diff options
Diffstat (limited to 'ggml-cuda.h')
| -rw-r--r-- | ggml-cuda.h | 26 |
1 files changed, 7 insertions, 19 deletions
diff --git a/ggml-cuda.h b/ggml-cuda.h index cdb0c0c4..d19cbf3f 100644 --- a/ggml-cuda.h +++ b/ggml-cuda.h @@ -27,22 +27,6 @@ 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); @@ -52,13 +36,17 @@ GGML_API void ggml_cuda_get_device_description(int device, char * description, GGML_API ggml_backend_t ggml_backend_cuda_init(int device); GGML_API bool ggml_backend_is_cuda(ggml_backend_t backend); -GGML_API int ggml_backend_cuda_get_device(ggml_backend_t backend); GGML_API ggml_backend_buffer_type_t ggml_backend_cuda_buffer_type(int device); - -// pinned host buffer for use with CPU backend for faster copies between CPU and GPU +// split tensor buffer that splits matrices by rows across multiple devices +GGML_API 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_backend_buffer_type_t ggml_backend_cuda_host_buffer_type(void); +GGML_API int ggml_backend_cuda_get_device_count(void); +GGML_API void ggml_backend_cuda_get_device_description(int device, char * description, size_t description_size); +GGML_API void ggml_backend_cuda_get_device_memory(int device, size_t * free, size_t * total); + #ifdef __cplusplus } #endif |