chore: update Dockerfile (#5894)

.github/workflows/release-docker.yml

@@ -14,8 +14,8 @@ jobs:
     environment: 'prod'
     strategy:
       matrix:
-        cuda_version: ['11.8.0', '12.1.1', '12.4.1', '12.5.1']
-        build_type: ['all', 'srt']
+        cuda_version: ['12.4.1']
+        build_type: ['all']
     steps:
       - name: Delete huge unnecessary tools folder
         run: rm -rf /opt/hostedtoolcache
@@ -60,7 +60,7 @@ jobs:
           docker build . -f docker/Dockerfile --build-arg CUDA_VERSION=${{ matrix.cuda_version }} --build-arg BUILD_TYPE=${{ matrix.build_type }} -t lmsysorg/sglang:${tag}${tag_suffix} --no-cache
           docker push lmsysorg/sglang:${tag}${tag_suffix}
 
-          if [ "${{ matrix.cuda_version }}" = "12.5.1" ]; then
+          if [ "${{ matrix.cuda_version }}" = "12.4.1" ]; then
             docker tag lmsysorg/sglang:${tag}${tag_suffix} lmsysorg/sglang:latest${tag_suffix}
             docker push lmsysorg/sglang:latest${tag_suffix}
           fi

docker/Dockerfile

-ARG CUDA_VERSION=12.5.1
+ARG CUDA_VERSION=12.4.1
 
 FROM nvcr.io/nvidia/tritonserver:24.04-py3-min
 
@@ -9,13 +9,9 @@ RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
     && echo 'tzdata tzdata/Zones/America select Los_Angeles' | debconf-set-selections \
     && apt update -y \
     && apt install software-properties-common -y \
-    && add-apt-repository ppa:deadsnakes/ppa -y && apt update \
-    && apt install python3.10 python3.10-dev -y \
-    && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1 \
-    && update-alternatives --set python3 /usr/bin/python3.10 && apt install python3.10-distutils -y \
+    && apt install python3 python3-pip -y \
     && apt install curl git sudo libibverbs-dev -y \
-    && apt install -y rdma-core infiniband-diags openssh-server perftest ibverbs-providers libibumad3 libibverbs1 libnl-3-200 libnl-route-3-200 librdmacm1 \
-    && curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py && python3 get-pip.py \
+    && apt install rdma-core infiniband-diags openssh-server perftest -y \
     && python3 --version \
     && python3 -m pip --version \
     && rm -rf /var/lib/apt/lists/* \
@@ -43,6 +39,7 @@ RUN python3 -m pip install --upgrade pip setuptools wheel html5lib six \
        fi \
     && python3 -m pip install --no-cache-dir torch --index-url https://download.pytorch.org/whl/cu${CUINDEX} \
     && cd sglang \
-    && python3 -m pip --no-cache-dir install -e "python[${BUILD_TYPE}]" --find-links https://flashinfer.ai/whl/cu${CUINDEX}/torch2.6/flashinfer-python
+    && python3 -m pip --no-cache-dir install -e "python[${BUILD_TYPE}]" --find-links https://flashinfer.ai/whl/cu${CUINDEX}/torch2.6/flashinfer-python \
+    && python3 -m pip install nvidia-nccl-cu12==2.26.2.post1 --force-reinstall --no-deps
 
 ENV DEBIAN_FRONTEND=interactive