Skip to content

LLM inference in C/C++

C++ ggml
218 B
Raw Blame
#include "common.cuh"

#define CUDA_IM2COL_BLOCK_SIZE 256

void ggml_cuda_op_im2col(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_im2col_3d(ggml_backend_cuda_context & ctx, ggml_tensor * dst);