This website requires JavaScript.
Explore
Help
Register
Sign In
upstream-archive
/
llama.cpp
Watch
1
Star
0
Fork
0
mirror of
https://github.com/ggml-org/llama.cpp.git
synced
2026-09-30 18:07:38 -05:00
Code
Issues
Packages
Projects
Releases
Wiki
Activity
Files
xsn/tool_parser_test
llama.cpp
/
ggml
/
src
/
ggml-vulkan
T
Add File
New File
Upload File
Apply Patch
Copy Permalink
Download directory as ZIP
Download directory as TAR.GZ
History
Jeff Bolz
78ec4c3780
vulkan: FA MMQ should use fp32 for Q quantization calculations (
#27413
)
...
Codex found that qd could be a denorm and 1/qd would overflow.
2026-08-20 09:18:11 -05:00
..
cmake
cmake: fix ggml-shaders-gen compiler paths containing spaces (
#12747
)
2025-04-04 10:12:40 -03:00
vulkan-shaders
vulkan: FA MMQ should use fp32 for Q quantization calculations (
#27413
)
2026-08-20 09:18:11 -05:00
CMakeLists.txt
vulkan : add source groups for shaders (
#26666
)
2026-08-20 09:52:28 +03:00
ggml-vulkan.cpp
vulkan : dequant q8_0 KV once in coopmat1 (
#25494
)
2026-08-19 17:44:15 +02:00
