Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	AGENTS.md
#	CODEOWNERS
#	CONTRIBUTING.md
#	docs/backend/OPENCL.md
#	docs/development/HOWTO-add-model.md
#	examples/training/finetune.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp-drv.cpp
#	ggml/src/ggml-hexagon/htp/act-ops.c
#	ggml/src/ggml-hexagon/htp/dma-queue.c
#	ggml/src/ggml-hexagon/htp/dma-queue.h
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.h
#	ggml/src/ggml-hexagon/htp/hmx-mm-kernels-tiled.h
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/htp-tensor.c
#	ggml/src/ggml-hexagon/htp/htp-tensor.h
#	ggml/src/ggml-hexagon/htp/hvx-fa-kernels.h
#	ggml/src/ggml-hexagon/htp/hvx-reduce.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.h
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-hexagon/htp/unary-ops.h
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	scripts/compare-llama-bench.py
#	scripts/snapdragon/ggml-hexagon-profile.py
#	scripts/snapdragon/ggml-hexagon-trace.py
#	scripts/sync_vendor.py
#	tests/test-arg-parser.cpp
#	tests/test-chat.cpp
#	tests/test-model-load-cancel.cpp
#	tests/test-quantize-stats.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/server/README.md
#	tools/ui/src/lib/constants/settings-registry.ts

src/llama.cpp

@@ -66,6 +66,28 @@ const char * llama_flash_attn_type_name(enum llama_flash_attn_type flash_attn_ty
     GGML_ABORT("fatal error");
 }
 
+const char * llama_load_mode_name(enum llama_load_mode load_mode) {
+    switch (load_mode) {
+        case LLAMA_LOAD_MODE_NONE:
+            return "none";
+        case LLAMA_LOAD_MODE_MMAP:
+            return "mmap";
+        case LLAMA_LOAD_MODE_MLOCK:
+            return "mlock";
+        case LLAMA_LOAD_MODE_DIRECT_IO:
+            return "dio";
+    }
+    GGML_ABORT("fatal error");
+}
+
+enum llama_load_mode llama_load_mode_from_str(const char * str) {
+    if (std::strcmp(str, "none")  == 0) { return LLAMA_LOAD_MODE_NONE;      }
+    if (std::strcmp(str, "mmap")  == 0) { return LLAMA_LOAD_MODE_MMAP;      }
+    if (std::strcmp(str, "mlock") == 0) { return LLAMA_LOAD_MODE_MLOCK;     }
+    if (std::strcmp(str, "dio")   == 0) { return LLAMA_LOAD_MODE_DIRECT_IO; }
+    throw std::invalid_argument(std::string("unknown load mode: ") + str);
+}
+
 struct llama_sampler_chain_params llama_sampler_chain_default_params() {
     struct llama_sampler_chain_params result = {
         /*.no_perf =*/ true,
@@ -299,7 +321,7 @@ static bool llama_prepare_model_devices(const llama_model_params & params, llama
 static std::pair<int, llama_model *> llama_model_load(struct gguf_context * metadata, llama_model_set_tensor_data_t set_tensor_data, void * set_tensor_data_ud,
         const std::string & fname, std::vector<std::string> & splits, FILE * file, llama_model_params & params) {
     try {
-        llama_model_loader ml(metadata, set_tensor_data, set_tensor_data_ud, fname, splits, file, params.use_mmap, params.use_direct_io,
+        llama_model_loader ml(metadata, set_tensor_data, set_tensor_data_ud, fname, splits, file, params.load_mode,
             params.check_tensors, params.no_alloc, params.kv_overrides, params.tensor_buft_overrides);
 
         ml.print_info();
@@ -432,7 +454,7 @@ struct llama_model * llama_model_init_from_user(
     GGML_ASSERT(metadata != nullptr);
     std::string path_model;
     std::vector<std::string> splits = {};
-    params.use_mmap = false;
+    params.load_mode = LLAMA_LOAD_MODE_NONE;
     params.use_extra_bufts = false;
     return llama_model_load_from_file_impl(metadata, set_tensor_data, set_tensor_data_ud, path_model, splits, /*file*/ nullptr, params);
 }