mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-01-10 02:31:46 +00:00
10 lines
298 B
Plaintext
10 lines
298 B
Plaintext
#include "common.cuh"
|
|
|
|
#define CUDA_CPY_BLOCK_SIZE 64
|
|
|
|
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);
|
|
|
|
void* ggml_cuda_cpy_fn(const ggml_tensor * src0, ggml_tensor * src1);
|