llama.cpp/ggml-cuda.h
slaren 097e121e2f
llama : add benchmark example (#2626)
* llama : add benchmark example

* add to examples CMakeLists.txt

* fix msvc build

* add missing include

* add Bessel's correction to stdev calculation

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* improve markdown formatting

* add missing include

* print warning is NDEBUG is not defined

* remove n_prompt and n_gen from the matrix, use each value separately instead

* better checks for non-optimized builds

* llama.cpp : fix MEM_REQ_SCRATCH0 reusing the value of n_ctx of the first call

* fix json formatting

* add sql output

* add basic cpu and gpu info (linx/cuda only)

* markdown: also show values that differ from the default

* markdown: add build id

* cleanup

* improve formatting

* formatting

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
2023-08-18 12:44:58 +02:00

34 lines
1.3 KiB
C

#pragma once
#include "ggml.h"
#ifdef __cplusplus
extern "C" {
#endif
#define GGML_CUDA_MAX_DEVICES 16
GGML_API void ggml_init_cublas(void);
GGML_API void * ggml_cuda_host_malloc(size_t size);
GGML_API void ggml_cuda_host_free(void * ptr);
GGML_API bool ggml_cuda_can_mul_mat(const struct ggml_tensor * src0, const struct ggml_tensor * src1, struct ggml_tensor * dst);
GGML_API void ggml_cuda_set_tensor_split(const float * tensor_split);
GGML_API void ggml_cuda_transform_tensor(void * data, struct ggml_tensor * tensor);
GGML_API void ggml_cuda_free_data(struct ggml_tensor * tensor);
GGML_API void ggml_cuda_assign_buffers(struct ggml_tensor * tensor);
GGML_API void ggml_cuda_assign_buffers_no_scratch(struct ggml_tensor * tensor);
GGML_API void ggml_cuda_assign_buffers_force_inplace(struct ggml_tensor * tensor);
GGML_API void ggml_cuda_set_main_device(int main_device);
GGML_API void ggml_cuda_set_mul_mat_q(bool mul_mat_q);
GGML_API void ggml_cuda_set_scratch_size(size_t scratch_size);
GGML_API void ggml_cuda_free_scratch(void);
GGML_API bool ggml_cuda_compute_forward(struct ggml_compute_params * params, struct ggml_tensor * tensor);
GGML_API int ggml_cuda_get_device_count(void);
GGML_API void ggml_cuda_get_device_description(int device, char * description, size_t description_size);
#ifdef __cplusplus
}
#endif