EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[feat] apply deep_gemm compile_mode to skip launch (#9879)

Browse Source
This commit is contained in:
JieXin Liang
2025-09-02 18:20:30 +08:00
committed by GitHub
parent a1e5d78115
commit 1db649ac02
4 changed files with 12 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docker/Dockerfile
View File

@@ -85,10 +85,10 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip setuptools wheel html5li
&& python3 -m pip install --no-cache-dir nvidia-nccl-cu12==2.27.6 --force-reinstall --no-deps \
&& python3 -m flashinfer --download-cubin \
&& if [ "$CUDA_VERSION" = "12.8.1" ]; then \
python3 -m pip install --no-cache-dir https://github.com/sgl-project/whl/releases/download/v0.3.7.post1/sgl_kernel-0.3.7.post1+cu128-cp310-abi3-manylinux2014_x86_64.whl --force-reinstall --no-deps ; \
python3 -m pip install --no-cache-dir https://github.com/sgl-project/whl/releases/download/v0.3.8/sgl_kernel-0.3.8+cu128-cp310-abi3-manylinux2014_x86_64.whl --force-reinstall --no-deps ; \
fi \
&& if [ "$CUDA_VERSION" = "12.9.1" ]; then \
python3 -m pip install --no-cache-dir https://github.com/sgl-project/whl/releases/download/v0.3.7.post1/sgl_kernel-0.3.7.post1+cu129-cp310-abi3-manylinux2014_x86_64.whl --force-reinstall --no-deps ; \
python3 -m pip install --no-cache-dir https://github.com/sgl-project/whl/releases/download/v0.3.8/sgl_kernel-0.3.8+cu129-cp310-abi3-manylinux2014_x86_64.whl --force-reinstall --no-deps ; \
fi
# Download source files