905d87b70a
* CUDA kernel for q4_0 dequant. + mat. vec. mult. * Added q4_1 via template * Added missing __syncthreads(); * --gpu_layers -> --gpu-layers * Shorter dequantize_mul_mat_vec line * q5_0 dequantize_mul_mat kernel * More readable dequantize_mul_mat_vec logic * dequantize_mul_mat_vec kernels for q5_1, q8_0, f16 * llama : offload "output" tensor to GPU too + coding style fixes --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
22 lines
701 B
C
22 lines
701 B
C
#include "ggml.h"
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
void ggml_init_cublas(void);
|
|
|
|
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);
|
|
|
|
// 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(struct ggml_tensor * tensor);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|