mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-06-28 04:30:15 -05:00
72440a19fc
* host-swap tensor loop the host-swap functionality is only triggered when the certain env. variables are declared * target_include_directories tweak * hot-swap tensor support two intrusions: 1.) at the model loading to collect the snapshot 2.) the modification of the `/health` HTTP endpoint to be able to trigger the hot-swap via sending the `llama-server` the HTTP-request. *both a braced by the specific env. variables * hot-swap tensor support; graph invalidation ggml_backend_cuda_invalidate_graphs export * hot-swap tensor support graph invalidation implementation; extended debug output (commented out) * llama_reload_changed_tensors export * tensor hot-swap on-demand reload cpu-only/hybrid/gpu-only with split mode layer/graph full support implementation * docs * reuse the gguf parsing from llama.cpp gguf_init_from_file, gguf_find_tensor, ggml_get_tensor * remove the manual scheduling for hybrid inference * update docs * tensor shape validation * update docs * update docs accidentally wiped the previous changes; so recovered them * revert the GGML_CUDA_MAX_DEVICES to 16 * update llama_reload_changed_tensor update llama_reload_changed_tensor, revert CMakeLists.txt * update llama_reload_changed_tensor * GGML_MAX_SRC GGML_MAX_SRC compile-time definition support * GGML_MAX_SRC GGML_MAX_SRC compile-time definition support * GGML_MAX_SRC GGML_MAX_SRC compile-time definition support * llama_reload_changed_tensor update llama_reload_changed_tensor definition * refactory move the tensor-reloading implementation to llama-reload.cpp, llama-reload-info.h; some bugfixes and code reduction * revert added back the missing newline * update docs * reload_info constructor * bugfix: cpu-only TODO: improve the working environment by compiling for multiple hardware configurations; possibly make a test pipeline * cpu-only bugfix set the fix again after unsuccessful sync with main * windows os compilation fix #include <string> * fix windows os build error C2039: 'string': is not a member of 'std' * remove dead file * implement perplexity in server * Revert "implement perplexity in server"
50 lines
1.7 KiB
C
50 lines
1.7 KiB
C
#pragma once
|
|
|
|
#include "ggml.h"
|
|
#include "ggml-backend.h"
|
|
|
|
#ifdef GGML_USE_HIPBLAS
|
|
#define GGML_CUDA_NAME "ROCm"
|
|
#define GGML_CUBLAS_NAME "hipBLAS"
|
|
#elif defined(GGML_USE_MUSA)
|
|
#define GGML_CUDA_NAME "MUSA"
|
|
#define GGML_CUBLAS_NAME "muBLAS"
|
|
#else
|
|
#define GGML_CUDA_NAME "CUDA"
|
|
#define GGML_CUBLAS_NAME "cuBLAS"
|
|
#endif
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#define GGML_CUDA_MAX_DEVICES 16
|
|
|
|
// backend API
|
|
GGML_API GGML_CALL ggml_backend_t ggml_backend_cuda_init(int device, const void * params);
|
|
|
|
GGML_API GGML_CALL bool ggml_backend_is_cuda(ggml_backend_t backend);
|
|
|
|
// device buffer
|
|
GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_cuda_buffer_type(int device);
|
|
|
|
// split tensor buffer that splits matrices by rows across multiple devices
|
|
GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_cuda_split_buffer_type(const float * tensor_split);
|
|
|
|
// pinned host buffer for use with the CPU backend for faster copies between CPU and GPU
|
|
GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_cuda_host_buffer_type(void);
|
|
|
|
GGML_API GGML_CALL int ggml_backend_cuda_get_device_count(void);
|
|
GGML_API GGML_CALL void ggml_backend_cuda_get_device_description(int device, char * description, size_t description_size);
|
|
GGML_API GGML_CALL void ggml_backend_cuda_get_device_memory(int device, size_t * free, size_t * total);
|
|
|
|
GGML_API GGML_CALL bool ggml_backend_cuda_register_host_buffer(void * buffer, size_t size);
|
|
GGML_API GGML_CALL void ggml_backend_cuda_unregister_host_buffer(void * buffer);
|
|
|
|
GGML_API void ggml_backend_cuda_log_set_callback(ggml_log_callback log_callback, void * user_data);
|
|
|
|
GGML_API void ggml_backend_cuda_invalidate_graphs(void);
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|