CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-16 11:27:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: add mean operation (#14313)

Browse Source 
* CUDA: add mean operation

* add back sum_rows_f32_cuda

* Review: early exit if col!=0
This commit is contained in:
Aman Gupta
2025-06-22 12:39:54 +08:00
committed by GitHub
parent aa0ef5c578
commit aa064b2eb7
7 changed files with 54 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/src/ggml-cuda/sumrows.cuh
View File

@@ -1,5 +1,4 @@
#include "common.cuh"
void sum_rows_f32_cuda(const float * x, float * dst, const int ncols, const int nrows, cudaStream_t stream);
void ggml_cuda_op_sum_rows(ggml_backend_cuda_context & ctx, ggml_tensor * dst);