vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : add benchmark example (#2626)

Browse source 
* 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>
This commit is contained in:
slaren 2023-08-18 12:44:58 +02:00 • committed by GitHub
parent eaf98c2649
commit 097e121e2f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
9 changed files with 1029 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

38
ggml-cuda.h
View file

@ -8,29 +8,25 @@ extern "C" {
#define GGML_CUDA_MAX_DEVICES 16
void ggml_init_cublas(void);
void ggml_cuda_set_tensor_split(const float * tensor_split);
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);
void ggml_cuda_mul(const struct ggml_tensor * src0, const struct ggml_tensor * src1, struct ggml_tensor * dst);
bool ggml_cuda_can_mul_mat(const struct ggml_tensor * src0, const struct ggml_tensor * src1, struct ggml_tensor * dst);
size_t ggml_cuda_mul_mat_get_wsize(const struct ggml_tensor * src0, const struct ggml_tensor * src1, struct ggml_tensor * dst);
void ggml_cuda_mul_mat(const struct ggml_tensor * src0, const struct ggml_tensor * src1, struct ggml_tensor * dst, void * wdata, size_t wsize);
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);
// TODO: export these with GGML_API
void * ggml_cuda_host_malloc(size_t size);
void ggml_cuda_host_free(void * ptr);
void ggml_cuda_transform_tensor(void * data, struct ggml_tensor * tensor);
void ggml_cuda_free_data(struct ggml_tensor * tensor);
void ggml_cuda_assign_buffers(struct ggml_tensor * tensor);
void ggml_cuda_assign_buffers_no_scratch(struct ggml_tensor * tensor);
void ggml_cuda_assign_buffers_force_inplace(struct ggml_tensor * tensor);
void ggml_cuda_set_main_device(int main_device);
void ggml_cuda_set_mul_mat_q(bool mul_mat_q);
void ggml_cuda_set_scratch_size(size_t scratch_size);
void ggml_cuda_free_scratch(void);
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
}