CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-11 10:36:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: backwards pass for misc. ops, add tests (#11257)

Browse Source 
* CUDA: backwards pass for misc. ops, add tests

* remove restrict from pointers
This commit is contained in:
Johannes Gäßler
2025-01-16 16:43:38 +01:00
committed by GitHub
parent 681149ced2
commit 9c8dcefe17
18 changed files with 930 additions and 332 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda/softmax.cuh
View File

@@ -3,3 +3,5 @@
#define CUDA_SOFT_MAX_BLOCK_SIZE 1024
void ggml_cuda_op_soft_max(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_soft_max_back(ggml_backend_cuda_context & ctx, ggml_tensor * dst);