happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge a787084155 into ef83fb8601

This commit is contained in:
Francisco Herrera 2025-12-17 03:16:36 +08:00 committed by GitHub
parent ef83fb8601 a787084155
commit 0fa9380055
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/backend/OPENCL.md
View File

@ -218,6 +218,10 @@ cmake .. -G Ninja `
ninja ninja
``` ```
## Linux
The two steps just above also apply to Linux. If building for Linux, Ensure you have Git, CMake, Clang, Ninja and Python installed, in the second step remove the `-DCMAKE_TOOLCHAIN_FILE` parameter, and then in both steps replace the backticks with back slashes.
## Known Issues ## Known Issues
- Flash attention does not always improve performance. - Flash attention does not always improve performance.