mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-09-23 13:36:20 +00:00
8 lines
227 B
Plaintext
8 lines
227 B
Plaintext
|
#include "common.cuh"
|
||
|
|
|
||
|
|
#define CUDA_CPY_BLOCK_SIZE 32
|
||
|
|
|
||
|
|
void ggml_cuda_cpy(ggml_backend_cuda_context & ctx, const ggml_tensor * src0, ggml_tensor * src1);
|
||
|
|
|
||
|
|
void ggml_cuda_dup(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|