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

clarify by placing info after steps

This commit is contained in:
Francisco Herrera 2025-12-14 09:42:36 -05:00 committed by GitHub
parent 836d49facd
commit 95d8332579
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docs/backend/OPENCL.md
View File

@ -174,8 +174,6 @@ If an older version of Powershell is used, these commands may not work as they a
### I. Setup Environment
The two steps below 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.
1. **Install OpenCL Headers and Library**
```powershell
@ -220,6 +218,10 @@ cmake .. -G Ninja `
ninja
```
## Linux
The two steps below 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
- Flash attention does not always improve performance.