[docker] added rdma support (#3619)

docker/Dockerfile

@@ -14,6 +14,7 @@ RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
     && 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 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 \
     && python3 --version \
     && python3 -m pip --version \

docker/Dockerfile.dev

@@ -21,6 +21,7 @@ RUN apt-get update && apt-get install -y \
     pkg-config \
     libssl-dev \
     bear \
+    && apt install -y rdma-core infiniband-diags openssh-server perftest ibverbs-providers libibumad3 libibverbs1 libnl-3-200 libnl-route-3-200 librdmacm1 \
     && rm -rf /var/lib/apt/lists/* \
     && apt-get clean
 

docker/Dockerfile.rocm

@@ -20,6 +20,8 @@ ARG TRITON_COMMIT="improve_fa_decode_3.0.0"
 ARG ATER_REPO="https://github.com/HaiShaw/ater"
 ARG CK_COMMITS="fa05ae"
 
+RUN apt install -y rdma-core infiniband-diags openssh-server perftest ibverbs-providers libibumad3 libibverbs1 libnl-3-200 libnl-route-3-200 librdmacm1
+
 RUN git clone ${SGL_REPO} \
     && cd sglang \
     && if [ "${SGL_BRANCH}" = ${SGL_DEFAULT} ]; then \

docker/compose.yaml

@@ -7,7 +7,8 @@ services:
       # If you use modelscope, you need mount this directory
       # - ${HOME}/.cache/modelscope:/root/.cache/modelscope
     restart: always
-    network_mode: host
+    network_mode: host # required by RDMA
+    privileged: true # required by RDMA
     # Or you can only publish port 30000
     # ports:
     #   - 30000:30000
@@ -16,8 +17,7 @@ services:
       # if you use modelscope to download model, you need set this environment
       # - SGLANG_USE_MODELSCOPE: true
     entrypoint: python3 -m sglang.launch_server
-    command:
-      --model-path meta-llama/Llama-3.1-8B-Instruct
+    command: --model-path meta-llama/Llama-3.1-8B-Instruct
       --host 0.0.0.0
       --port 30000
     ulimits:
@@ -31,5 +31,5 @@ services:
         reservations:
           devices:
             - driver: nvidia
-              device_ids: ['0']
+              device_ids: ["0"]
               capabilities: [gpu]