tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

doc: [MUSA] minor changes (#12583)

Browse Source 
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
This commit is contained in:
R0CKSTAR
2025-03-26 15:09:48 +08:00
committed by GitHub
parent 53af4dba42
commit fd7855f8f5
2 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ci/README.md
View File

@ -60,7 +60,7 @@ docker run --privileged -it \
Inside the container, execute the following commands: Inside the container, execute the following commands:
```bash ```bash
apt update -y && apt install -y cmake git python3.10-venv wget apt update -y && apt install -y bc cmake git python3.10-venv time unzip wget
git config --global --add safe.directory /ws git config --global --add safe.directory /ws
GG_BUILD_MUSA=1 bash ./ci/run.sh /ci-results /ci-cache GG_BUILD_MUSA=1 bash ./ci/run.sh /ci-results /ci-cache
``` ```

1
docs/build.md
View File

@ -218,6 +218,7 @@ By default, all supported compute capabilities are enabled. To customize this be
```bash ```bash
cmake -B build -DGGML_MUSA=ON -DMUSA_ARCHITECTURES="21" cmake -B build -DGGML_MUSA=ON -DMUSA_ARCHITECTURES="21"
cmake --build build --config Release
``` ```
This configuration enables only compute capability `2.1` (MTT S80) during compilation, which can help reduce compilation time. This configuration enables only compute capability `2.1` (MTT S80) during compilation, which can help reduce compilation time.