This website requires JavaScript.
Explore
Help
Sign In
pingu_98
/
llama_cpp_for_radxa_dragon_wing_q6a
Watch
1
Star
0
Fork
You've already forked llama_cpp_for_radxa_dragon_wing_q6a
0
Code
Issues
Pull requests
Projects
Releases
Packages
Wiki
Activity
Actions
56f3ebf38e
llama_cpp_for_radxa_dragon_...
/
ggml
History
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
ggml : add ggml_build_forward_select (
#18550
)
2026-01-19 20:03:19 +02:00
src
CUDA: faster FA for GQA > 1 but not power of 2 (
#19092
)
2026-01-25 21:19:47 +01:00
.gitignore
CMakeLists.txt