This website requires JavaScript.
Explore
Help
Sign in
thek0tyara
/
llama-cpp-turboquant
Watch
1
Star
0
Fork
You've already forked llama-cpp-turboquant
0
Code
Issues
Pull requests
Projects
Releases
Packages
Wiki
Activity
Actions
6
142cbe2ac6
llama-cpp-turboquant
/
ggml
History
Download ZIP
Download TAR.GZ
Johannes Gäßler
0c21677e43
CUDA: faster FA for GQA > 1 but not power of 2 (
#19092
)
2026-01-25 21:19:47 +01:00
..
cmake
include
src
CUDA: faster FA for GQA > 1 but not power of 2 (
#19092
)
2026-01-25 21:19:47 +01:00
.gitignore
CMakeLists.txt