation
        uint32_t n_threads_batch;   // number of threads to use for batch processing

@@ -376,6 +377,7 @@ extern "C" {

    LLAMA_API uint32_t llama_n_ctx      (const struct llama_context * ctx);
    LLAMA_API uint32_t llama_n_batch    (const struct llama_context * ctx);
+    LLAMA_API uint32_t llama_n_max_seq  (const struct llama_context * ctx);

    LLAMA_API enum llama_vocab_type llama_vocab_type(const struct llama_model * model);
    LLAMA_API enum llama_rope_type  llama_rope_type (const struct llama_model * model);
@@ -502,7 +504,7 @@ extern "C" {
    // seq_id < 0 : match any sequence
    // p0 < 0     : [0,  p1]
    // p1 < 0     : [p0, inf)
-    LLAMA_API void llama_kv_cache_seq_rm(
+    LLAMA_API bool llama_kv_cache_seq_rm(
            struct llama_context * ctx,
                    llama_seq_id   seq_id,
                       llama_pos   p0,
@@ -94,6 +94,7 @@ if [ -f $SRC_LLAMA/ggml-src.patch ]; then
    # src/ggml-alloc.c            -> ggml-alloc.c
    # src/ggml-backend-impl.h     -> ggml-backend-impl.h
    # src/ggml-backend.c          -> ggml-backend.c
+    # src/ggml-common.h           -> ggml-common.h
    # src/ggml-cuda.cu            -> ggml-cuda.cu
    # src/ggml-cuda.h             -> ggml-cuda.h
    # src/ggml-impl.h             -> ggml-impl.h
@@ -126,6 +127,7 @@ if [ -f $SRC_LLAMA/ggml-src.patch ]; then
        -e 's/src\/ggml-alloc\.c/ggml-alloc.c/g' \
        -e 's/src\/ggml-backend-impl\.h/ggml-backend-impl.h/g' \
        -e 's/src\/ggml-backend\.c/ggml-backend.c/g' \
+        -e 's/src\/ggml-common\.h/ggml-common.h/g' \
        -e 's/src\/ggml-cuda\.cu/ggml-cuda.cu/g' \
        -e 's/src\/ggml-cuda\.h/ggml-cuda.h/g' \
        -e 's/src\/ggml-impl\.h/ggml-impl.h/g' \
@@ -4,6 +4,7 @@ cp -rpv ../ggml/src/ggml.c                  ./ggml.c
 cp -rpv ../ggml/src/ggml-alloc.c            ./ggml-alloc.c
 cp -rpv ../ggml/src/ggml-backend-impl.h     ./ggml-backend-impl.h
 cp -rpv ../ggml/src/ggml-backend.c          ./ggml-backend.c
+cp -rpv ../ggml/src/ggml-common.h           ./ggml-common.h
 cp -rpv ../ggml/src/ggml-cuda.cu            ./ggml-cuda.cu
 cp -rpv ../ggml/src/ggml-cuda.h             ./ggml-cuda.h
 cp -rpv ../ggml/src/ggml-impl.h             ./ggml-impl.h
@@ -1,3 +1,4 @@
 *
 !*.*
 *.o
+ggml-common.h
@@ -53,7 +53,6 @@ static void init_tensor_uniform(ggml_tensor * tensor, float min = -1.0f, float m
    } else if (ggml_is_quantized(tensor->type) || tensor->type == GGML_TYPE_F16) {
        GGML_ASSERT(size % ggml_blck_size(tensor->type) == 0);
        std::vector<uint8_t> dataq(ggml_row_size(tensor->type, size));
-        int64_t hist[16];
        std::vector<float> imatrix(tensor->ne[0], 1.0f); // dummy importance matrix
        const float * im = imatrix.data();
        if (!ggml_quantize_requires_imatrix(tensor->type)) {
@@ -63,7 +62,7 @@ static void init_tensor_uniform(ggml_tensor * tensor, float min = -1.0f, float m
                im = nullptr;
            }
        }
-        ggml_quantize_chunk(tensor->type, data.data(), dataq.data(), 0, size/tensor->ne[0], tensor->ne[0], hist, im);
+        ggml_quantize_chunk(tensor->type, data.data(), dataq.data(), 0, size/tensor->ne[0], tensor->ne[0], im);
        ggml_backend_tensor_set(tensor, dataq.data(), 0, dataq.size());
    } else if (tensor->type == GGML_TYPE_I8 || tensor->type == GGML_TYPE_I16 || tensor->type == GGML_TYPE_I32) {
        // This is going to create some weird integers though.
Author	SHA1	Message	Date
Georgi Gerganov	5b09797321	ggml : remove old quantization functions (#5942 ) * ggml : remove old quantization functions ggml-ci * ggml : simplify ggml_quantize_chunk ggml-ci * ggml : restrict correctness ggml-ci * ggml : remove hist data from the quantization API ggml-ci * tests : remove hist usage in test-backend-ops ggml-ci * vulkan : remove hist and fix typo	2024-03-09 15:53:59 +02:00
Georgi Gerganov	97c09585d6	server : clarify some items in the readme (#5957 ) * server : clarify some items in the readme * server : fix typo	2024-03-09 15:47:47 +02:00
SeungWon Jeong	fb215c3832	server : normalize embeddings (#5956 ) * output normalize embedding in '/v1/embeddings' * common : reuse llama_embd_normalize * common : better normalize impl --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-03-09 14:27:58 +02:00
Georgi Gerganov	2c4f566c88	tests : gitignore ggml-common.h	2024-03-09 14:17:11 +02:00
Alexey Parfenov	0db32beaf0	server : fix passing prompt as tokens (#5955 ) * server: fix passing prompt as tokens * Update examples/server/server.cpp --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-03-09 13:16:53 +02:00
Georgi Gerganov	8a3012a4ad	ggml : add ggml-common.h to deduplicate shared code (#5940 ) * ggml : add ggml-common.h to shared code ggml-ci * scripts : update sync scripts * sycl : reuse quantum tables ggml-ci * ggml : minor * ggml : minor * sycl : try to fix build	2024-03-09 12:47:57 +02:00
Georgi Gerganov	9674aaf35c	server : simplify logic for empty prompts (#5953 )	2024-03-09 12:34:18 +02:00
Xuan Son Nguyen	950ba1ab84	Server: reorganize some http logic (#5939 ) * refactor static file handler * use set_pre_routing_handler for validate_api_key * merge embedding handlers * correct http verb for endpoints * fix embedding response * fix test case CORS Options * fix code style	2024-03-09 11:27:53 +01:00
Gabe Goodhart	e1fa9569ba	server : add SSL support (#5926 ) * add cmake build toggle to enable ssl support in server Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * add flags for ssl key/cert files and use SSLServer if set All SSL setup is hidden behind CPPHTTPLIB_OPENSSL_SUPPORT in the same way that the base httlib hides the SSL support Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * Update readme for SSL support in server Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * Add LLAMA_SERVER_SSL variable setup to top-level Makefile Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> --------- Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>	2024-03-09 11:57:09 +02:00
Pierrick Hymbert	fd72d2d2a5	server: tests: add truncated prompt tests, better kv cache size (#5933 ) * server: tests: add truncated prompt tests, better size * server, tests : update regex --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-03-09 11:30:04 +02:00
compilade	c2101a2e90	llama : support Mamba Selective State Space Models (#5328 ) * mamba : begin working on support for Mamba SSM * mamba : begin figuring out how to (ab)use the kv cache for Mamba * mamba : recurrent inference almost works, but incoherent * mamba : recurrent inference WORKS!!! * convert : optionally use d_conv and d_state from config.json for Mamba * mamba : refactor recurrent conv, resulting in 20% perf increase It's still slower than I'd like, but I did not really optimize `ggml_exp` yet. I also refactored `ggml_exp` to work with tensors with more than 2 dimensions. * ggml : parallelize ggml_exp This results in 8% faster token generation for Mamba-130M. * mamba : simplify the conv step with a self-overlapping view Turns out the conv_state can be made smaller by one column. Note that this breaks existing GGUFs of Mamba, because the key_value_length field is tied to the conv_state size. Convolution with a self-overlapping view is cool! And it's much simpler than what I initially thought would be necessary to make the convolution step work with more than 1 token at a time. Next step is to make the SSM step work on batches of tokens too, and thus I need to figure out a way to make a parallel selective scan which will keep the ssm_state small and won't make it bigger by a factor of (n_layer * batch_size). * llama : fix Mamba KV self size wrongly displaying as f16 instead of f32 Relatedly, I also tried to see if other types than f32 worked for the states, but they don't, because of the operators used. It's probably better anyway to keep lots of precision there, since the states are small anyway. * mamba : fix self-overlapping view depth stride * mamba : handle batches of more than 1 token This means running Mamba no longer crashes when using the default settings! And probably also slightly faster prompt processing. Both batched and non-batched processing yield the same output. Previously, the state was not cleared when starting a sequence. Next step is to make the KV cache API work as expected for Mamba models. * ggml: add ggml_ssm_scan to help with parallel selective scan If the selective scan was implemented without a custom operator, there would be waaay too many nodes in the graph. For example, for Mamba-130M, with a batch size of 512 (the default), a naive selective scan could add at least 24512=12288 nodes, which is more than LLAMA_MAX_NODES (8192), and that's only for the smallest Mamba model. So it's much cleaner with a custom operator. Not sure about the name, though. ggml : in ggml_ssm_scan, merge multiple rows in the same vec operation This will help with performance on CPU if ggml_vec_mul_f32 and ggml_vec_add_f32 are ever optimized with SIMD. * mamba : very basic quantization support Mostly works, but there is currently no difference between the variants of a k-quant (e.g. Q4_K_S and Q4_K_M are the same). Most of the SSM-specific weights can be kept in f32 without affecting the size that much, since they are relatively small. (the linear projection weights are responsible for most of Mamba's size) Too much quantization seems to make the state degrade quite fast, and the model begins to output gibberish. It seems to affect bigger models to a lesser extent than small models, but I'm not sure by how much. Experimentation will be needed to figure out which weights are more important for the _M (and _L?) variants of k-quants for Mamba. * convert : fix wrong name for layer norm weight of offical Mamba models I was using Q-bert/Mamba-* models before, which have a slighlty different naming scheme for the weights. (they start with "model.layers" instead of "backbone.layers") * mamba : fuse more steps of the SSM scan in the ggml_ssm_scan operator This increases performance on CPU by around 30% for prompt processing, and by around 20% for text generation. However, it also makes the ggml_exp and ggml_soft_plus operators unused. Whether or not they should be kept will be decided later. * convert : for Mamba, also consider the "MambaLMHeadModel" arch name It's the name of the class of the official implementation, though they don't use it (yet) in the "architectures" field of config.json * mamba : fix vocab size problems with official models The perplexity was waaaay to high for models with a non-round vocab size. Not sure why, but it needed to be fixed in the metadata. Note that this breaks existing GGUF-converted Mamba models, but only if the vocab size was not already rounded. * ggml : remove ggml_exp and ggml_soft_plus They did not exist anyway outside of this branch, and since ggml_ssm_scan fused operations together, they are unused. It's always possible to bring them back if needed. * mamba : remove some useless comments No code change. * convert : fix flake8 linter errors * mamba : apply suggestions from code review * mamba : remove unecessary branch for row-wise ssm_state and C multiplication It was previously done to avoid permuting when only one token is processed at a time (like when generating text), but permuting is cheap, and dynamically changing the compute graph is not future-proof. * ggml : in ggml_ssm_scan, use more appropriate asserts * ggml : rename the destination pointer in ggml_compute_forward_ssm_scan_f32 * mamba : multiple sequences, but one at a time This is a step towards making this Mamba implementation usable with the server example (the way the system prompt is kept when clearing the client slots will need to be changed before this can work, though). The KV cache size for this kind of model is tied to the maximum number of sequences kept at any single time. For now, this number is obtained from n_parallel (plus one, to have an extra sequence to dedicate to the system prompt), but there might be a better way to do this which won't also make the main example use 2 cells even if only 1 is really used. (for this specific case, --parallel 0 helps) Simultaneous sequence processing will probably require changes to ggml_ssm_scan, and possibly a new operator for the conv step. * mamba : support llama_kv_cache_seq_cp This (mis)uses the logic around K shifts, because tokens in a state can't be shifted anyway, and because inp_K_shift has the right shape and type. Using ggml_get_rows is a nice way to do copies, but copy chains can't work. Fortunately, copy chains don't really seem to be used in the examples. Each KV cell is dedicated to the sequence ID corresponding to its own index. * mamba : use a state mask It's cleaner than the previous heuristic of checking for the pos of the first token in the batch. inp_KQ_mask could not be re-used for this, because it has the wrong shape and because it seems more suited to the next step of simultaneous sequence processing (helping with the problem of remembering which token belongs to which sequence(s)/state(s)). * llama : replace the usage of n_ctx with kv_self.size in many places * mamba : use n_tokens directly instead of n_tok * mamba : in comments, properly refer to KV cells instead of slots * mamba : reduce memory usage of ggml_ssm_scan From 290.37 MiB to 140.68 MiB of CPU compute buffer size with Mamba 3B with a batch size of 512. The result tensor of ggml_ssm_scan was previously a big part of the CPU compute buffer size. To make it smaller, it does not contain the intermediate ssm states anymore. Both y and the last ssm state are combined in the result tensor, because it seems only a single tensor can be returned by an operator with the way the graph is built. * mamba : simultaneous sequence processing A batch can now contain tokens from multiple sequences. This is necessary for at least the parallel example, the server example, and the HellaSwag test in the perplexity example. However, for this to be useful, uses of llama_kv_cache_seq_rm/cp will need to be changed to work on whole sequences. * ggml : add ggml_ssm_conv as a new operator for the conv step of Mamba This operator makes it possible to use and update the correct states for each token of the batch in the same way as ggml_ssm_scan. Other solutions which use existing operators would need loops which would add too many nodes to the graph (at least the ones I thought of). Using this operator further reduces the size of the CPU compute buffer from 140.68 MiB to 103.20 MiB with Mamba 3B with a batch size of 512. And (at least on CPU), it's a bit faster than before. Note that "ggml_ssm_conv" is probably not the most appropriate name, and it could be changed if a better one is found. * llama : add inp_s_seq as a new input tensor The most convenient implementation to select the correct state (for Mamba) for each token is to directly get the correct index from a tensor. This is why inp_s_seq is storing int32_t and not floats. The other, less convenient way to select the correct state would be to have inp_KQ_mask contain 1.0f for each state used by a token and 0.0f otherwise. This complicates quickly fetching the first used state of a token, and is also less efficient because a whole row of the mask would always need to be read for each token. Using indexes makes it easy to stop searching when there are no more sequences for a token, and the first sequence assigned is always very quickly available (it's the first element of each row). * mamba : support llama_kv_cache_seq_cp copy chains * mamba : support shifting and dividing the kv cache pos * mamba : make the server and parallel examples work with whole sequences A seq_id is dedicated to the system prompt in both cases. * llama : make llama_kv_cache_seq_rm return whether it succeeded or not * mamba : dedicate an input tensor for state copy indices This is cleaner and makes it easier to adapt when/if token positions (and by extension, inp_K_shift) are no longer integers. * mamba : adapt perplexity, batched, and batched-bench examples * perplexity : limit the max number of sequences This adapts to what the loaded model can provide. * llama : add llama_n_max_seq to get the upper limit for seq_ids Used by the perplexity example. * batched : pass n_parallel to the model's context params This should have been there already, but it wasn't. * batched-bench : reserve sequences to support Mamba * batched-bench : fix tokens being put in wrong sequences Generation quality isn't what's measured in there anyway, but at least using the correct sequences avoids using non-consecutive token positions. * mamba : stop abusing attention metadata This breaks existing converted-to-GGUF Mamba models, but will allow supporting mixed architectures like MambaFormer without needing to break Mamba models. This will also allow changing the size of Mamba's states without having to reconvert models in the future. (e.g. using something else than d_conv - 1 columns for the conv_states will not require breaking existing converted Mamba models again) * gguf-py : add new KV metadata key-value pairs for Mamba * llama : add new metadata key-value pairs for Mamba * llama : guard against divisions by zero when n_head is 0 * mamba : rename "unlimited" KV cache property to "recurrent" * mamba : more correctly update the "used" field of the KV cache * ggml : in ggml_ssm_scan, use a threshold for soft_plus This is how the official Mamba implementation does it, and it's also what torch.nn.Softplus does. * convert : for Mamba, fallback to internal NeoX tokenizer The resulting models are exactly the same as if the tokenizer.json and tokenizer_config.json of GPT-NeoX were there. * mamba : support state saving and restoring * ggml : implicitly pass src tensors through dst for Mamba-related ops * mamba : clarify some comments * server : fix cache_tokens not getting correctly resized Otherwise, when the "we have to evaluate at least 1 token" special case was triggered, an extra token was kept in cache_tokens even if it was removed from the KV cache. For Mamba, this caused useless prompt reprocessing when the previous request triggered the above case. * convert-hf : support new metadata keys for Mamba For the models available at https://huggingface.co/collections/state-spaces/transformers-compatible-mamba-65e7b40ab87e5297e45ae406 * mamba : rename metadata to be more similar to transformers library This breaks existing converted-to-GGUF models, but the metadata names are more "standard". * mamba : support mamba--hf models These models share their token_embd.weight with their output.weight mamba : add missing spaces This is purely a formatting change. * convert-hf : omit output.weight when identical with token_embd.weight Only for Mamba for now, but it might be relevant for other models eventually. Most Mamba models actually share these two tensors, albeit implicitly. * readme : add Mamba to supported models, and add recent API changes * mamba : move state_seq and state_mask views outside layer loop A few tensors were also missing `struct` in front of `ggml_tensor`.	2024-03-08 17:31:00 -05:00
compilade	515f7d0d4f	llama : fix quantization of shared token_embd (#5944 )	2024-03-08 17:53:37 +02:00
Pierrick Hymbert	76e868821a	server: metrics: add llamacpp:prompt_seconds_total and llamacpp:tokens_predicted_seconds_total, reset bucket only on /metrics. Fix values cast to int. Add Process-Start-Time-Unix header. (#5937 ) Closes #5850	2024-03-08 12:25:04 +01:00
Don Mahurin	e457fb3540	llama : assume tied weights if lm_head/output weights is missing (#5824 ) This is to support model configurations with "tie_word_embeddings" set to true. Co-authored-by: Don Mahurin <2797413+dmahurin@users.noreply.github.com>	2024-03-08 12:41:50 +02:00
Georgi Gerganov	af37fd8b30	server : fix EOS token detection with disabled cache (#5938 )	2024-03-08 12:40:02 +02:00
UEXTM.com	581ed5c4fe	log : fix MSVC compile errors (#5643 ) MSVC gives the following error with the existing macros: `Error C2059 : syntax error: ','` This patch adds `##` as a prefix to `__VA_ARGS__` to address this error.	2024-03-08 11:35:04 +02:00
Georgi Gerganov	6cdabe6526	llama-bench : add embeddings option (#5924 ) * llama-bench : add embeddings option * llama-bench : do not hard code embd default value --------- Co-authored-by: slaren <slarengh@gmail.com>	2024-03-07 16:32:38 +02:00
Neo Zhang Jianyu	89fb735fcf	Revert "[SYCL] fix error when set main gpu to non-zero (#5901 )" (#5918 ) This reverts commit `ceca1aef07`.	2024-03-07 12:14:49 +01:00