mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-17 11:37:10 +00:00
9eaa51e7f0
* CUDA: add conv_2d_dw * better naming * simplify using template * Review: fix operation ordering in ggml-cuda, use __forceinline__, use more const
6 lines
155 B
Plaintext
6 lines
155 B
Plaintext
#pragma once
|
|
#include "common.cuh"
|
|
|
|
#define CUDA_CONV2D_DW_BLOCK_SIZE 256
|
|
void ggml_cuda_op_conv2d_dw(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|