mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-10-30 14:40:16 +01:00
e7e4df031b
* llama : ggml-backend integration * ggml-backend : add names to buffers * fix unmap after loading * batched-bench : add tensor_split param * llama : check for null tensor_split * ggml-backend : increase GGML_MAX_BACKENDS * improve graph splitting, partial fix for --no-kv-offload * cuda : add ggml-backend split buffer support * cuda : do not create buffer types for devices that don't exist (fixes usage without CUDA devices available) * ggml : fix null backend dereference (#4807) * ggml : fix null backend dereference * ggml : also check ggml_backend_is_cpu * test-backend-ops : check buffer allocation failures * llama : add cparam (split_mode) and command line argument (--split-mode, -sm) to configure the split mode (none, layer or row) * ggml : fix mul_mat_id work size * llama : rewrite session kv load/set without graphs * minor * llama : only initialize used backends, free backends on context free * llama : abort ctx if cuda backend init fails * llama : rewrite lora with ggml-backend and compute on CPU ggml-ci * llama : only map to a backend buffer the region of the file mapping containing the tensors used in the buffer * opencl : add ggml-backend buffer type * cuda : only use batched_cublas with batched mat muls (fixes fp16 tg perf) * llama : on Metal, by default offload the full model ggml-ci * metal : page align the data ptr (#4854) * Apply suggestions from code review Co-authored-by: Johannes Gäßler <johannesg@5d6.de> * cuda : fix split buffer free * address review comments * llama-bench : add split-mode parameter * fix whitespace * opencl : fix double initialization * server : add --split-mode parameter * use async copy and compute to improve multi-gpu performance ggml-ci * use async memcpys to copy the graph outputs to the CPU * fix opencl * use a host buffer for the cpu compute buffer for faster copies to the gpu --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
36 lines
1.2 KiB
C
36 lines
1.2 KiB
C
#pragma once
|
|
|
|
#include "ggml.h"
|
|
#include "ggml-backend.h"
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
GGML_API void ggml_cl_init(void);
|
|
|
|
GGML_API void ggml_cl_mul(const struct ggml_tensor * src0, const struct ggml_tensor * src1, struct ggml_tensor * dst);
|
|
GGML_API bool ggml_cl_can_mul_mat(const struct ggml_tensor * src0, const struct ggml_tensor * src1, const struct ggml_tensor * dst);
|
|
GGML_API size_t ggml_cl_mul_mat_get_wsize(const struct ggml_tensor * src0, const struct ggml_tensor * src1, struct ggml_tensor * dst);
|
|
GGML_API void ggml_cl_mul_mat(const struct ggml_tensor * src0, const struct ggml_tensor * src1, struct ggml_tensor * dst, void * wdata, size_t wsize);
|
|
|
|
// GGML_API void * ggml_cl_host_malloc(size_t size);
|
|
// GGML_API void ggml_cl_host_free(void * ptr);
|
|
|
|
GGML_API void ggml_cl_free_data(const struct ggml_tensor* tensor);
|
|
|
|
GGML_API void ggml_cl_transform_tensor(void * data, struct ggml_tensor * tensor);
|
|
|
|
// backend API
|
|
|
|
// GGML_API ggml_backend_t ggml_backend_opencl_init(void);
|
|
|
|
// GGML_API bool ggml_backend_is_opencl(ggml_backend_t backend);
|
|
|
|
GGML_API ggml_backend_buffer_type_t ggml_backend_opencl_buffer_type(void);
|
|
// GGML_API ggml_backend_buffer_type_t ggml_backend_opencl_host_buffer_type(void);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|