Reduce docker size (#632)

README.md

@@ -51,6 +51,16 @@ pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3/
 ### Method 3: Using docker
 The docker images are available on Docker Hub as [lmsysorg/sglang](https://hub.docker.com/r/lmsysorg/sglang/tags).
 
+```bash
+docker run --gpus all \
+    -p 30000:30000 \
+    -v ~/.cache/huggingface:/root/.cache/huggingface \
+    --env "HUGGING_FACE_HUB_TOKEN=<secret>" \
+    --ipc=host \
+    lmsysorg/sglang:latest \
+    python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B --host 0.0.0.0 --port 30000
+```
+
 ### Common Notes
 - If you see errors from the Triton compiler, please install the [Triton Nightly](https://triton-lang.org/main/getting-started/installation.html) by
 ```

docker/Dockerfile

@@ -16,7 +16,9 @@ RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
     && apt-get install -y python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv python3-pip \
     && if [ "${PYTHON_VERSION}" != "3" ]; then update-alternatives --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1; fi \
     && python3 --version \
-    && python3 -m pip --version
+    && python3 -m pip --version \
+    && rm -rf /var/lib/apt/lists/* \
+    && apt-get clean
 
 RUN apt-get update -y \
     && apt-get install -y python3-pip git curl sudo
@@ -29,9 +31,10 @@ RUN ldconfig /usr/local/cuda-$(echo $CUDA_VERSION | cut -d. -f1,2)/compat/
 
 WORKDIR /sgl-workspace
 
-RUN pip3 install --upgrade pip
-RUN pip3 install "sglang[all]"
-RUN pip3 uninstall -y triton triton-nightly && pip3 install --no-deps --index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/Triton-Nightly/pypi/simple/ triton-nightly
-RUN pip3 install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3/
+RUN pip3 --no-cache-dir install --upgrade pip \
+    && pip3 --no-cache-dir install "sglang[all]" \
+    && pip3 --no-cache-dir uninstall -y triton triton-nightly \
+    && pip3 --no-cache-dir install --no-deps --index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/Triton-Nightly/pypi/simple/ triton-nightly \
+    && pip3 --no-cache-dir install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3/
 
 ENV DEBIAN_FRONTEND=interactive