sglang (v0.5.15.post1)

Published 2026-07-15 22:17:18 -07:00 by kennysheridan

Installation

docker pull forgejo.kennysheridan.io/kennysheridan/sglang:v0.5.15.post1
sha256:289cf51da1e5fd6f8eb3231f0202d46800c2e241ecf28f68a5a51507ed928e31

Image layers

ARG RELEASE
ARG LAUNCHPAD_BUILD_ARCH
LABEL org.opencontainers.image.ref.name=ubuntu
LABEL org.opencontainers.image.version=24.04
ADD file:e67907c77897d27192314f6c4fa0112b6f7dce3e127500516535cc50fe736c92 in /
CMD ["/bin/bash"]
ENV NVARCH=x86_64
ENV NVIDIA_REQUIRE_CUDA=cuda>=13.0 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566 brand=unknown,driver>=570,driver<571 brand=grid,driver>=570,driver<571 brand=tesla,driver>=570,driver<571 brand=nvidia,driver>=570,driver<571 brand=quadro,driver>=570,driver<571 brand=quadrortx,driver>=570,driver<571 brand=nvidiartx,driver>=570,driver<571 brand=vapps,driver>=570,driver<571 brand=vpc,driver>=570,driver<571 brand=vcs,driver>=570,driver<571 brand=vws,driver>=570,driver<571 brand=cloudgaming,driver>=570,driver<571 brand=unknown,driver>=575,driver<576 brand=grid,driver>=575,driver<576 brand=tesla,driver>=575,driver<576 brand=nvidia,driver>=575,driver<576 brand=quadro,driver>=575,driver<576 brand=quadrortx,driver>=575,driver<576 brand=nvidiartx,driver>=575,driver<576 brand=vapps,driver>=575,driver<576 brand=vpc,driver>=575,driver<576 brand=vcs,driver>=575,driver<576 brand=vws,driver>=575,driver<576 brand=cloudgaming,driver>=575,driver<576
ENV NV_CUDA_CUDART_VERSION=13.0.88-1
ARG TARGETARCH
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends gnupg2 curl ca-certificates && curl -fsSL https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${NVARCH}/3bf863cc.pub | apt-key add - && echo "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${NVARCH} /" > /etc/apt/sources.list.d/cuda.list && apt-get purge --autoremove -y curl && rm -rf /var/lib/apt/lists/* # buildkit
ENV CUDA_VERSION=13.0.1
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-cudart-13-0=${NV_CUDA_CUDART_VERSION} cuda-compat-13-0 && rm -rf /var/lib/apt/lists/* # buildkit
RUN |1 TARGETARCH=amd64 /bin/sh -c echo "/usr/local/cuda/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit
ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
COPY NGC-DL-CONTAINER-LICENSE / # buildkit
ENV NVIDIA_VISIBLE_DEVICES=all
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
ENV NV_CUDA_LIB_VERSION=13.0.1-1
ENV NV_NVTX_VERSION=13.0.85-1
ENV NV_LIBNPP_VERSION=13.0.1.2-1
ENV NV_LIBNPP_PACKAGE=libnpp-13-0=13.0.1.2-1
ENV NV_LIBCUSPARSE_VERSION=12.6.3.3-1
ENV NV_LIBCUBLAS_PACKAGE_NAME=libcublas-13-0
ENV NV_LIBCUBLAS_VERSION=13.0.2.14-1
ENV NV_LIBCUBLAS_PACKAGE=libcublas-13-0=13.0.2.14-1
ENV NV_LIBNCCL_PACKAGE_NAME=libnccl2
ENV NV_LIBNCCL_PACKAGE_VERSION=2.28.3-1
ENV NCCL_VERSION=2.28.3-1
ENV NV_LIBNCCL_PACKAGE=libnccl2=2.28.3-1+cuda13.0
ARG TARGETARCH
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-libraries-13-0=${NV_CUDA_LIB_VERSION} ${NV_LIBNPP_PACKAGE} cuda-nvtx-13-0=${NV_NVTX_VERSION} libcusparse-13-0=${NV_LIBCUSPARSE_VERSION} ${NV_LIBCUBLAS_PACKAGE} ${NV_LIBNCCL_PACKAGE} && rm -rf /var/lib/apt/lists/* # buildkit
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-mark hold ${NV_LIBCUBLAS_PACKAGE_NAME} ${NV_LIBNCCL_PACKAGE_NAME} # buildkit
COPY entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit
COPY nvidia_entrypoint.sh /opt/nvidia/ # buildkit
ENV NVIDIA_PRODUCT_NAME=CUDA
ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
ENV NV_CUDA_LIB_VERSION=13.0.1-1
ENV NV_CUDA_CUDART_DEV_VERSION=13.0.88-1
ENV NV_NVML_DEV_VERSION=13.0.87-1
ENV NV_LIBCUSPARSE_DEV_VERSION=12.6.3.3-1
ENV NV_LIBNPP_DEV_VERSION=13.0.1.2-1
ENV NV_LIBNPP_DEV_PACKAGE=libnpp-dev-13-0=13.0.1.2-1
ENV NV_LIBCUBLAS_DEV_VERSION=13.0.2.14-1
ENV NV_LIBCUBLAS_DEV_PACKAGE_NAME=libcublas-dev-13-0
ENV NV_LIBCUBLAS_DEV_PACKAGE=libcublas-dev-13-0=13.0.2.14-1
ENV NV_CUDA_NSIGHT_COMPUTE_VERSION=13.0.1-1
ENV NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-13-0=13.0.1-1
ENV NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-dev
ENV NV_LIBNCCL_DEV_PACKAGE_VERSION=2.28.3-1
ENV NCCL_VERSION=2.28.3-1
ENV NV_LIBNCCL_DEV_PACKAGE=libnccl-dev=2.28.3-1+cuda13.0
ARG TARGETARCH
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-cudart-dev-13-0=${NV_CUDA_CUDART_DEV_VERSION} cuda-command-line-tools-13-0=${NV_CUDA_LIB_VERSION} cuda-minimal-build-13-0=${NV_CUDA_LIB_VERSION} cuda-libraries-dev-13-0=${NV_CUDA_LIB_VERSION} cuda-nvml-dev-13-0=${NV_NVML_DEV_VERSION} ${NV_LIBNPP_DEV_PACKAGE} libcusparse-dev-13-0=${NV_LIBCUSPARSE_DEV_VERSION} ${NV_LIBCUBLAS_DEV_PACKAGE} ${NV_LIBNCCL_DEV_PACKAGE} ${NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE} && rm -rf /var/lib/apt/lists/* # buildkit
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-mark hold ${NV_LIBCUBLAS_DEV_PACKAGE_NAME} ${NV_LIBNCCL_DEV_PACKAGE_NAME} # buildkit
ENV LIBRARY_PATH=/usr/local/cuda/lib64/stubs
ENV NV_CUDNN_VERSION=9.13.0.50-1
ENV NV_CUDNN_PACKAGE_NAME=libcudnn9-cuda-13
ENV NV_CUDNN_PACKAGE=libcudnn9-cuda-13=9.13.0.50-1
ENV NV_CUDNN_PACKAGE_DEV=libcudnn9-dev-cuda-13=9.13.0.50-1
ENV NV_CUDNN_PACKAGE_DEV_HEADERS=libcudnn9-headers-cuda-13=9.13.0.50-1
ARG TARGETARCH
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
LABEL com.nvidia.cudnn.version=9.13.0.50-1
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends ${NV_CUDNN_PACKAGE} ${NV_CUDNN_PACKAGE_DEV} ${NV_CUDNN_PACKAGE_DEV_HEADERS} && apt-mark hold ${NV_CUDNN_PACKAGE_NAME} && rm -rf /var/lib/apt/lists/* # buildkit
ARG TARGETARCH=amd64
ARG BUILD_TYPE=all
ARG BRANCH_TYPE=remote
ARG GRACE_BLACKWELL=0
ARG HOPPER_SBO=0
ARG HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6
ARG DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee
ARG BUILD_AND_DOWNLOAD_PARALLEL=8
ARG SGL_KERNEL_VERSION=0.4.4
ARG SGL_VERSION=0.5.15.post1
ARG SGL_DEEP_GEMM_VERSION=0.1.4
ARG USE_LATEST_SGLANG=0
ARG GDRCOPY_VERSION=2.5.1
ARG PIP_DEFAULT_INDEX
ARG UBUNTU_MIRROR
ARG GITHUB_ARTIFACTORY=github.com
ARG INSTALL_FLASHINFER_JIT_CACHE=1
ARG FLASHINFER_VERSION=0.6.12
ARG MOONCAKE_VERSION=0.3.11.post1
ARG MSCCLPP_VERSION=sglang-v0.9.1
ARG MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON
ENV DEBIAN_FRONTEND=noninteractive CUDA_HOME=/usr/local/cuda GDRCOPY_HOME=/usr/src/gdrdrv-2.5.1/ FLASHINFER_VERSION=0.6.12
ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/nvidia/bin LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
RUN |21 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON /bin/sh -c if [ -n "$UBUNTU_MIRROR" ]; then sed -i "s|http://.*archive.ubuntu.com|$UBUNTU_MIRROR|g" /etc/apt/sources.list && sed -i "s|http://.*security.ubuntu.com|$UBUNTU_MIRROR|g" /etc/apt/sources.list; fi # buildkit
RUN |21 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON /bin/sh -c apt update && apt install -y --no-install-recommends wget software-properties-common && apt install -y --no-install-recommends python3.12-full python3.12-dev && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.12 2 && update-alternatives --set python3 /usr/bin/python3.12 && wget -q https://bootstrap.pypa.io/get-pip.py && python3 get-pip.py --break-system-packages && rm get-pip.py && python3 -m pip config set global.break-system-packages true && cd /usr/lib/python3/dist-packages/ && ln -s apt_pkg.cpython-312-*-linux-gnu.so apt_pkg.so # buildkit
RUN |21 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON /bin/sh -c apt-get update && apt-get install -y --no-install-recommends ca-certificates software-properties-common netcat-openbsd kmod unzip openssh-server curl wget lsof locales build-essential cmake perl patchelf ccache git-lfs libopenmpi-dev libnuma1 libnuma-dev numactl ffmpeg libibverbs-dev libibverbs1 libibumad3 librdmacm1 libnl-3-200 libnl-route-3-200 libnl-route-3-dev libnl-3-dev ibverbs-providers infiniband-diags perftest libgoogle-glog-dev libgtest-dev libjsoncpp-dev libunwind-dev libboost-all-dev libssl-dev libgrpc-dev libgrpc++-dev libprotobuf-dev protobuf-compiler protobuf-compiler-grpc pybind11-dev libhiredis-dev libcurl4-openssl-dev libczmq4 libczmq-dev libfabric-dev linux-libc-dev devscripts debhelper fakeroot dkms check libsubunit0 libsubunit-dev && ln -sf /usr/bin/python3.12 /usr/bin/python && rm -rf /var/lib/apt/lists/* && apt-get clean # buildkit
RUN |21 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON /bin/sh -c if [ -n "${PIP_DEFAULT_INDEX}" ]; then python3 -m pip config set global.index-url ${PIP_DEFAULT_INDEX}; fi # buildkit
RUN |21 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON /bin/sh -c mkdir -p /tmp/gdrcopy && cd /tmp && curl --retry 3 --retry-delay 2 -fsSL -o v${GDRCOPY_VERSION}.tar.gz https://${GITHUB_ARTIFACTORY}/NVIDIA/gdrcopy/archive/refs/tags/v${GDRCOPY_VERSION}.tar.gz && tar -xzf v${GDRCOPY_VERSION}.tar.gz && rm v${GDRCOPY_VERSION}.tar.gz && cd gdrcopy-${GDRCOPY_VERSION}/packages && CUDA=/usr/local/cuda ./build-deb-packages.sh && dpkg -i gdrdrv-dkms_*.deb libgdrapi_*.deb gdrcopy-tests_*.deb gdrcopy_*.deb && cd / && rm -rf /tmp/gdrcopy # buildkit
RUN |21 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON /bin/sh -c ln -sf /usr/lib/$(uname -m)-linux-gnu/libmlx5.so.1 /usr/lib/$(uname -m)-linux-gnu/libmlx5.so # buildkit
RUN |21 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON /bin/sh -c locale-gen en_US.UTF-8 # buildkit
ENV LANG=en_US.UTF-8 LANGUAGE=en_US:en LC_ALL=en_US.UTF-8
ARG CUDA_VERSION=13.0.1
ARG BUILD_TYPE=all
ARG SGL_KERNEL_VERSION
ARG GITHUB_ARTIFACTORY
WORKDIR /sgl-workspace
ENV PATH=/root/.cargo/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/nvidia/bin
RUN |22 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON CUDA_VERSION=13.0.1 /bin/sh -c curl --proto '=https' --tlsv1.2 --retry 3 --retry-delay 2 -sSf https://sh.rustup.rs | sh -s -- -y --no-modify-path --profile minimal && rustc --version && cargo --version # buildkit
RUN |22 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON CUDA_VERSION=13.0.1 /bin/sh -c python3 -m pip install --upgrade pip setuptools wheel html5lib six && case "$CUDA_VERSION" in 12.6.1) CUINDEX=126 ;; 12.8.1) CUINDEX=128 ;; 12.9.1) CUINDEX=129 ;; 13.0.1) CUINDEX=130 ;; *) echo "Unsupported CUDA version: $CUDA_VERSION" && exit 1 ;; esac && if [ "$CUDA_VERSION" = "12.6.1" ]; then python3 -m pip install https://${GITHUB_ARTIFACTORY}/sgl-project/whl/releases/download/v${SGL_KERNEL_VERSION}/sglang_kernel-${SGL_KERNEL_VERSION}+cu124-cp310-abi3-manylinux2014_$(uname -m).whl --force-reinstall --no-deps ; elif [ "$CUDA_VERSION" = "12.8.1" ] || [ "$CUDA_VERSION" = "12.9.1" ]; then python3 -m pip install https://github.com/sgl-project/whl/releases/download/v${SGL_KERNEL_VERSION}/sglang_kernel-${SGL_KERNEL_VERSION}+cu129-cp310-abi3-manylinux2014_$(uname -m).whl --force-reinstall --no-deps ; elif [ "$CUDA_VERSION" = "13.0.1" ]; then python3 -m pip install sglang-kernel==${SGL_KERNEL_VERSION} --force-reinstall --no-deps ; else echo "Unsupported CUDA version: $CUDA_VERSION" && exit 1 ; fi # buildkit
COPY python/pyproject.toml /tmp/sglang_deps/python/pyproject.toml # buildkit
COPY rust/sglang-grpc /tmp/sglang_deps/rust/sglang-grpc # buildkit
COPY proto /tmp/sglang_deps/proto # buildkit
RUN |22 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON CUDA_VERSION=13.0.1 /bin/sh -c case "$CUDA_VERSION" in 12.6.1) CUINDEX=126 ;; 12.8.1) CUINDEX=128 ;; 12.9.1) CUINDEX=129 ;; 13.0.1) CUINDEX=130 ;; *) echo "Unsupported CUDA version: $CUDA_VERSION" && exit 1 ;; esac && cd /tmp/sglang_deps/python && mkdir -p sglang && touch sglang/__init__.py && echo '__version__ = "0.0.0"' > sglang/version.py && touch README.md && touch LICENSE && if [ "${CUDA_VERSION%%.*}" = "12" ]; then sed -i 's/cuda-python>=13\.0/cuda-python>=12,<13/' pyproject.toml && sed -i 's/flashinfer_python\[cu13\]/flashinfer_python[cu12]/' pyproject.toml && sed -i 's/nvidia-cutlass-dsl\[cu13\]/nvidia-cutlass-dsl/' pyproject.toml; fi && python3 -m pip install --extra-index-url https://download.pytorch.org/whl/cu${CUINDEX} ".[${BUILD_TYPE}]" && if [ "${CUDA_VERSION%%.*}" = "12" ]; then pip list --format=freeze | awk -F'==' '/-cu13(==|$)/ {print $1}' | xargs -r python3 -m pip uninstall -y && python3 -m pip install --index-url https://download.pytorch.org/whl/cu${CUINDEX} torch==2.11.0 torchvision==0.26.0 torchaudio==2.11.0 --force-reinstall; python3 -m pip install https://github.com/sgl-project/whl/releases/download/v${SGL_DEEP_GEMM_VERSION}/sgl_deep_gemm-${SGL_DEEP_GEMM_VERSION}+cu129-py3-none-manylinux2014_$(uname -m).whl --force-reinstall; fi && cd /sgl-workspace && rm -rf /tmp/sglang_deps && pip freeze | grep -v "^sglang==" > /sgl-workspace/constraints.txt # buildkit
ARG BRANCH_TYPE
ARG BUILD_TYPE=all
ARG CUDA_VERSION=13.0.1
ARG BUILD_AND_DOWNLOAD_PARALLEL
ARG SGL_VERSION=0.5.15.post1
ARG USE_LATEST_SGLANG
ARG GITHUB_ARTIFACTORY
ARG MOONCAKE_VERSION
ARG MOONCAKE_COMPILE_ARG
ARG MSCCLPP_VERSION
WORKDIR /sgl-workspace
COPY /wheels /tmp/wheels/deepep # buildkit
COPY /build/DeepEP /sgl-workspace/DeepEP # buildkit
RUN |22 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON CUDA_VERSION=13.0.1 /bin/sh -c pip install /tmp/wheels/deepep/*.whl && rm -rf /tmp/wheels/deepep # buildkit
COPY /flashinfer_jit_output/ /usr/local/lib/python3.12/dist-packages/ # buildkit
COPY /tools/diff-so-fancy /usr/local/bin/ # buildkit
COPY /tools/clang-format /usr/local/bin/ # buildkit
COPY /tools/clangd /usr/local/bin/ # buildkit
COPY /tools/lib /usr/local/lib/ # buildkit
COPY /tools/cmake /usr/local/bin/ # buildkit
COPY /tools/ctest /usr/local/bin/ # buildkit
COPY /tools/cpack /usr/local/bin/ # buildkit
COPY /tools/share/cmake-3.31 /usr/local/share/cmake-3.31 # buildkit
COPY /tools/just /usr/local/bin/ # buildkit
COPY /root/.oh-my-zsh /root/.oh-my-zsh # buildkit
RUN |22 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON CUDA_VERSION=13.0.1 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends gdb ninja-build vim tmux htop zsh tree silversearcher-ag cloc pkg-config bear less rdma-core openssh-server gnuplot infiniband-diags perftest ibverbs-providers libibumad3 libibverbs1 libnl-3-200 libnl-route-3-200 librdmacm1 && rm -rf /var/lib/apt/lists/* && apt-get clean # buildkit
RUN |22 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON CUDA_VERSION=13.0.1 /bin/sh -c apt update -y && apt install -y --no-install-recommends gnupg && echo "deb http://developer.download.nvidia.com/devtools/repos/ubuntu2004/$(if [ "$(uname -m)" = "aarch64" ]; then echo "arm64"; else echo "amd64"; fi) /" | tee /etc/apt/sources.list.d/nvidia-devtools.list && apt-key adv --fetch-keys http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/$(if [ "$(uname -m)" = "aarch64" ]; then echo "arm64"; else echo "x86_64"; fi)/7fa2af80.pub && apt update -y && apt install -y --no-install-recommends nsight-systems-cli && rm -rf /var/lib/apt/lists/* # buildkit
RUN |22 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON CUDA_VERSION=13.0.1 /bin/sh -c CUDA_MAJOR="${CUDA_VERSION%%.*}" && if [ "$CUDA_MAJOR" -ge 13 ]; then python3 -m pip install mooncake-transfer-engine-cuda13==${MOONCAKE_VERSION}; else python3 -m pip install mooncake-transfer-engine==${MOONCAKE_VERSION}; fi # buildkit
RUN |22 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON CUDA_VERSION=13.0.1 /bin/sh -c git clone --depth=1 --branch ${MSCCLPP_VERSION} https://${GITHUB_ARTIFACTORY}/microsoft/mscclpp.git /tmp/mscclpp && case "${CUDA_VERSION}" in 12.*) CMAKE_ARGS="-DMSCCLPP_BYPASS_GPU_CHECK=ON -DMSCCLPP_USE_CUDA=ON -DMSCCLPP_GPU_ARCHS=80,90,100,100a,103,103a" python3 -m pip install "/tmp/mscclpp[cuda12]"; ;; 13.*) CMAKE_ARGS="-DMSCCLPP_BYPASS_GPU_CHECK=ON -DMSCCLPP_USE_CUDA=ON -DMSCCLPP_GPU_ARCHS=80,90,100,100a,103,103a" python3 -m pip install "/tmp/mscclpp[cuda13]"; ;; *) echo "Unsupported CUDA version for MSCCL++: ${CUDA_VERSION}" && exit 1; ;; esac && rm -rf /tmp/mscclpp # buildkit
RUN |22 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON CUDA_VERSION=13.0.1 /bin/sh -c python3 -m pip install -c /sgl-workspace/constraints.txt datamodel_code_generator pre-commit pytest black isort icdiff uv wheel scikit-build-core py-spy cubloaty google-cloud-storage pandas matplotlib tabulate termplotlib "runai-model-streamer[s3,gcs,azure]>=0.15.7" # buildkit
ARG INSTALL_DYNAMO=0
ARG DYNAMO_VERSION=
RUN |24 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON CUDA_VERSION=13.0.1 INSTALL_DYNAMO=0 DYNAMO_VERSION= /bin/sh -c set -eu; if [ "$INSTALL_DYNAMO" = "1" ]; then if [ -z "$DYNAMO_VERSION" ]; then index="$(curl -fsSL --retry 3 --retry-delay 2 https://pypi.nvidia.com/ai-dynamo/)" || { echo "ERROR: failed to fetch the ai-dynamo index from pypi.nvidia.com"; exit 1; }; DYNAMO_VERSION="$(printf '%s\n' "$index" | grep -oE '[0-9]+\.[0-9]+\.[0-9]+\.dev[0-9]{8}' | sort -Vu | tail -1)"; case "$DYNAMO_VERSION" in *.*.*.dev????????) : ;; *) echo "ERROR: no X.Y.Z.devYYYYMMDD nightly found in the index (format may have changed)"; exit 1 ;; esac; fi; echo "Installing ai-dynamo==${DYNAMO_VERSION}"; python3 -m pip install --extra-index-url https://pypi.nvidia.com "ai-dynamo==${DYNAMO_VERSION}"; fi # buildkit
RUN |24 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON CUDA_VERSION=13.0.1 INSTALL_DYNAMO=0 DYNAMO_VERSION= /bin/sh -c if [ "${CUDA_VERSION%%.*}" = "12" ]; then python3 -m pip install nixl nixl-cu12 --no-deps ; python3 -m pip install cuda-python==12.9 ; elif [ "${CUDA_VERSION%%.*}" = "13" ]; then python3 -m pip install nixl nixl-cu13 --no-deps ; python3 -m pip install cuda-python==13.2.0 ; fi # buildkit
COPY --chown=root:root --chmod=755 docker/configs/yank /usr/local/bin/yank # buildkit
COPY docker/configs/opt/.vimrc /opt/sglang/.vimrc # buildkit
COPY docker/configs/opt/.tmux.conf /opt/sglang/.tmux.conf # buildkit
COPY docker/configs/opt/.gitconfig /opt/sglang/.gitconfig # buildkit
COPY docker/configs/.zshrc /root/.zshrc # buildkit
RUN |24 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON CUDA_VERSION=13.0.1 INSTALL_DYNAMO=0 DYNAMO_VERSION= /bin/sh -c python3 -m pip install --upgrade "urllib3>=2.6.3" "pillow>=12.1.1" # buildkit
RUN |24 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON CUDA_VERSION=13.0.1 INSTALL_DYNAMO=0 DYNAMO_VERSION= /bin/sh -c apt-get update && apt-get install -y --only-upgrade binutils binutils-common binutils-x86-64-linux-gnu libbinutils libctf0 libctf-nobfd0 libgprofng0 libsframe1 libgnutls30t64 libpam-modules libpam-modules-bin libpam-runtime libpam0g libsqlite3-0 libtasn1-6 dpkg dpkg-dev libdpkg-perl && rm -rf /var/lib/apt/lists/* # buildkit
ARG BRANCH_TYPE
ARG BUILD_TYPE=all
ARG CUDA_VERSION=13.0.1
ARG SGL_VERSION=0.5.15.post1
ARG USE_LATEST_SGLANG
ARG INSTALL_DYNAMO=0
WORKDIR /sgl-workspace
COPY /src /tmp/local_src # buildkit
RUN |24 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON CUDA_VERSION=13.0.1 INSTALL_DYNAMO=0 DYNAMO_VERSION= /bin/sh -c if [ "$BRANCH_TYPE" = "local" ]; then cp -r /tmp/local_src /sgl-workspace/sglang; elif [ "$USE_LATEST_SGLANG" = "1" ]; then git clone --depth=1 https://github.com/sgl-project/sglang.git /sgl-workspace/sglang; elif [ -z "$SGL_VERSION" ]; then echo "ERROR: SGL_VERSION must be set when USE_LATEST_SGLANG=0 and BRANCH_TYPE!=local" && exit 1; else git clone --depth=1 --branch v${SGL_VERSION} https://github.com/sgl-project/sglang.git /sgl-workspace/sglang; fi && rm -rf /tmp/local_src # buildkit
RUN |24 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON CUDA_VERSION=13.0.1 INSTALL_DYNAMO=0 DYNAMO_VERSION= /bin/sh -c cd /sgl-workspace/sglang && if [ "${CUDA_VERSION%%.*}" = "12" ]; then sed -i 's/cuda-python>=13\.0/cuda-python>=12,<13/' python/pyproject.toml && sed -i 's/flashinfer_python\[cu13\]/flashinfer_python[cu12]/' python/pyproject.toml && sed -i 's/nvidia-cutlass-dsl\[cu13\]/nvidia-cutlass-dsl/' python/pyproject.toml; fi && python3 -m pip install --no-deps -e "python[${BUILD_TYPE}]" && kernels lock python && ( success=0; if [ "$(uname -m)" = "aarch64" ]; then echo "Skipping kernels-community/sgl-flash-attn3 cubin download on aarch64 (no variants published upstream); kernels will be JIT-compiled at runtime"; success=1; else for i in 1 2 3; do echo "Attempt $i/3: downloading sgl-kernel cubins..." && kernels download python && success=1 && break; echo "sgl-kernel cubin download failed, retrying in 30s..." && sleep 30; done; if [ "$success" != "1" ]; then echo "WARNING: no matching sgl-flash-attn3 cubin variant for this torch+CUDA; kernels will be JIT-compiled at runtime"; success=1; fi; fi; [ "$success" = "1" ] ) && mkdir -p /root/.cache/huggingface /root/.cache/sglang && ( if [ -f python/kernels.lock ]; then mv python/kernels.lock /root/.cache/sglang/; fi ) && ( find /usr/local/lib/python3.12/dist-packages -type d -name "__pycache__" -exec rm -rf {} + 2>/dev/null || true ) # buildkit
COPY /build/sgl-model-gateway-bin /usr/local/bin/sgl-model-gateway # buildkit
COPY /build/gateway_wheels /tmp/gateway_wheels # buildkit
RUN |24 TARGETARCH=amd64 BUILD_TYPE=all BRANCH_TYPE=remote GRACE_BLACKWELL=0 HOPPER_SBO=0 HOPPER_SBO_DEEPEP_COMMIT=9f2fc4b3182a51044ae7ecb6610f7c9c3258c4d6 DEEPEP_COMMIT=9af0e0d0e74f3577af1979c9b9e1ac2cad0104ee BUILD_AND_DOWNLOAD_PARALLEL=8 SGL_KERNEL_VERSION=0.4.4 SGL_VERSION=0.5.15.post1 SGL_DEEP_GEMM_VERSION=0.1.4 USE_LATEST_SGLANG=0 GDRCOPY_VERSION=2.5.1 PIP_DEFAULT_INDEX= UBUNTU_MIRROR= GITHUB_ARTIFACTORY=github.com INSTALL_FLASHINFER_JIT_CACHE=1 FLASHINFER_VERSION=0.6.12 MOONCAKE_VERSION=0.3.11.post1 MSCCLPP_VERSION=sglang-v0.9.1 MOONCAKE_COMPILE_ARG=-DUSE_HTTP=ON -DUSE_MNNVL=ON -DUSE_CUDA=ON -DWITH_EP=ON CUDA_VERSION=13.0.1 INSTALL_DYNAMO=0 DYNAMO_VERSION= /bin/sh -c if [ "$INSTALL_DYNAMO" = "1" ]; then python3 -m pip install --force-reinstall --no-deps /tmp/gateway_wheels/*.whl; else python3 -m pip install --force-reinstall /tmp/gateway_wheels/*.whl; fi && rm -rf /tmp/gateway_wheels # buildkit
WORKDIR /sgl-workspace/sglang
ARG SGLANG_BUILD_COMMIT=0b3bb0cbe31873994c9f989fddfe2f87ca839fdd
ARG SGLANG_BUILD_URL=https://github.com/sgl-project/sglang/actions/runs/29305409570
ARG SGLANG_IMAGE_TAG=lmsysorg/sglang:v0.5.15.post1
ENV SGLANG_BUILD_COMMIT=0b3bb0cbe31873994c9f989fddfe2f87ca839fdd SGLANG_BUILD_URL=https://github.com/sgl-project/sglang/actions/runs/29305409570 SGLANG_IMAGE_TAG=lmsysorg/sglang:v0.5.15.post1
LABEL org.opencontainers.image.source=https://github.com/sgl-project/sglang org.opencontainers.image.revision=0b3bb0cbe31873994c9f989fddfe2f87ca839fdd org.opencontainers.image.version=lmsysorg/sglang:v0.5.15.post1 org.opencontainers.image.url=https://github.com/sgl-project/sglang/actions/runs/29305409570 ai.sglang.build.commit=0b3bb0cbe31873994c9f989fddfe2f87ca839fdd ai.sglang.build.url=https://github.com/sgl-project/sglang/actions/runs/29305409570 ai.sglang.image.tag=lmsysorg/sglang:v0.5.15.post1

Labels

Key Value
ai.sglang.build.commit 0b3bb0cbe31873994c9f989fddfe2f87ca839fdd
ai.sglang.build.url https://github.com/sgl-project/sglang/actions/runs/29305409570
ai.sglang.image.tag lmsysorg/sglang:v0.5.15.post1
com.nvidia.cudnn.version 9.13.0.50-1
maintainer NVIDIA CORPORATION <cudatools@nvidia.com>
org.opencontainers.image.ref.name ubuntu
org.opencontainers.image.revision 0b3bb0cbe31873994c9f989fddfe2f87ca839fdd
org.opencontainers.image.source https://github.com/sgl-project/sglang
org.opencontainers.image.url https://github.com/sgl-project/sglang/actions/runs/29305409570
org.opencontainers.image.version lmsysorg/sglang:v0.5.15.post1
Details
Container
2026-07-15 22:17:18 -07:00
2
OCI / Docker
linux/amd64
12 GiB
Versions (1) View all
v0.5.15.post1 2026-07-15