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

include/llama.h

@@ -205,6 +205,16 @@ extern "C" {
         LLAMA_SPLIT_MODE_TENSOR = 3,
     };
 
+    enum llama_load_mode {
+        LLAMA_LOAD_MODE_NONE      = 0, // no special loading mode
+        LLAMA_LOAD_MODE_MMAP      = 1, // memory map the model
+        LLAMA_LOAD_MODE_MLOCK     = 2, // mmap + force system to keep model in RAM rather than swapping or compressing
+        LLAMA_LOAD_MODE_DIRECT_IO = 3, // use direct I/O if available
+    };
+
+    LLAMA_API const char * llama_load_mode_name(enum llama_load_mode load_mode);
+    LLAMA_API enum llama_load_mode llama_load_mode_from_str(const char * str);
+
     enum llama_context_type {
         LLAMA_CONTEXT_TYPE_DEFAULT = 0,
         LLAMA_CONTEXT_TYPE_MTP     = 1,
@@ -304,6 +314,7 @@ extern "C" {
 
         int32_t n_gpu_layers; // number of layers to store in VRAM, a negative value means all layers
         enum llama_split_mode split_mode; // how to split the model across multiple GPUs
+        enum llama_load_mode  load_mode;  // how to load the model
 
         // the GPU that is used for the entire model when split_mode is LLAMA_SPLIT_MODE_NONE
         int32_t main_gpu;
@@ -324,9 +335,6 @@ extern "C" {
 
         // Keep the booleans together to avoid misalignment during copy-by-value.
         bool vocab_only;      // only load the vocabulary, no weights
-        bool use_mmap;        // use mmap if possible
-        bool use_direct_io;   // use direct io, takes precedence over use_mmap when supported
-        bool use_mlock;       // force system to keep model in RAM
         bool check_tensors;   // validate model tensor data
         bool use_extra_bufts; // use extra buffer types (used for weight repacking)
         bool no_host;         // bypass host buffer allowing extra buffers to be used