This website requires JavaScript.
Explore
Help
Sign In
happyz
/
llama.cpp
mirror of
https://github.com/ggerganov/llama.cpp.git
Watch
1
Star
0
Fork
You've already forked llama.cpp
0
Code
Issues
Packages
Projects
Releases
Wiki
Activity
23e88631c4
llama.cpp
/
ggml
History
Tim Burke
23e88631c4
fix: gate tiled GEMM and split-KV paths to preserve q8_0/q4_0 vec_dot semantics
2026-03-20 23:40:15 -04:00
..
cmake
ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (
#15094
)
2025-08-07 13:45:41 +02:00
include
Merge branch 'master' into mxfp-flash-attention
2026-03-20 18:49:51 -04:00
src
fix: gate tiled GEMM and split-KV paths to preserve q8_0/q4_0 vec_dot semantics
2026-03-20 23:40:15 -04:00
.gitignore
vulkan : cmake integration (
#8119
)
2024-07-13 18:12:39 +02:00
CMakeLists.txt
ggml : bump version to 0.9.8 (ggml/1442)
2026-03-18 15:17:28 +02:00