This website requires JavaScript.
Explore
Help
Sign In
Superminaren
/
llama.cpp
Watch
1
Star
0
Fork
0
mirror of
https://github.com/ggml-org/llama.cpp.git
synced
2026-09-27 21:46:57 +02:00
Code
Issues
Packages
Projects
Releases
Wiki
Activity
Files
bb3c853c300323913d8535eb371fe906cae9b932
llama.cpp
/
ggml
T
History
cwriter
and
cwriter
bb3c853c30
sycl : support gated DSV4_HC_PRE and optional HC_POST comb matrix (
#29132
)
...
Co-authored-by: cwriter <cwriter@localhost>
2026-09-21 13:59:38 +03:00
..
cmake
CUDA: replace GGML_FA_ALL_QUANTS with GGML_FA_QUANTS, more control over what is compiled (
#28079
)
2026-09-09 12:50:08 +02:00
include
sycl : pinned memory use right device context instead of 0 (
#28895
)
2026-09-21 13:58:59 +03:00
src
sycl : support gated DSV4_HC_PRE and optional HC_POST comb matrix (
#29132
)
2026-09-21 13:59:38 +03:00
.gitignore
vulkan : cmake integration (
#8119
)
2024-07-13 18:12:39 +02:00
CMakeLists.txt
ggml : bump version to 0.24.0 (ggml/1627)
2026-09-14 16:45:33 +03:00
