CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-17 11:37:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: add conv_2d_transpose (#14287)

Browse Source 
* CUDA: add conv_2d_transpose

* remove direct include of cuda_fp16

* Review: add brackets for readability, remove ggml_set_param and add asserts
This commit is contained in:
Aman Gupta
2025-06-20 22:48:24 +08:00
committed by GitHub
parent 22015b2092
commit c959f462a0
4 changed files with 134 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cuda/conv2d-transpose.cuh Normal file
View File

@@ -0,0 +1,4 @@
#include "common.cuh"
#define CUDA_CONV2D_TRANSPOSE_BLOCK_SIZE 256
void ggml_cuda_conv_2d_transpose_p0(ggml_backend_cuda_context & ctx, ggml_tensor * dst);