94057c3d3e
PR Test (NPU) / check-changes (push) Has been cancelled
PR Test (NPU) / pr-gate (push) Has been cancelled
PR Test (NPU) / set-image-config (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-4-npu-a3 (push) Has been cancelled
PR Test (NPU) / stage-b-test-16-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-1-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-2-npu-a3 (push) Has been cancelled
PR Test (Arm64) / pr-gate (push) Has been cancelled
PR Test (Arm64) / check-changes (push) Has been cancelled
PR Test (Arm64) / build-test (push) Has been cancelled
PR Test (sgl-router) / gate (push) Has been cancelled
PR Test (sgl-router) / tier-1 — lint (push) Has been cancelled
PR Test (sgl-router) / tier-2 — build + test (push) Has been cancelled
PR Test (sgl-router) / tier-3 — docker (placeholder) (push) Has been cancelled
PR Test (sgl-router) / tier-3 — k8s integration (push) Has been cancelled
PR Test (sgl-router) / tier-3 — e2e (push) Has been cancelled
PR Test (sgl-router) / finish (push) Has been cancelled
PR Test (NPU) / single-node-poc (map[name:qwen3_6_27b_w8a8_1p_in64k_out1k_50ms runner:linux-aarch64-a3-2 test_case:test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_1p_in64k_out1k_50ms.py test_type:perf]) (push) Has been cancelled
PR Test (NPU) / pr-test-npu-finish (push) Has been cancelled
PR Test (Xeon) / pr-gate (push) Has been cancelled
PR Test (Xeon) / check-changes (push) Has been cancelled
PR Test (Xeon) / build-test (, xeon-gnr, base-b-test-cpu) (push) Has been cancelled
PR Test (XPU) / check-changes (push) Has been cancelled
PR Test (XPU) / pr-gate (push) Has been cancelled
PR Test (XPU) / stage-a-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / wait-for-stage-a (push) Has been cancelled
PR Test (XPU) / stage-b-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / finish (push) Has been cancelled
CI Model Inventory / build-inventory (push) Has been cancelled
Lint / lint (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Compilation Check (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Manual Policy (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Request Processing (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Summary (push) Has been cancelled
PR Test (SMG) / build-wheel (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on windows (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (x86_64 - auto) (push) Has been cancelled
PR Test (SMG) / python-unit-tests (push) Has been cancelled
PR Test (SMG) / unit-tests (push) Has been cancelled
PR Test (SMG) / benchmarks (push) Has been cancelled
PR Test (SMG) / chat-completions (push) Has been cancelled
PR Test (SMG) / chat-completions-4gpu (push) Has been cancelled
PR Test (SMG) / e2e (push) Has been cancelled
PR Test (SMG) / docker-build-test (push) Has been cancelled
PR Test (SMG) / k8s-integration (push) Has been cancelled
PR Test (SMG) / finish (push) Has been cancelled
PR Test (SMG) / summarize-benchmarks (push) Has been cancelled
Release SGLang Model Gateway Docker Image / publish (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Build SDist (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Upload to PyPI (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (aarch64, 12.9, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (x86_64, 12.9, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu129 (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (aarch64, 13.0, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (x86_64, 13.0, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu130 (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 700) (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 720) (push) Has been cancelled
Release SGLang Kernels / release-rocm700 (push) Has been cancelled
Release SGLang Kernels / release-rocm720 (push) Has been cancelled
Release SGLang Kernels / build-musa43 (43, 3.10) (push) Has been cancelled
Release SGLang Kernels / release-musa43 (push) Has been cancelled
78 lines
2.1 KiB
Docker
78 lines
2.1 KiB
Docker
######################## BASE IMAGE ##########################
|
|
FROM ubuntu:24.04 AS base
|
|
|
|
ARG PYTHON_VERSION=3.12
|
|
|
|
# set the environment variables
|
|
ENV PATH="/root/.local/bin:${PATH}"
|
|
ENV DEBIAN_FRONTEND=noninteractive
|
|
|
|
# uv environment variables
|
|
ENV UV_HTTP_TIMEOUT=500
|
|
ENV VIRTUAL_ENV="/opt/venv"
|
|
ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
|
|
ENV UV_LINK_MODE="copy"
|
|
ENV PATH="$VIRTUAL_ENV/bin:$PATH"
|
|
|
|
|
|
# install dependencies
|
|
RUN apt update -y \
|
|
&& apt install -y curl \
|
|
&& rm -rf /var/lib/apt/lists/* \
|
|
&& apt clean
|
|
|
|
# install uv
|
|
RUN curl -LsSf https://astral.sh/uv/install.sh | sh
|
|
|
|
# install python
|
|
RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
|
|
|
|
FROM scratch AS local_src
|
|
COPY . /src
|
|
|
|
######################### BUILD IMAGE #########################
|
|
FROM base AS build-image
|
|
|
|
# set the environment variables
|
|
ENV PATH="/root/.cargo/bin:${PATH}"
|
|
|
|
# install dependencies
|
|
RUN apt update -y \
|
|
&& apt install -y git build-essential libssl-dev pkg-config protobuf-compiler \
|
|
&& rm -rf /var/lib/apt/lists/* \
|
|
&& apt clean
|
|
|
|
# install rustup from rustup.rs
|
|
RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y \
|
|
&& rustc --version && cargo --version && protoc --version
|
|
|
|
# copy source code
|
|
COPY --from=local_src /src /opt/sglang
|
|
|
|
# working directory
|
|
WORKDIR /opt/sglang/sgl-model-gateway
|
|
|
|
# install maturin and build the wheel with vendored OpenSSL
|
|
RUN uv pip install maturin \
|
|
&& cargo clean \
|
|
&& rm -rf bindings/python/dist/ \
|
|
&& cd bindings/python \
|
|
&& ulimit -n 65536 && maturin build --release --features vendored-openssl --out dist \
|
|
&& rm -rf /root/.cache
|
|
|
|
######################### ROUTER IMAGE #########################
|
|
FROM base AS router-image
|
|
|
|
# Copy the built package from the build image
|
|
COPY --from=build-image /opt/sglang/sgl-model-gateway/bindings/python/dist/*.whl dist/
|
|
|
|
# Build the package and install
|
|
RUN uv pip install --force-reinstall dist/*.whl
|
|
|
|
# Clean up unnecessary files to reduce the image size
|
|
RUN rm -rf /root/.cache dist/ \
|
|
&& apt purge -y --auto-remove curl
|
|
|
|
# Set the entrypoint to the main command
|
|
ENTRYPOINT ["python3", "-m", "sglang_router.launch_router"]
|