wylab/llama.cpp
0
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-07 16:37:57 +02:00
Code Issues Packages Projects Releases Wiki Activity
10,853 Commits 778 Branches 7,351 Tags
allozaur/ui/hf-data-layer
Commit Graph
1 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Siavash NorouziandGitHub b74f590eaf ggml-cuda: fix divergent barrier in f16 flash attention (#27870) 
* ggml-cuda: fix divergent barrier in f16 flash attention

* ggml-cuda: avoid duplicate metadata pointer setup
 2026-09-07 09:23:21 +03:00