llama.cpp/ggml-cuda/cpy.cuh

10 lines
298 B
Plaintext
Raw Normal View History

#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);
void* ggml_cuda_cpy_fn(const ggml_tensor * src0, ggml_tensor * src1);