Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.devops/full-cuda.Dockerfile
#	.devops/llama-cli-cuda.Dockerfile
#	.devops/llama-server-cuda.Dockerfile
#	.devops/llama-server-intel.Dockerfile
#	.devops/llama-server-rocm.Dockerfile
#	.devops/llama-server-vulkan.Dockerfile
#	.devops/llama-server.Dockerfile
#	.github/workflows/docker.yml
#	docs/docker.md
#	examples/llama-bench/llama-bench.cpp
#	flake.lock
#	ggml/include/ggml.h
#	ggml/src/CMakeLists.txt
#	scripts/sync-ggml.last
#	src/llama.cpp
#	tests/test-backend-ops.cpp
#	tests/test-grad0.cpp
#	tests/test-rope.cpp

examples/baby-llama/baby-llama.cpp

@@ -18,7 +18,7 @@ constexpr float rms_norm_eps = 5e-6f;
 #endif
 
 static void ggml_graph_compute_helper(std::vector<uint8_t> & buf, ggml_cgraph * graph, int n_threads) {
-    struct ggml_cplan plan = ggml_graph_plan(graph, n_threads);
+    struct ggml_cplan plan = ggml_graph_plan(graph, n_threads, nullptr);
 
     if (plan.work_size > 0) {
         buf.resize(plan.work_size);

examples/benchmark/benchmark-matmult.cpp

@@ -22,7 +22,7 @@
 #endif
 
 static void ggml_graph_compute_helper(std::vector<uint8_t> & buf, ggml_cgraph * graph, int n_threads) {
-    struct ggml_cplan plan = ggml_graph_plan(graph, n_threads);
+    struct ggml_cplan plan = ggml_graph_plan(graph, n_threads, nullptr);
 
     if (plan.work_size > 0) {
         buf.resize(plan.work_size);
@@ -55,7 +55,7 @@ static void tensor_dump(const ggml_tensor * tensor, const char * name) {
 #define TENSOR_DUMP(tensor) tensor_dump(tensor, #tensor)
 
 struct benchmark_params_struct {
-    int32_t n_threads     = 1;
+    int     n_threads     = 1;
     int32_t n_iterations  = 10;
 };
 

examples/cvector-generator/cvector-generator.cpp

@@ -486,8 +486,8 @@ int main(int argc, char ** argv) {
     if (use_pca) {
         // run PCA
         PCA::pca_params pca_params;
-        pca_params.n_threads = params.n_threads;
-        pca_params.n_batch = params.n_pca_batch;
+        pca_params.n_threads    = params.cpuparams.n_threads;
+        pca_params.n_batch      = params.n_pca_batch;
         pca_params.n_iterations = params.n_pca_iterations;
         PCA::run_pca(pca_params, ctx_train.v_diff, ctx_train.v_final);
     } else {

examples/export-lora/export-lora.cpp

@@ -410,7 +410,7 @@ int main(int argc, char ** argv) {
 
     g_verbose = (params.verbosity == 1);
     try {
-        lora_merge_ctx ctx(params.model, params.lora_adapters, params.lora_outfile, params.n_threads);
+        lora_merge_ctx ctx(params.model, params.lora_adapters, params.lora_outfile, params.cpuparams.n_threads);
         ctx.run_merge();
     } catch (const std::exception & err) {
         fprintf(stderr, "%s\n", err.what());

examples/llama.swiftui/llama.cpp.swift/LibLlama.swift

@@ -71,8 +71,8 @@ actor LlamaContext {
         var ctx_params = llama_context_default_params()
         ctx_params.seed  = 1234
         ctx_params.n_ctx = 2048
-        ctx_params.n_threads       = UInt32(n_threads)
-        ctx_params.n_threads_batch = UInt32(n_threads)
+        ctx_params.n_threads       = Int32(n_threads)
+        ctx_params.n_threads_batch = Int32(n_threads)
 
         let context = llama_new_context_with_model(model, ctx_params)
         guard let context else {

examples/llava/README-minicpmv2.5.md

@@ -15,8 +15,8 @@ cd llama.cpp
 Convert PyTorch model to gguf files (You can also download the converted [gguf](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5-gguf) by us)
 
 ```bash
-python ./examples/minicpmv/minicpmv-surgery.py -m ../MiniCPM-Llama3-V-2_5
-python ./examples/minicpmv/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-Llama3-V-2_5 --minicpmv-projector ../MiniCPM-Llama3-V-2_5/minicpmv.projector --output-dir ../MiniCPM-Llama3-V-2_5/ --image-mean 0.5 0.5 0.5 --image-std 0.5 0.5 0.5 --minicpmv_version 2
+python ./examples/llava/minicpmv-surgery.py -m ../MiniCPM-Llama3-V-2_5
+python ./examples/llava/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-Llama3-V-2_5 --minicpmv-projector ../MiniCPM-Llama3-V-2_5/minicpmv.projector --output-dir ../MiniCPM-Llama3-V-2_5/ --image-mean 0.5 0.5 0.5 --image-std 0.5 0.5 0.5 --minicpmv_version 2
 python ./convert_hf_to_gguf.py ../MiniCPM-Llama3-V-2_5/model
 
 # quantize int4 version

examples/llava/llava-cli.cpp

@@ -129,14 +129,14 @@ static struct llava_image_embed * load_image(llava_context * ctx_llava, gpt_para
         if (!params->image.empty()) {
             LOG_TEE("using base64 encoded image instead of command line image path\n");
         }
-        embed = llava_image_embed_make_with_prompt_base64(ctx_llava->ctx_clip, params->n_threads, prompt);
+        embed = llava_image_embed_make_with_prompt_base64(ctx_llava->ctx_clip, params->cpuparams.n_threads, prompt);
         if (!embed) {
             LOG_TEE("%s: can't load image from prompt\n", __func__);
             return NULL;
         }
         params->prompt = remove_image_from_prompt(prompt);
     } else {
-        embed = llava_image_embed_make_with_filename(ctx_llava->ctx_clip, params->n_threads, fname.c_str());
+        embed = llava_image_embed_make_with_filename(ctx_llava->ctx_clip, params->cpuparams.n_threads, fname.c_str());
         if (!embed) {
             fprintf(stderr, "%s: is %s really an image file?\n", __func__, fname.c_str());
             return NULL;

examples/llava/minicpmv-cli.cpp

@@ -180,7 +180,7 @@ static const char * sample(struct llama_sampling_context * ctx_sampling,
 
 static struct llava_context * minicpmv_init(gpt_params * params, const std::string & fname, int &n_past){
     auto ctx_clip = clip_init_context(params);
-    auto embeds = llava_image_embed_make_with_filename(ctx_clip, params->n_threads, fname.c_str());
+    auto embeds = llava_image_embed_make_with_filename(ctx_clip, params->cpuparams.n_threads, fname.c_str());
     if (!embeds) {
         std::cerr << "error: failed to load image " << fname << ". Terminating\n\n";
         return NULL;

examples/main/main.cpp

@@ -222,6 +222,40 @@ int main(int argc, char ** argv) {
         return 1;
     }
 
+    LOG("%s: llama threadpool init = n_threads = %d\n",
+        __func__,
+        (int) params.cpuparams.n_threads
+    );
+    struct ggml_threadpool_params tpp_batch =
+            ggml_threadpool_params_from_cpu_params(params.cpuparams_batch);
+    struct ggml_threadpool_params tpp =
+            ggml_threadpool_params_from_cpu_params(params.cpuparams);
+
+    set_process_priority(params.cpuparams.priority);
+
+    struct ggml_threadpool * threadpool_batch = NULL;
+    if (!ggml_threadpool_params_match(&tpp, &tpp_batch)) {
+        threadpool_batch = ggml_threadpool_new(&tpp_batch);
+        if (!threadpool_batch) {
+            LOG_TEE("%s: batch threadpool create failed : n_threads %d\n", __func__, tpp_batch.n_threads);
+            exit(1);
+        }
+
+        // Start the non-batch threadpool in the paused state
+        tpp.paused = true;
+    }
+
+    struct ggml_threadpool * threadpool = ggml_threadpool_new(&tpp);
+    if (!threadpool) {
+        LOG_TEE("%s: threadpool create failed : n_threads %d\n", __func__, tpp.n_threads);
+        exit(1);
+    }
+
+    llama_attach_threadpool(ctx, threadpool, threadpool_batch);
+    if (ctx_guidance) {
+        llama_attach_threadpool(ctx_guidance, threadpool, threadpool_batch);
+    }
+
     const int n_ctx_train = llama_n_ctx_train(model);
     const int n_ctx = llama_n_ctx(ctx);
     LOG("n_ctx: %d\n", n_ctx);
@@ -990,6 +1024,9 @@ int main(int argc, char ** argv) {
     llama_sampling_free(ctx_sampling);
     llama_backend_free();
 
+    ggml_threadpool_free(threadpool);
+    ggml_threadpool_free(threadpool_batch);
+
 #ifndef LOG_DISABLE_LOGS
     LOG_TEE("Log end\n");
 #endif // LOG_DISABLE_LOGS

examples/server/README.md

@@ -249,23 +249,49 @@ logging:
 
 Available environment variables (if specified, these variables will override parameters specified in arguments):
 
-- `LLAMA_CACHE` (cache directory, used by `--hf-repo`)
-- `HF_TOKEN` (Hugging Face access token, used when accessing a gated model with `--hf-repo`)
-- `LLAMA_ARG_MODEL`
-- `LLAMA_ARG_THREADS`
-- `LLAMA_ARG_CTX_SIZE`
-- `LLAMA_ARG_N_PARALLEL`
-- `LLAMA_ARG_BATCH`
-- `LLAMA_ARG_UBATCH`
-- `LLAMA_ARG_N_GPU_LAYERS`
-- `LLAMA_ARG_THREADS_HTTP`
-- `LLAMA_ARG_CHAT_TEMPLATE`
-- `LLAMA_ARG_N_PREDICT`
-- `LLAMA_ARG_ENDPOINT_METRICS`
-- `LLAMA_ARG_ENDPOINT_SLOTS`
-- `LLAMA_ARG_EMBEDDINGS`
-- `LLAMA_ARG_FLASH_ATTN`
-- `LLAMA_ARG_DEFRAG_THOLD`
+- `LLAMA_CACHE`: cache directory, used by `--hf-repo`
+- `HF_TOKEN`: Hugging Face access token, used when accessing a gated model with `--hf-repo`
+- `LLAMA_ARG_MODEL`: equivalent to `-m`
+- `LLAMA_ARG_MODEL_URL`: equivalent to `-mu`
+- `LLAMA_ARG_MODEL_ALIAS`: equivalent to `-a`
+- `LLAMA_ARG_HF_REPO`: equivalent to `--hf-repo`
+- `LLAMA_ARG_HF_FILE`: equivalent to `--hf-file`
+- `LLAMA_ARG_THREADS`: equivalent to `-t`
+- `LLAMA_ARG_CTX_SIZE`: equivalent to `-c`
+- `LLAMA_ARG_N_PARALLEL`: equivalent to `-np`
+- `LLAMA_ARG_BATCH`: equivalent to `-b`
+- `LLAMA_ARG_UBATCH`: equivalent to `-ub`
+- `LLAMA_ARG_N_GPU_LAYERS`: equivalent to `-ngl`
+- `LLAMA_ARG_THREADS_HTTP`: equivalent to `--threads-http`
+- `LLAMA_ARG_CHAT_TEMPLATE`: equivalent to `--chat-template`
+- `LLAMA_ARG_N_PREDICT`: equivalent to `-n`
+- `LLAMA_ARG_ENDPOINT_METRICS`: if set to `1`, it will enable metrics endpoint (equivalent to `--metrics`)
+- `LLAMA_ARG_ENDPOINT_SLOTS`: if set to `0`, it will **disable** slots endpoint (equivalent to `--no-slots`). This feature is enabled by default.
+- `LLAMA_ARG_EMBEDDINGS`: if set to `1`, it will enable embeddings endpoint (equivalent to `--embeddings`)
+- `LLAMA_ARG_FLASH_ATTN`: if set to `1`, it will enable flash attention (equivalent to `-fa`)
+- `LLAMA_ARG_CONT_BATCHING`: if set to `0`, it will **disable** continuous batching (equivalent to `--no-cont-batching`). This feature is enabled by default.
+- `LLAMA_ARG_DEFRAG_THOLD`: equivalent to `-dt`
+- `LLAMA_ARG_HOST`: equivalent to `--host`
+- `LLAMA_ARG_PORT`: equivalent to `--port`
+
+Example usage of docker compose with environment variables:
+
+```yml
+services:
+  llamacpp-server:
+    image: ghcr.io/ggerganov/llama.cpp:server
+    ports:
+      - 8080:8080
+    volumes:
+      - ./models:/models
+    environment:
+      # alternatively, you can use "LLAMA_ARG_MODEL_URL" to download the model
+      LLAMA_ARG_MODEL: /models/my_model.gguf
+      LLAMA_ARG_CTX_SIZE: 4096
+      LLAMA_ARG_N_PARALLEL: 2
+      LLAMA_ARG_ENDPOINT_METRICS: 1  # to disable, either remove or set to 0
+      LLAMA_ARG_PORT: 8080
+```
 
 ## Build
 

examples/server/server.cpp

@@ -2535,8 +2535,8 @@ int main(int argc, char ** argv) {
     });
 
     LOG_INFO("system info", {
-        {"n_threads",       params.n_threads},
-        {"n_threads_batch", params.n_threads_batch},
+        {"n_threads",       params.cpuparams.n_threads},
+        {"n_threads_batch", params.cpuparams_batch.n_threads},
         {"total_threads",   std::thread::hardware_concurrency()},
         {"system_info",     llama_print_system_info()},
     });
@@ -2573,7 +2573,7 @@ int main(int argc, char ** argv) {
 
     auto res_error = [](httplib::Response & res, json error_data) {
         json final_response {{"error", error_data}};
-        res.set_content(final_response.dump(), MIMETYPE_JSON);
+        res.set_content(final_response.dump(-1, ' ', false, json::error_handler_t::replace), MIMETYPE_JSON);
         res.status = json_value(error_data, "code", 500);
     };
 

examples/speculative/speculative.cpp

@@ -75,10 +75,11 @@ int main(int argc, char ** argv) {
     // load the draft model
     params.model = params.model_draft;
     params.n_gpu_layers = params.n_gpu_layers_draft;
-    if (params.n_threads_draft > 0) {
-        params.n_threads = params.n_threads_draft;
+    if (params.draft_cpuparams.n_threads > 0) {
+        params.cpuparams.n_threads = params.draft_cpuparams.n_threads;
     }
-    params.n_threads_batch = params.n_threads_batch_draft;
+
+    params.cpuparams_batch.n_threads = params.draft_cpuparams_batch.n_threads;
     llama_init_result llama_init_dft = llama_init_from_gpt_params(params);
     model_dft = llama_init_dft.model;
     ctx_dft = llama_init_dft.context;