RYDE-WORK/llama.cpp
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/llama.cpp.git synced 2026-02-09 09:13:28 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity
4,758 Commits 1 Branch 0 Tags
Commit Graph

1 Commits

Author SHA1 Message Date
Johannes Gäßler
5fa07c2f93
CUDA: optimize FA for GQA + large batches (#12014) 2025-02-22 12:20:17 +01:00