mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2024-12-24 06:46:37 +00:00
f96e1c5b78
* sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.) * metal : allow env metal variable to override resource path (#1415) * Allow env variable to override resource path * Update ggml-metal.m --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * sync : restore common / main from `master` * sync : restore whisper from `master` * talk-llama : update to latest llama.cpp * ruby : fix build * ggml : fix 32-bit ARM build * ggml : fix MIN / MAX macro collisions + update ios bindings * ggml : fix ifdefs and MIN / MAX again * exampels : fix Obj-C and Swift examples * ggml : fix 32-bit ARM compatibility * ggml : one more attempt to fix 32-bit ARM compat * whisper : fix support for larger graphs --------- Co-authored-by: Chris Raethke <codesoda@users.noreply.github.com>
52 lines
1.9 KiB
C
52 lines
1.9 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"
|
|
#else
|
|
#define GGML_CUDA_NAME "CUDA"
|
|
#define GGML_CUBLAS_NAME "cuBLAS"
|
|
#endif
|
|
|
|
#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_assign_buffers_no_alloc(struct ggml_tensor * tensor);
|
|
GGML_API void ggml_cuda_assign_scratch_offset(struct ggml_tensor * tensor, size_t offset);
|
|
GGML_API void ggml_cuda_copy_to_device(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);
|
|
|
|
// backend API
|
|
GGML_API ggml_backend_t ggml_backend_cuda_init(void); // TODO: take a list of devices to use
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|