Docker拉取命令

docker pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/gpustack/runner:cuda13.0-vllm0.22.1
docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/gpustack/runner:cuda13.0-vllm0.22.1  docker.io/gpustack/runner:cuda13.0-vllm0.22.1

Containerd拉取命令

ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/gpustack/runner:cuda13.0-vllm0.22.1
ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/gpustack/runner:cuda13.0-vllm0.22.1  docker.io/gpustack/runner:cuda13.0-vllm0.22.1

Shell快速替换命令

sed -i 's#gpustack/runner:cuda13.0-vllm0.22.1#swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/gpustack/runner:cuda13.0-vllm0.22.1#' deployment.yaml

Ansible快速分发-Docker

#ansible k8s -m shell -a 'docker pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/gpustack/runner:cuda13.0-vllm0.22.1 && docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/gpustack/runner:cuda13.0-vllm0.22.1  docker.io/gpustack/runner:cuda13.0-vllm0.22.1'

Ansible快速分发-Containerd

#ansible k8s -m shell -a 'ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/gpustack/runner:cuda13.0-vllm0.22.1 && ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/gpustack/runner:cuda13.0-vllm0.22.1  docker.io/gpustack/runner:cuda13.0-vllm0.22.1'

镜像构建历史

# 2026-06-08 18:39:16  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["tini" "--"]
                        
# 2026-06-08 18:39:16  0.00B 设置工作目录为/
WORKDIR /
                        
# 2026-06-08 18:39:16  0.00B 设置环境变量 RAY_EXPERIMENTAL_NOSET_CUDA_VISIBLE_DEVICES SAFETENSORS_FAST_GPU RUNAI_STREAMER_MEMORY_LIMIT RUNAI_STREAMER_LOG_TO_STDERR RUNAI_STREAMER_LOG_LEVEL
ENV RAY_EXPERIMENTAL_NOSET_CUDA_VISIBLE_DEVICES=1 SAFETENSORS_FAST_GPU=1 RUNAI_STREAMER_MEMORY_LIMIT=0 RUNAI_STREAMER_LOG_TO_STDERR=1 RUNAI_STREAMER_LOG_LEVEL=INFO
                        
# 2026-06-08 18:39:16  35.86MB 执行命令并创建新的镜像层
RUN |9 TARGETPLATFORM=linux/amd64 TARGETOS=linux TARGETARCH=amd64 PYTHON_VERSION=3.12 CUDA_VERSION=13.0.1 CUDA_ARCHS= VLLM_VERSION=0.22.1 VLLM_TORCH_VERSION=2.11.0 VLLM_TORCH_CUDA_VERSION=13.0.1 /bin/bash -eo pipefail -c     # Dependencies

    # Install
    cat <<EOT >/tmp/requirements.txt
# audio extras
librosa
soundfile
mistral_common[audio]
EOT
    uv pip install \
        -r /tmp/requirements.txt

    # Cleanup
    rm -rf /var/tmp/* \
        && rm -rf /tmp/*
 # buildkit
                        
# 2026-06-08 18:39:15  27.13KB 执行命令并创建新的镜像层
RUN |9 TARGETPLATFORM=linux/amd64 TARGETOS=linux TARGETARCH=amd64 PYTHON_VERSION=3.12 CUDA_VERSION=13.0.1 CUDA_ARCHS= VLLM_VERSION=0.22.1 VLLM_TORCH_VERSION=2.11.0 VLLM_TORCH_CUDA_VERSION=13.0.1 /bin/bash -eo pipefail -c     # Patch

    tree -hs /workspace/patches
    pushd $(pip show vllm | grep Location: | cut -d" " -f 2) \
        && patch -p1 < /workspace/patches/vllm/*.patch
    if pip show vllm_omni > /dev/null 2>&1; then \
        pushd $(pip show vllm_omni | grep Location: | cut -d" " -f 2) \
            && patch -p1 < /workspace/patches/vllm_omni/*.patch; \
    fi
 # buildkit
                        
# 2026-06-08 18:39:13  0.00B 执行命令并创建新的镜像层
RUN |9 TARGETPLATFORM=linux/amd64 TARGETOS=linux TARGETARCH=amd64 PYTHON_VERSION=3.12 CUDA_VERSION=13.0.1 CUDA_ARCHS= VLLM_VERSION=0.22.1 VLLM_TORCH_VERSION=2.11.0 VLLM_TORCH_CUDA_VERSION=13.0.1 /bin/bash -eo pipefail -c     # Postprocess

    # Review
    uv pip tree \
        --package vllm \
        --package vllm-omni \
        --package flashinfer-python \
        --package torch \
        --package triton \
        --package deep-gemm \
        --package deep-ep \
        --package lmcache \
        --package mooncake-transfer-engine \
        --package ray
 # buildkit
                        
# 2026-06-08 18:39:13  195.40MB 执行命令并创建新的镜像层
RUN |9 TARGETPLATFORM=linux/amd64 TARGETOS=linux TARGETARCH=amd64 PYTHON_VERSION=3.12 CUDA_VERSION=13.0.1 CUDA_ARCHS= VLLM_VERSION=0.22.1 VLLM_TORCH_VERSION=2.11.0 VLLM_TORCH_CUDA_VERSION=13.0.1 /bin/bash -eo pipefail -c     # CuPy
    # ray[cgraph] pulls cupy-cuda12x while the base already ships cupy-cuda13x; both share
    # the same cupy/ tree, so uninstalling one breaks the other. Purge both, then reinstall
    # the CUDA-matching variant at the version vLLM pinned in the base (its cupy-cuda13x),
    # so cu129 also gets that pinned version instead of ray's unconstrained cupy-cuda12x.

    IFS="." read -r CUDA_MAJOR CUDA_MINOR CUDA_PATCH <<< "${CUDA_VERSION}"
    PURELIB="$(python -c 'import sysconfig; print(sysconfig.get_paths()["purelib"])')"
    CUPY="cupy-cuda${CUDA_MAJOR}x"
    CUPY_VER="$(uv pip show cupy-cuda13x 2>/dev/null | awk '/^Version:/{print $2}' || true)"
    uv pip uninstall cupy-cuda12x cupy-cuda13x || true
    rm -rf "${PURELIB}"/cupy "${PURELIB}"/cupyx "${PURELIB}"/cupy_backends
    # cupy-cuda12x and cupy-cuda13x share the same version number, so reuse the base's
    # pinned version and install only the variant matching the CUDA major we build for.
    # Fail loudly if the base no longer ships cupy, rather than installing an unpinned latest.
    if [[ -z "${CUPY_VER}" ]]; then
        echo "cupy-cuda13x not found in base image; refusing to install unpinned cupy" >&2
        exit 1
    fi
    uv pip install "${CUPY}==${CUPY_VER}"

    # Review
    uv pip list | grep -i cupy

    # Cleanup
    rm -rf /var/tmp/* \
        && rm -rf /tmp/*
 # buildkit
                        
# 2026-06-08 18:39:10  549.95MB 执行命令并创建新的镜像层
RUN |9 TARGETPLATFORM=linux/amd64 TARGETOS=linux TARGETARCH=amd64 PYTHON_VERSION=3.12 CUDA_VERSION=13.0.1 CUDA_ARCHS= VLLM_VERSION=0.22.1 VLLM_TORCH_VERSION=2.11.0 VLLM_TORCH_CUDA_VERSION=13.0.1 /bin/bash -eo pipefail -c     # Omni

    if [[ ! -d /omni/workspace ]]; then
        echo "Skipping vLLM Omni installation for ${TARGETARCH}..."
        exit 0
    fi

    # Install
    uv pip install --no-build-isolation \
        /omni/workspace/*.whl

    # Dependencies
    cat <<EOT >/tmp/requirements.txt
onnxruntime
sox
EOT
    uv pip install \
        -r /tmp/requirements.txt

    # Cleanup
    rm -rf /var/tmp/* \
        && rm -rf /tmp/*
 # buildkit
                        
# 2026-06-08 18:38:31  491.59MB 执行命令并创建新的镜像层
RUN |9 TARGETPLATFORM=linux/amd64 TARGETOS=linux TARGETARCH=amd64 PYTHON_VERSION=3.12 CUDA_VERSION=13.0.1 CUDA_ARCHS= VLLM_VERSION=0.22.1 VLLM_TORCH_VERSION=2.11.0 VLLM_TORCH_CUDA_VERSION=13.0.1 /bin/bash -eo pipefail -c     # Ray

    # Install Ray Client and Default.
    # Pinned to 2.54.0: ray 2.55 (ray-project/ray#61029) breaks distributed
    # ray.init when the driver has no co-located raylet (gpustack split containers).
    RAY_VERSION=2.54.0
    cat <<EOT >/tmp/requirements.txt
ray[cgraph]==${RAY_VERSION}
ray[client]==${RAY_VERSION}
ray[default]==${RAY_VERSION}
EOT
    uv pip install \
        -r /tmp/requirements.txt

    # Cleanup
    rm -rf /var/tmp/* \
        && rm -rf /tmp/*
 # buildkit
                        
# 2026-06-08 18:38:26  0.00B 定义构建参数
ARG TARGETARCH=amd64
                        
# 2026-06-08 18:38:26  0.00B 定义构建参数
ARG TARGETOS=linux
                        
# 2026-06-08 18:38:26  0.00B 定义构建参数
ARG TARGETPLATFORM=linux/amd64
                        
# 2026-06-08 18:38:26  0.00B 
SHELL [/bin/bash -eo pipefail -c]
                        
# 2026-06-08 18:38:26  0.00B 设置环境变量 VLLM_VERSION VLLM_TORCH_VERSION VLLM_TORCH_CUDA_VERSION
ENV VLLM_VERSION=0.22.1 VLLM_TORCH_VERSION=2.11.0 VLLM_TORCH_CUDA_VERSION=13.0.1
                        
# 2026-06-08 18:38:26  0.00B 定义构建参数
ARG VLLM_TORCH_CUDA_VERSION=13.0.1
                        
# 2026-06-08 18:38:26  0.00B 定义构建参数
ARG VLLM_TORCH_VERSION=2.11.0
                        
# 2026-06-08 18:38:26  0.00B 定义构建参数
ARG VLLM_VERSION=0.22.1
                        
# 2026-06-08 18:38:26  0.00B 设置环境变量 UV_SYSTEM_PYTHON UV_PRERELEASE UV_SKIP_WHEEL_FILENAME_CHECK UV_NO_CACHE UV_HTTP_TIMEOUT UV_INDEX_STRATEGY
ENV UV_SYSTEM_PYTHON=1 UV_PRERELEASE=allow UV_SKIP_WHEEL_FILENAME_CHECK=1 UV_NO_CACHE=1 UV_HTTP_TIMEOUT=500 UV_INDEX_STRATEGY=unsafe-best-match
                        
# 2026-06-08 18:38:26  0.00B 设置环境变量 CUDA_HOME CUDA_VERSION CUDA_ARCHS
ENV CUDA_HOME=/usr/local/cuda CUDA_VERSION=13.0.1 CUDA_ARCHS=
                        
# 2026-06-08 18:38:26  0.00B 定义构建参数
ARG CUDA_ARCHS
                        
# 2026-06-08 18:38:26  0.00B 定义构建参数
ARG CUDA_VERSION=13.0.1
                        
# 2026-06-08 18:38:26  84.46MB 执行命令并创建新的镜像层
RUN |4 TARGETPLATFORM=linux/amd64 TARGETOS=linux TARGETARCH=amd64 PYTHON_VERSION=3.12 /bin/bash -eo pipefail -c     # Buildkit

    cat <<EOT >/tmp/requirements.txt
build
cmake<4
wheel
pybind11<3
Cython
EOT
    pip install -r /tmp/requirements.txt

    # Cleanup
    rm -rf /var/tmp/* \
        && rm -rf /tmp/*
 # buildkit
                        
# 2026-06-08 18:38:22  0.00B 设置环境变量 PIP_NO_CACHE_DIR PIP_DISABLE_PIP_VERSION_CHECK PIP_ROOT_USER_ACTION
ENV PIP_NO_CACHE_DIR=1 PIP_DISABLE_PIP_VERSION_CHECK=1 PIP_ROOT_USER_ACTION=ignore
                        
# 2026-06-08 18:38:22  14.51KB 执行命令并创建新的镜像层
RUN |4 TARGETPLATFORM=linux/amd64 TARGETOS=linux TARGETARCH=amd64 PYTHON_VERSION=3.12 /bin/bash -eo pipefail -c     # Python

    # Update alternatives
    if ! command -v python >/dev/null 2>&1 \
        && command -v python${PYTHON_VERSION} >/dev/null 2>&1; then
        update-alternatives --install /usr/bin/python python $(which python${PYTHON_VERSION}) 1
    fi
 # buildkit
                        
# 2026-06-08 18:38:22  0.00B 设置环境变量 PYTHON_VERSION
ENV PYTHON_VERSION=3.12
                        
# 2026-06-08 18:38:22  0.00B 定义构建参数
ARG PYTHON_VERSION=3.12
                        
# 2026-06-08 18:38:22  230.08MB 执行命令并创建新的镜像层
RUN |3 TARGETPLATFORM=linux/amd64 TARGETOS=linux TARGETARCH=amd64 /bin/bash -eo pipefail -c     # Tools

    # Refresh
    apt-get update -y && apt-get install -y --no-install-recommends \
        software-properties-common apt-transport-https \
        ca-certificates gnupg2 lsb-release gnupg-agent \
      && apt-get update -y

    # Install
    apt-get install -y --no-install-recommends \
        ca-certificates build-essential binutils bash openssl \
        curl wget aria2 \
        git git-lfs \
        unzip xz-utils \
        tzdata locales \
        iproute2 iputils-ping ifstat net-tools dnsutils pciutils ipmitool \
        rdma-core rdmacm-utils infiniband-diags \
        procps sysstat htop \
        tini vim jq bc tree

    # Update locale
    localedef -i en_US -c -f UTF-8 -A /usr/share/locale/locale.alias en_US.UTF-8

    # Update timezone
    rm -f /etc/localtime \
        && ln -sf /usr/share/zoneinfo/Asia/Shanghai /etc/localtime \
        && echo "Asia/Shanghai" > /etc/timezone \
        && dpkg-reconfigure --frontend noninteractive tzdata

    # Cleanup
    rm -rf /var/tmp/* \
        && rm -rf /tmp/* \
        && rm -rf /var/cache/apt
 # buildkit
                        
# 2026-06-08 18:38:22  0.00B 设置环境变量 DEBIAN_FRONTEND LANG LANGUAGE LC_ALL
ENV DEBIAN_FRONTEND=noninteractive LANG=en_US.UTF-8 LANGUAGE=en_US:en LC_ALL=en_US.UTF-8
                        
# 2026-06-08 18:38:22  0.00B 定义构建参数
ARG TARGETARCH=amd64
                        
# 2026-06-08 18:38:22  0.00B 定义构建参数
ARG TARGETOS=linux
                        
# 2026-06-08 18:38:22  0.00B 定义构建参数
ARG TARGETPLATFORM=linux/amd64
                        
# 2026-06-08 18:38:22  0.00B 
SHELL [/bin/bash -eo pipefail -c]
                        
# 2026-06-05 05:53:51  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["vllm" "serve"]
                        
# 2026-06-05 05:53:51  0.00B 添加元数据标签
LABEL org.opencontainers.image.source=https://github.com/vllm-project/vllm org.opencontainers.image.revision=0decac0d96c42b49572498019f0a0e3600f50398 org.opencontainers.image.version=vllm/vllm-openai:v0.22.1-ubuntu2404 org.opencontainers.image.url=https://buildkite.com/vllm/release-v2/builds/2333 ai.vllm.build.commit=0decac0d96c42b49572498019f0a0e3600f50398 ai.vllm.build.pipeline=019d130e-464e-4ff7-b84b-492992c0c06b ai.vllm.build.url=https://buildkite.com/vllm/release-v2/builds/2333 ai.vllm.image.tag=vllm/vllm-openai:v0.22.1-ubuntu2404
                        
# 2026-06-05 05:53:51  0.00B 设置环境变量 VLLM_BUILD_COMMIT VLLM_BUILD_PIPELINE VLLM_BUILD_URL VLLM_IMAGE_TAG
ENV VLLM_BUILD_COMMIT=0decac0d96c42b49572498019f0a0e3600f50398 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/2333 VLLM_IMAGE_TAG=vllm/vllm-openai:v0.22.1-ubuntu2404
                        
# 2026-06-05 05:53:51  0.00B 设置环境变量 VLLM_USAGE_SOURCE
ENV VLLM_USAGE_SOURCE=production-docker-image
                        
# 2026-06-05 05:53:51  1.58GB 执行命令并创建新的镜像层
RUN |14 TARGETPLATFORM=linux/amd64 INSTALL_KV_CONNECTORS=true CUDA_VERSION=13.0.2 VLLM_BUILD_COMMIT=0decac0d96c42b49572498019f0a0e3600f50398 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/2333 VLLM_IMAGE_TAG=vllm/vllm-openai:v0.22.1-ubuntu2404 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=7.5 8.0 8.6 8.9 9.0 10.0 12.0+PTX MOONCAKE_WHEEL_AARCH64=https://vllm-wheels.s3.amazonaws.com/mooncake/mooncake_transfer_engine-0.3.10.post2-0da9dfea3-cp312-cp312-manylinux_2_39_aarch64.whl MOONCAKE_WHEEL_X86_64=https://vllm-wheels.s3.amazonaws.com/mooncake/mooncake_transfer_engine-0.3.10.post2-0da9dfea3-cp312-cp312-manylinux_2_35_x86_64.whl /bin/sh -c if [ "$INSTALL_KV_CONNECTORS" = "true" ]; then         if [ "$TARGETPLATFORM" = "linux/arm64" ]; then             WHEEL="${MOONCAKE_WHEEL_AARCH64}";         else             WHEEL="${MOONCAKE_WHEEL_X86_64}";         fi &&         if [ -n "${WHEEL}" ]; then             uv pip install --system "${WHEEL}" &&             CUDA_MAJOR="${CUDA_VERSION%%.*}" &&             if [ ! -f /usr/local/cuda/lib64/libcudart.so ] &&                [ -f "/usr/local/cuda/lib64/libcudart.so.${CUDA_MAJOR}" ]; then                 ln -s "libcudart.so.${CUDA_MAJOR}" /usr/local/cuda/lib64/libcudart.so;             fi;         fi;     fi # buildkit
                        
# 2026-06-05 05:53:43  0.00B 定义构建参数
ARG MOONCAKE_WHEEL_X86_64
                        
# 2026-06-05 05:53:43  0.00B 定义构建参数
ARG MOONCAKE_WHEEL_AARCH64
                        
# 2026-06-05 05:53:43  729.57MB 执行命令并创建新的镜像层
RUN |12 TARGETPLATFORM=linux/amd64 INSTALL_KV_CONNECTORS=true CUDA_VERSION=13.0.2 VLLM_BUILD_COMMIT=0decac0d96c42b49572498019f0a0e3600f50398 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/2333 VLLM_IMAGE_TAG=vllm/vllm-openai:v0.22.1-ubuntu2404 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=7.5 8.0 8.6 8.9 9.0 10.0 12.0+PTX /bin/sh -c CUDA_MAJOR="${CUDA_VERSION%%.*}";     CUDA_VERSION_DASH=$(echo $CUDA_VERSION | cut -d. -f1,2 | tr '.' '-');     CUDA_HOME=/usr/local/cuda;     BUILD_PKGS="libcusparse-dev-${CUDA_VERSION_DASH}                 libcublas-dev-${CUDA_VERSION_DASH}                 libcusolver-dev-${CUDA_VERSION_DASH}";     if [ "$INSTALL_KV_CONNECTORS" = "true" ]; then         uv pip install --system -r /tmp/kv_connectors.txt --no-build || (             apt-get update -y &&             apt-get install -y --no-install-recommends --allow-change-held-packages ${BUILD_PKGS} &&             uv pip install --system -r /tmp/kv_connectors.txt --no-build-isolation &&             apt-get purge -y ${BUILD_PKGS} &&             rm -rf /var/lib/apt/lists/*         );         uv pip install --system --force-reinstall --no-deps nixl-cu${CUDA_MAJOR};     fi # buildkit
                        
# 2026-06-05 05:53:37  0.00B 设置环境变量 TORCH_CUDA_ARCH_LIST
ENV TORCH_CUDA_ARCH_LIST=7.5 8.0 8.6 8.9 9.0 10.0 12.0+PTX
                        
# 2026-06-05 05:53:37  0.00B 定义构建参数
ARG torch_cuda_arch_list=7.5 8.0 8.6 8.9 9.0 10.0 11.0 12.0+PTX
                        
# 2026-06-05 05:53:37  0.00B 设置环境变量 UV_HTTP_TIMEOUT
ENV UV_HTTP_TIMEOUT=500
                        
# 2026-06-05 05:53:37  0.00B 定义构建参数
ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
                        
# 2026-06-05 05:53:37  0.00B 定义构建参数
ARG PIP_INDEX_URL UV_INDEX_URL
                        
# 2026-06-05 05:53:37  0.00B 定义构建参数
ARG VLLM_IMAGE_TAG
                        
# 2026-06-05 05:53:37  0.00B 定义构建参数
ARG VLLM_BUILD_URL
                        
# 2026-06-05 05:53:37  0.00B 定义构建参数
ARG VLLM_BUILD_PIPELINE
                        
# 2026-06-05 05:53:37  0.00B 定义构建参数
ARG VLLM_BUILD_COMMIT
                        
# 2026-06-05 05:53:37  0.00B 定义构建参数
ARG CUDA_VERSION
                        
# 2026-06-05 05:53:37  0.00B 定义构建参数
ARG INSTALL_KV_CONNECTORS=false
                        
# 2026-06-05 05:53:37  0.00B 定义构建参数
ARG TARGETPLATFORM
                        
# 2026-06-05 05:53:37  35.09KB 复制新文件或目录到容器中
COPY ./vllm/collect_env.py . # buildkit
                        
# 2026-06-05 05:53:37  1.05MB 复制新文件或目录到容器中
COPY benchmarks benchmarks # buildkit
                        
# 2026-06-05 05:53:37  1.31MB 复制新文件或目录到容器中
COPY examples examples # buildkit
                        
# 2026-06-05 05:53:37  0.00B 设置环境变量 LD_LIBRARY_PATH
ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
                        
# 2026-06-05 05:53:37  1.55GB 执行命令并创建新的镜像层
RUN |22 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl FLASHINFER_VERSION=0.6.11.post2 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/amd64 BITSANDBYTES_VERSION_X86=0.46.1 BITSANDBYTES_VERSION_ARM64=0.42.0 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= /bin/sh -c flashinfer show-config && flashinfer download-cubin # buildkit
                        
# 2026-06-05 05:45:23  30.28MB 执行命令并创建新的镜像层
RUN |22 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl FLASHINFER_VERSION=0.6.11.post2 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/amd64 BITSANDBYTES_VERSION_X86=0.46.1 BITSANDBYTES_VERSION_ARM64=0.42.0 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= /bin/sh -c uv pip install --system ep_kernels/dist/*.whl --verbose         --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') # buildkit
                        
# 2026-06-05 05:45:22  0.00B 设置环境变量 LD_LIBRARY_PATH
ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
                        
# 2026-06-05 05:45:22  0.00B 执行命令并创建新的镜像层
RUN |22 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl FLASHINFER_VERSION=0.6.11.post2 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/amd64 BITSANDBYTES_VERSION_X86=0.46.1 BITSANDBYTES_VERSION_ARM64=0.42.0 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= /bin/sh -c . /etc/environment && uv pip list # buildkit
                        
# 2026-06-05 05:45:21  591.30MB 执行命令并创建新的镜像层
RUN |22 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl FLASHINFER_VERSION=0.6.11.post2 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/amd64 BITSANDBYTES_VERSION_X86=0.46.1 BITSANDBYTES_VERSION_ARM64=0.42.0 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= /bin/sh -c if [ "${PYTORCH_NIGHTLY}" = "1" ]; then         echo "Installing torch nightly..."         && uv pip install --system $(cat torch_lib_versions.txt | xargs) --pre         --index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')         && echo "Installing vLLM..."         && uv pip install --system dist/*.whl --verbose         --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.');     else         echo "Installing vLLM..."         && uv pip install --system dist/*.whl --verbose         --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.');     fi # buildkit
                        
# 2026-06-05 05:32:28  71.00B 复制新文件或目录到容器中
COPY /workspace/torch_lib_versions.txt torch_lib_versions.txt # buildkit
                        
# 2026-06-05 05:32:28  0.00B 定义构建参数
ARG PYTORCH_NIGHTLY
                        
# 2026-06-05 05:32:28  0.00B 定义构建参数
ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER
                        
# 2026-06-05 05:32:28  0.00B 定义构建参数
ARG PYTORCH_CUDA_INDEX_BASE_URL
                        
# 2026-06-05 05:32:28  0.00B 定义构建参数
ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
                        
# 2026-06-05 05:32:28  0.00B 定义构建参数
ARG PIP_INDEX_URL UV_INDEX_URL
                        
# 2026-06-05 05:32:28  388.77MB 执行命令并创建新的镜像层
RUN |14 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl FLASHINFER_VERSION=0.6.11.post2 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/amd64 BITSANDBYTES_VERSION_X86=0.46.1 BITSANDBYTES_VERSION_ARM64=0.42.0 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 /bin/sh -c if [ "$TARGETPLATFORM" = "linux/arm64" ]; then         BITSANDBYTES_VERSION="${BITSANDBYTES_VERSION_ARM64}";     else         BITSANDBYTES_VERSION="${BITSANDBYTES_VERSION_X86}";     fi;     uv pip install --system accelerate modelscope         "bitsandbytes>=${BITSANDBYTES_VERSION}" "timm${TIMM_VERSION}" "runai-model-streamer[s3,gcs,azure]${RUNAI_MODEL_STREAMER_VERSION}" # buildkit
                        
# 2026-06-05 05:32:24  0.00B 定义构建参数
ARG RUNAI_MODEL_STREAMER_VERSION=>=0.15.7
                        
# 2026-06-05 05:32:24  0.00B 定义构建参数
ARG TIMM_VERSION=>=1.0.17
                        
# 2026-06-05 05:32:24  0.00B 定义构建参数
ARG BITSANDBYTES_VERSION_ARM64=0.42.0
                        
# 2026-06-05 05:32:24  0.00B 定义构建参数
ARG BITSANDBYTES_VERSION_X86=0.46.1
                        
# 2026-06-05 05:32:24  2.47MB 执行命令并创建新的镜像层
RUN |10 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl FLASHINFER_VERSION=0.6.11.post2 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/amd64 /bin/sh -c set -eux;     case "${TARGETPLATFORM}" in       linux/arm64) UUARCH="aarch64" ;;       linux/amd64) UUARCH="x64" ;;       *) echo "Unsupported TARGETPLATFORM: ${TARGETPLATFORM}" >&2; exit 1 ;;     esac;     /tmp/install_gdrcopy.sh "${GDRCOPY_OS_VERSION}" "${GDRCOPY_CUDA_VERSION}" "${UUARCH}" &&     rm /tmp/install_gdrcopy.sh # buildkit
                        
# 2026-06-05 05:32:19  1.44KB 复制新文件或目录到容器中
COPY tools/install_gdrcopy.sh /tmp/install_gdrcopy.sh # buildkit
                        
# 2026-06-05 05:32:18  0.00B 定义构建参数
ARG TARGETPLATFORM
                        
# 2026-06-05 05:32:18  0.00B 定义构建参数
ARG GDRCOPY_OS_VERSION=Ubuntu22_04
                        
# 2026-06-05 05:32:18  0.00B 定义构建参数
ARG GDRCOPY_CUDA_VERSION=12.8
                        
# 2026-06-05 05:32:18  8.20GB 执行命令并创建新的镜像层
RUN |7 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl FLASHINFER_VERSION=0.6.11.post2 /bin/sh -c uv pip install --system flashinfer-jit-cache==${FLASHINFER_VERSION}         --index-url https://flashinfer.ai/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') # buildkit
                        
# 2026-06-05 05:31:09  0.00B 定义构建参数
ARG FLASHINFER_VERSION=0.6.11.post2
                        
# 2026-06-05 05:31:09  8.26GB 执行命令并创建新的镜像层
RUN |6 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl /bin/sh -c if [ "$(echo $CUDA_VERSION | cut -d. -f1)" = "12" ]; then         sed -i 's/^nvidia-cutlass-dsl\[cu13\]/nvidia-cutlass-dsl/' /tmp/requirements-cuda.txt;         sed -i 's/^humming-kernels\[cu13\]/humming-kernels[cu12]/' /tmp/requirements-cuda.txt;     fi &&     uv pip install --system -r /tmp/requirements-cuda.txt         --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') &&     rm /tmp/requirements-cuda.txt /tmp/common.txt # buildkit
                        
# 2026-06-05 05:29:59  971.00B 复制新文件或目录到容器中
COPY requirements/cuda.txt /tmp/requirements-cuda.txt # buildkit
                        
# 2026-06-05 05:29:59  3.07KB 复制新文件或目录到容器中
COPY requirements/common.txt /tmp/common.txt # buildkit
                        
# 2026-06-05 05:29:59  0.00B 定义构建参数
ARG PYTORCH_CUDA_INDEX_BASE_URL
                        
# 2026-06-05 05:29:59  0.00B 设置环境变量 VLLM_ENABLE_CUDA_COMPATIBILITY
ENV VLLM_ENABLE_CUDA_COMPATIBILITY=0
                        
# 2026-06-05 05:29:59  3.69KB 执行命令并创建新的镜像层
RUN |5 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c chmod 0755 /usr/local/bin/vllm-nonroot-entrypoint.sh # buildkit
                        
# 2026-06-05 05:29:58  3.69KB 复制新文件或目录到容器中
COPY docker/entrypoints/vllm-nonroot-entrypoint.sh /usr/local/bin/vllm-nonroot-entrypoint.sh # buildkit
                        
# 2026-06-05 05:29:58  9.38KB 执行命令并创建新的镜像层
RUN |5 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c useradd --uid 2000 --gid 0 --create-home --home-dir /home/vllm         --shell /bin/bash vllm     && mkdir -p /home/vllm/.cache /home/vllm/.config     && chown -R 2000:0 /home/vllm     && chmod -R g+rwX /home/vllm     && chgrp 0 /etc/passwd /etc/group     && chmod g=u /etc/passwd /etc/group # buildkit
                        
# 2026-06-05 05:29:57  0.00B 执行命令并创建新的镜像层
RUN |5 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c mkdir -p "${UV_PYTHON_INSTALL_DIR}" "${UV_CACHE_DIR}"     && chgrp -R 0 /opt/uv     && chmod -R g+rwX,a+rX /opt/uv # buildkit
                        
# 2026-06-05 05:29:56  0.00B 设置环境变量 UV_CACHE_DIR
ENV UV_CACHE_DIR=/opt/uv/cache
                        
# 2026-06-05 05:29:56  0.00B 设置环境变量 UV_PYTHON_INSTALL_DIR
ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
                        
# 2026-06-05 05:29:56  0.00B 设置环境变量 UV_LINK_MODE
ENV UV_LINK_MODE=copy
                        
# 2026-06-05 05:29:56  0.00B 设置环境变量 UV_INDEX_STRATEGY
ENV UV_INDEX_STRATEGY=unsafe-best-match
                        
# 2026-06-05 05:29:56  0.00B 设置环境变量 UV_HTTP_TIMEOUT
ENV UV_HTTP_TIMEOUT=500
                        
# 2026-06-05 05:29:56  86.75MB 执行命令并创建新的镜像层
RUN |5 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c python3 -m pip install uv # buildkit
                        
# 2026-06-05 05:29:54  3.08GB 执行命令并创建新的镜像层
RUN |5 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c CUDA_VERSION_DASH=$(echo $CUDA_VERSION | cut -d. -f1,2 | tr '.' '-') &&     CUDA_VERSION_SHORT=$(echo $CUDA_VERSION | cut -d. -f1,2) &&     apt-get update -y &&     apt-get install -y --no-install-recommends --allow-change-held-packages         cuda-nvcc-${CUDA_VERSION_DASH}         cuda-cudart-${CUDA_VERSION_DASH}         cuda-nvrtc-${CUDA_VERSION_DASH}         cuda-cuobjdump-${CUDA_VERSION_DASH}         libcurand-dev-${CUDA_VERSION_DASH}         libcublas-dev-${CUDA_VERSION_DASH}         libnuma-dev         numactl &&     NCCL_VER=$(apt-cache madison libnccl-dev | grep "+cuda${CUDA_VERSION_SHORT}" | head -1 | awk -F'|' '{gsub(/^ +| +$/, "", $2); print $2}') &&     apt-get install -y --no-install-recommends --allow-change-held-packages libnccl-dev=${NCCL_VER} libnccl2=${NCCL_VER} &&     rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2026-06-05 05:29:18  647.74MB 执行命令并创建新的镜像层
RUN |5 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c apt-get update -y     && apt-get install -y --no-install-recommends         software-properties-common         curl         sudo         ffmpeg         libsm6         libxext6         libgl1     && if [ ! -z ${DEADSNAKES_MIRROR_URL} ] ; then         if [ ! -z "${DEADSNAKES_GPGKEY_URL}" ] ; then             mkdir -p -m 0755 /etc/apt/keyrings ;             curl -L ${DEADSNAKES_GPGKEY_URL} | gpg --dearmor > /etc/apt/keyrings/deadsnakes.gpg ;             sudo chmod 644 /etc/apt/keyrings/deadsnakes.gpg ;             echo "deb [signed-by=/etc/apt/keyrings/deadsnakes.gpg] ${DEADSNAKES_MIRROR_URL} $(lsb_release -cs) main" > /etc/apt/sources.list.d/deadsnakes.list ;         fi ;     else         for i in 1 2 3; do             add-apt-repository -y ppa:deadsnakes/ppa && break ||             { echo "Attempt $i failed, retrying in 5s..."; sleep 5; };         done ;     fi     && apt-get update -y     && apt-get install -y --no-install-recommends         python${PYTHON_VERSION}         python${PYTHON_VERSION}-dev         python${PYTHON_VERSION}-venv         libibverbs-dev     && rm -rf /var/lib/apt/lists/*     && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1     && update-alternatives --set python3 /usr/bin/python${PYTHON_VERSION}     && ln -sf /usr/bin/python${PYTHON_VERSION}-config /usr/bin/python3-config     && rm -f /usr/lib/python${PYTHON_VERSION}/EXTERNALLY-MANAGED     && curl -sS ${GET_PIP_URL} | python${PYTHON_VERSION}     && python3 --version && python3 -m pip --version # buildkit
                        
# 2026-06-05 05:28:17  136.00B 执行命令并创建新的镜像层
RUN |5 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c PYTHON_VERSION_STR=$(echo ${PYTHON_VERSION} | sed 's/\.//g') &&     echo "export PYTHON_VERSION_STR=${PYTHON_VERSION_STR}" >> /etc/environment # buildkit
                        
# 2026-06-05 05:28:17  0.00B 设置工作目录为/vllm-workspace
WORKDIR /vllm-workspace
                        
# 2026-06-05 05:28:17  0.00B 设置环境变量 DEBIAN_FRONTEND
ENV DEBIAN_FRONTEND=noninteractive
                        
# 2026-06-05 05:28:17  0.00B 定义构建参数
ARG GET_PIP_URL
                        
# 2026-06-05 05:28:17  0.00B 定义构建参数
ARG DEADSNAKES_GPGKEY_URL
                        
# 2026-06-05 05:28:17  0.00B 定义构建参数
ARG DEADSNAKES_MIRROR_URL
                        
# 2026-06-05 05:28:17  0.00B 定义构建参数
ARG PYTHON_VERSION
                        
# 2026-06-05 05:28:17  0.00B 定义构建参数
ARG CUDA_VERSION
                        
# 2025-10-11 00:48:26  0.00B 设置环境变量 NVIDIA_DRIVER_CAPABILITIES
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
                        
# 2025-10-11 00:48:26  0.00B 设置环境变量 NVIDIA_VISIBLE_DEVICES
ENV NVIDIA_VISIBLE_DEVICES=all
                        
# 2025-10-11 00:48:26  17.29KB 复制新文件或目录到容器中
COPY NGC-DL-CONTAINER-LICENSE / # buildkit
                        
# 2025-10-11 00:48:26  0.00B 设置环境变量 LD_LIBRARY_PATH
ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
                        
# 2025-10-11 00:48:26  0.00B 设置环境变量 PATH
ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
                        
# 2025-10-11 00:48:26  22.00B 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c echo "/usr/local/cuda/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit
                        
# 2025-10-11 00:48:26  322.86MB 执行命令并创建新的镜像层
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
                        
# 2025-10-11 00:48:09  0.00B 设置环境变量 CUDA_VERSION
ENV CUDA_VERSION=13.0.2
                        
# 2025-10-11 00:48:09  10.26MB 执行命令并创建新的镜像层
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
                        
# 2025-10-11 00:48:09  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2025-10-11 00:48:09  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2025-10-11 00:48:09  0.00B 设置环境变量 NV_CUDA_CUDART_VERSION
ENV NV_CUDA_CUDART_VERSION=13.0.96-1
                        
# 2025-10-11 00:48:09  0.00B 设置环境变量 NVIDIA_REQUIRE_CUDA brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand
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
                        
# 2025-10-11 00:48:09  0.00B 设置环境变量 NVARCH
ENV NVARCH=x86_64
                        
# 2025-10-01 21:01:37  0.00B 
/bin/sh -c #(nop)  CMD ["/bin/bash"]
                        
# 2025-10-01 21:01:37  78.12MB 
/bin/sh -c #(nop) ADD file:249778a1782b02a1c2bcf9f292f5778d81442a53c3de1958d712f10baf7e0b60 in / 
                        
# 2025-10-01 21:01:35  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.version=24.04
                        
# 2025-10-01 21:01:35  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.ref.name=ubuntu
                        
# 2025-10-01 21:01:35  0.00B 
/bin/sh -c #(nop)  ARG LAUNCHPAD_BUILD_ARCH
                        
# 2025-10-01 21:01:35  0.00B 
/bin/sh -c #(nop)  ARG RELEASE
                        
                    

镜像信息

{
    "Id": "sha256:c28e3857277b4e9c95d003826fba157b192f3333dbbbee8a28525cf65c0ae1d7",
    "RepoTags": [
        "gpustack/runner:cuda13.0-vllm0.22.1",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/gpustack/runner:cuda13.0-vllm0.22.1"
    ],
    "RepoDigests": [
        "gpustack/runner@sha256:cb452365834e85eb6cf65f590dc8dde11f98a609099673e0354fb9e69b878898",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/gpustack/runner@sha256:947063da60ccd3eb5b4169b4fd258db999b7dd08813070c74673c9ff80dc8b74"
    ],
    "Parent": "",
    "Comment": "buildkit.dockerfile.v0",
    "Created": "2026-06-08T10:39:16.792995996Z",
    "Container": "",
    "ContainerConfig": null,
    "DockerVersion": "",
    "Author": "",
    "Config": {
        "Hostname": "",
        "Domainname": "",
        "User": "",
        "AttachStdin": false,
        "AttachStdout": false,
        "AttachStderr": false,
        "Tty": false,
        "OpenStdin": false,
        "StdinOnce": false,
        "Env": [
            "PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",
            "NVARCH=x86_64",
            "NVIDIA_REQUIRE_CUDA=cuda\u003e=13.0 brand=unknown,driver\u003e=535,driver\u003c536 brand=grid,driver\u003e=535,driver\u003c536 brand=tesla,driver\u003e=535,driver\u003c536 brand=nvidia,driver\u003e=535,driver\u003c536 brand=quadro,driver\u003e=535,driver\u003c536 brand=quadrortx,driver\u003e=535,driver\u003c536 brand=nvidiartx,driver\u003e=535,driver\u003c536 brand=vapps,driver\u003e=535,driver\u003c536 brand=vpc,driver\u003e=535,driver\u003c536 brand=vcs,driver\u003e=535,driver\u003c536 brand=vws,driver\u003e=535,driver\u003c536 brand=cloudgaming,driver\u003e=535,driver\u003c536 brand=unknown,driver\u003e=550,driver\u003c551 brand=grid,driver\u003e=550,driver\u003c551 brand=tesla,driver\u003e=550,driver\u003c551 brand=nvidia,driver\u003e=550,driver\u003c551 brand=quadro,driver\u003e=550,driver\u003c551 brand=quadrortx,driver\u003e=550,driver\u003c551 brand=nvidiartx,driver\u003e=550,driver\u003c551 brand=vapps,driver\u003e=550,driver\u003c551 brand=vpc,driver\u003e=550,driver\u003c551 brand=vcs,driver\u003e=550,driver\u003c551 brand=vws,driver\u003e=550,driver\u003c551 brand=cloudgaming,driver\u003e=550,driver\u003c551 brand=unknown,driver\u003e=565,driver\u003c566 brand=grid,driver\u003e=565,driver\u003c566 brand=tesla,driver\u003e=565,driver\u003c566 brand=nvidia,driver\u003e=565,driver\u003c566 brand=quadro,driver\u003e=565,driver\u003c566 brand=quadrortx,driver\u003e=565,driver\u003c566 brand=nvidiartx,driver\u003e=565,driver\u003c566 brand=vapps,driver\u003e=565,driver\u003c566 brand=vpc,driver\u003e=565,driver\u003c566 brand=vcs,driver\u003e=565,driver\u003c566 brand=vws,driver\u003e=565,driver\u003c566 brand=cloudgaming,driver\u003e=565,driver\u003c566 brand=unknown,driver\u003e=570,driver\u003c571 brand=grid,driver\u003e=570,driver\u003c571 brand=tesla,driver\u003e=570,driver\u003c571 brand=nvidia,driver\u003e=570,driver\u003c571 brand=quadro,driver\u003e=570,driver\u003c571 brand=quadrortx,driver\u003e=570,driver\u003c571 brand=nvidiartx,driver\u003e=570,driver\u003c571 brand=vapps,driver\u003e=570,driver\u003c571 brand=vpc,driver\u003e=570,driver\u003c571 brand=vcs,driver\u003e=570,driver\u003c571 brand=vws,driver\u003e=570,driver\u003c571 brand=cloudgaming,driver\u003e=570,driver\u003c571 brand=unknown,driver\u003e=575,driver\u003c576 brand=grid,driver\u003e=575,driver\u003c576 brand=tesla,driver\u003e=575,driver\u003c576 brand=nvidia,driver\u003e=575,driver\u003c576 brand=quadro,driver\u003e=575,driver\u003c576 brand=quadrortx,driver\u003e=575,driver\u003c576 brand=nvidiartx,driver\u003e=575,driver\u003c576 brand=vapps,driver\u003e=575,driver\u003c576 brand=vpc,driver\u003e=575,driver\u003c576 brand=vcs,driver\u003e=575,driver\u003c576 brand=vws,driver\u003e=575,driver\u003c576 brand=cloudgaming,driver\u003e=575,driver\u003c576",
            "NV_CUDA_CUDART_VERSION=13.0.96-1",
            "CUDA_VERSION=13.0.1",
            "LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64",
            "NVIDIA_VISIBLE_DEVICES=all",
            "NVIDIA_DRIVER_CAPABILITIES=compute,utility",
            "DEBIAN_FRONTEND=noninteractive",
            "UV_HTTP_TIMEOUT=500",
            "UV_INDEX_STRATEGY=unsafe-best-match",
            "UV_LINK_MODE=copy",
            "UV_PYTHON_INSTALL_DIR=/opt/uv/python",
            "UV_CACHE_DIR=/opt/uv/cache",
            "VLLM_ENABLE_CUDA_COMPATIBILITY=0",
            "TORCH_CUDA_ARCH_LIST=7.5 8.0 8.6 8.9 9.0 10.0 12.0+PTX",
            "VLLM_USAGE_SOURCE=production-docker-image",
            "VLLM_BUILD_COMMIT=0decac0d96c42b49572498019f0a0e3600f50398",
            "VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b",
            "VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/2333",
            "VLLM_IMAGE_TAG=vllm/vllm-openai:v0.22.1-ubuntu2404",
            "LANG=en_US.UTF-8",
            "LANGUAGE=en_US:en",
            "LC_ALL=en_US.UTF-8",
            "PYTHON_VERSION=3.12",
            "PIP_NO_CACHE_DIR=1",
            "PIP_DISABLE_PIP_VERSION_CHECK=1",
            "PIP_ROOT_USER_ACTION=ignore",
            "CUDA_HOME=/usr/local/cuda",
            "CUDA_ARCHS=",
            "UV_SYSTEM_PYTHON=1",
            "UV_PRERELEASE=allow",
            "UV_SKIP_WHEEL_FILENAME_CHECK=1",
            "UV_NO_CACHE=1",
            "VLLM_VERSION=0.22.1",
            "VLLM_TORCH_VERSION=2.11.0",
            "VLLM_TORCH_CUDA_VERSION=13.0.1",
            "RAY_EXPERIMENTAL_NOSET_CUDA_VISIBLE_DEVICES=1",
            "SAFETENSORS_FAST_GPU=1",
            "RUNAI_STREAMER_MEMORY_LIMIT=0",
            "RUNAI_STREAMER_LOG_TO_STDERR=1",
            "RUNAI_STREAMER_LOG_LEVEL=INFO"
        ],
        "Cmd": null,
        "Image": "",
        "Volumes": null,
        "WorkingDir": "/",
        "Entrypoint": [
            "tini",
            "--"
        ],
        "OnBuild": null,
        "Labels": {
            "ai.vllm.build.commit": "0decac0d96c42b49572498019f0a0e3600f50398",
            "ai.vllm.build.pipeline": "019d130e-464e-4ff7-b84b-492992c0c06b",
            "ai.vllm.build.url": "https://buildkite.com/vllm/release-v2/builds/2333",
            "ai.vllm.image.tag": "vllm/vllm-openai:v0.22.1-ubuntu2404",
            "maintainer": "NVIDIA CORPORATION \u003ccudatools@nvidia.com\u003e",
            "org.opencontainers.image.ref.name": "ubuntu",
            "org.opencontainers.image.revision": "0decac0d96c42b49572498019f0a0e3600f50398",
            "org.opencontainers.image.source": "https://github.com/vllm-project/vllm",
            "org.opencontainers.image.url": "https://buildkite.com/vllm/release-v2/builds/2333",
            "org.opencontainers.image.version": "vllm/vllm-openai:v0.22.1-ubuntu2404"
        },
        "Shell": [
            "/bin/bash",
            "-eo",
            "pipefail",
            "-c"
        ]
    },
    "Architecture": "amd64",
    "Os": "linux",
    "Size": 27155112351,
    "GraphDriver": {
        "Data": {
            "LowerDir": "/var/lib/docker/overlay2/100ea170193cdef73732200d8470de36fe1bde563d7469f7be0f1e6e6533548a/diff:/var/lib/docker/overlay2/ac7852dcdda7fb8322d63f043af3c6afdae474b31442245265c42a3bc67367f4/diff:/var/lib/docker/overlay2/60b2e4159c0182423ed31a09ab9662eee30247fbc4326fa39db5ed1d5e73750a/diff:/var/lib/docker/overlay2/d5d69db1fd04d1aacd02f8554caa9636697b443ec087dc95f03b02466fe6fb1e/diff:/var/lib/docker/overlay2/97cf98f7de870f83e6be6bf73927af6dc81fbfbcdc93a8ccf174993bae089644/diff:/var/lib/docker/overlay2/5d980b555852b69f2698dc72c2d0ebe3fb1aed87a37500bf192b9be71956bdb5/diff:/var/lib/docker/overlay2/7a66a396999f3034ec4412dd3e0f732d3d9eadbc8dc7c4b942cd06b5e9f91206/diff:/var/lib/docker/overlay2/70374251df68de48d0c63bb2ec15a27a20d2bd2e7d5e203582bd01f406426da3/diff:/var/lib/docker/overlay2/dd7b4279e059a4e5105e78e644fcaf0136f6c398aa93efc58ca2efbce92d7922/diff:/var/lib/docker/overlay2/148d6d9cf9c9299cc29eb142cd9bce30aa9d4d2003356257a232c883efbae818/diff:/var/lib/docker/overlay2/7ffbf127568b5a6a16f2f8a4879d5b27f97d1309bf6ea8c64804fa3b7464e1ef/diff:/var/lib/docker/overlay2/1949cf301ee49f64263a94dc644e611d425384e9bb1a9d12b88d6eeb931a6781/diff:/var/lib/docker/overlay2/c90777759463f6386ba075e9b12a154e75db46d40c31dbc5b53931f52f92d888/diff:/var/lib/docker/overlay2/b73881f2b6bfc8ad1dc03820141c76daa24cae62448a9d561162dfa5938b8e63/diff:/var/lib/docker/overlay2/5fa6a45446ef523c5fd98c51a6d9333686fde33461caa568e4187d26b1d4942b/diff:/var/lib/docker/overlay2/837d8971a06750bb36d80853762eb9ed1f2bf8753e0bf0136388c2f9510059ae/diff:/var/lib/docker/overlay2/2c86dd22e251d050c33a611abb10fb38711ce0d6d00a4624a9a8e11ddcdc733f/diff:/var/lib/docker/overlay2/07ff1f4c7e93462c0158bd101fa5dd82c188db20acade54c06dd40c47ff52abe/diff:/var/lib/docker/overlay2/e4c93bb27256041add0756bd0294f7ab868a688f1ecac81835086300e6218f44/diff:/var/lib/docker/overlay2/e476379dd13f9b659ca70ebb21ef21cc11caee0cc25de8d970bf3d74d110ccf2/diff:/var/lib/docker/overlay2/f2c452456a36bfd3711a8623f50ff90594848b0c90ec09a23a5319db3f9c33c6/diff:/var/lib/docker/overlay2/94f0e2457999eb73709d1344c21b12bd8bda7e91954e7e07f2fbb24fdf3b6d9a/diff:/var/lib/docker/overlay2/ae8e799308b04daadcdf9e81f4803f747ba9d57733979ac5010f671ab5ba55f8/diff:/var/lib/docker/overlay2/028b3e049acee1b3820c5772bd59f47842abc5b01f6b34f80de48666841af35c/diff:/var/lib/docker/overlay2/a7e004fc67c59ad475a0bd7f3edf87f8f9961913d444b6f63c87f0d77c798a2a/diff:/var/lib/docker/overlay2/e198cdd115a6f0692353ab6a047c33e887376e95f59481915051d9b8b1e1d210/diff:/var/lib/docker/overlay2/01a48a29fc32c6e01d535a00f05ae64a6ed8608ea9802e0057d1779bc23f8a67/diff:/var/lib/docker/overlay2/dc5900fad2547ede9e3bfd1269b4bf2051ce94545cdde1cbb073dbf44dd01492/diff:/var/lib/docker/overlay2/27e5d92ff8e29e3e6b687b01114de553b043aaebdc9f1742d80cdb033f63e496/diff:/var/lib/docker/overlay2/8b72387c68fc461b5c91db80895ee20f533f754ea89ffa948f05cf39ead2dd4e/diff:/var/lib/docker/overlay2/a86a9dcf7908ae9202e0a4ab1965850130ccf9357ae205af4834af75efb5f062/diff:/var/lib/docker/overlay2/67d16224ba2d295589b8cc8c22f455ad5cdbf6e94bcb6eedd7bd2ee313680940/diff:/var/lib/docker/overlay2/505fd64841b36a928dde11e296b51c726b5b64629d1ea7eac35235fbf5a4446a/diff:/var/lib/docker/overlay2/ad9fe3787ab5b02b760628ff00203b850d6d7d187e05dbb3f66e523345b3d588/diff:/var/lib/docker/overlay2/fab1f5b75ad64279e6e18fc39f9a71033c342eb1b5d8c9a91aa53ae256c26268/diff:/var/lib/docker/overlay2/20141db1dd044175fcb3d542f38e6d44e899d96b1f8487d569beb2e1177b2f9b/diff:/var/lib/docker/overlay2/a66ef137ff4b412e45453d4086c17d3013d9bd4294834585169adef3b0092cc2/diff:/var/lib/docker/overlay2/bebff1e9c34ac3c0be7739ca453e4fb5469ecc35ba6e0354ac4f8634639c91d4/diff:/var/lib/docker/overlay2/81e68190b283314b914ee252deba769fa2d672c6fac07862ae8e6053175c3fb3/diff",
            "MergedDir": "/var/lib/docker/overlay2/4944a29eccab3aab14bd912783e12b795abc305f8805f021fdd0bb79191839f4/merged",
            "UpperDir": "/var/lib/docker/overlay2/4944a29eccab3aab14bd912783e12b795abc305f8805f021fdd0bb79191839f4/diff",
            "WorkDir": "/var/lib/docker/overlay2/4944a29eccab3aab14bd912783e12b795abc305f8805f021fdd0bb79191839f4/work"
        },
        "Name": "overlay2"
    },
    "RootFS": {
        "Type": "layers",
        "Layers": [
            "sha256:073ec47a8c22dcaa4d6e5758799ccefe2f9bde943685830b1bf6fd2395f5eabc",
            "sha256:18241330a2d180465d0b9868e4978456293d37da715de2f313ba08862da2aab1",
            "sha256:b5c4de646bbad7dd50f917376023047d99ff9a1e806943dd86799e933b6a6294",
            "sha256:dab2da33fe40a74d9faf939b829b701aa6cfc6b4502ff68fcf716fd2973697ac",
            "sha256:b7ec8fd7c485bbedbe64cbc5a7a810ceabb9156e95c83ba60596ddb9b4955d48",
            "sha256:9a5ee1033143eb9a4eb709e988bf2d065e892b37e62060c804c2d98b46b56907",
            "sha256:bb3ccea308c60a950707a25addc7ca104ff32a6ddf695f0a6be905466ef4dcc2",
            "sha256:3fc1041d4464b5699325dff2fd6ed62209178aa34c2041455345dd093704be8e",
            "sha256:e4785f97fffcaeee5ff641a70c62adb33b781f71f84bdec4aff9aa5765c7ae85",
            "sha256:4b818fd1ce786bfc97cacdcd6cfed9d4053e478ef53cd895397531488dea001e",
            "sha256:6332b017573a3be035cfc6c98ef4607f59093ec6e77bb14936a5f957d32b7ff4",
            "sha256:6487ba2f84fee1965ce4f67b1f6f7a6f7e6a4d8fe0209e917cb1907cee2a2f28",
            "sha256:a28674f83dfba95b6b218d2574ef57f67679bd6f3da053c6f2b53fbb65810c16",
            "sha256:a28674f83dfba95b6b218d2574ef57f67679bd6f3da053c6f2b53fbb65810c16",
            "sha256:2f3364ff24ea2437cf40ce3e608718691cb788731982413b5f3728329fdf1ef3",
            "sha256:b20c752c6979c6ad54c71462a5d100fa10fbde07412f06848002cb2437275266",
            "sha256:473c86236e5eacc77c38d037bce4bf7a82fd29104a914baae340da099946653a",
            "sha256:05c89ddb745f8c93120762df574eeddf957249c70516c13e20d676bbfd40dc12",
            "sha256:69cd956a3867cf0202375e9811b794f37850837465a67a6b42c50647e29bdade",
            "sha256:205f74a1dbf3dc1049b34713bfa34db34a5179737fd104142aaad73377e18588",
            "sha256:bc94ef2f7306ba3e23aea7edbfd0fc4574c8a85b887a063dc0d52dbaddf57dd5",
            "sha256:1d9287509aa631381aad101413958b1632791edbdeb73b362951750534a90652",
            "sha256:7e664d9db354b0d248a2be4dec51785a33e81542879131c1f745264badd92e2b",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:950224ebbc71d07cbd3649de6344ed60efaf43ad8921e433c20d64a242ca4ccc",
            "sha256:e61b6e07a7e7124998d445b978339a41b303333aab24a50d0aa13e806890fdb0",
            "sha256:3c0b8bf3866dfb86d42360e88a83edd5e72918ef8b99f8593fd0e5e6d02510e7",
            "sha256:a9b625ba0b538b6ea7eec89bac413dae5e3f97486171caf3fe0bba0b507e50a2",
            "sha256:171359f9d537a606f9448fd49d390c41d90ebf7b2d24e72a56708c6734eb3272",
            "sha256:649a786c77b61cbdb34b065b70fe96b24052893735678b3832cac06f4c01c194",
            "sha256:5f02a74dcd968d86013b959d5fb9aabcb8c97d63c16871a796f8c2d7a79cc29f",
            "sha256:9c7e13b16c54f5f59d513df413ea1506c3d543f8e36b7f72c6478edb2313f8fa",
            "sha256:15c8fcf9e39b6b0358bf7b6d149daca27dfd57c7087535891164d1e2911c644a",
            "sha256:edd840ceb97db1ab322d3164f780b72dda3a9a7c2c1a302c6b649619edf6959b",
            "sha256:684632d142cfb55492d32c058c82d5e727fbb7bb65b202541afeb78cfe8a699f",
            "sha256:130b38a471a49645d0cde335718f2423708ffdacea027b80ca03a50aafbdf48f",
            "sha256:a98d88b448c2253f84601c0572fbb1ccfbf3f58c62acf56c5bc51b3df49c9659",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:038cc5b8ba63cb8b61bbf38dc24c3c359dc385a014c2797cf2936252bea01953",
            "sha256:67e0da74f351c46b3a21ba23e5c8b5c3634623a88b97c91423bef62ec41fd2ea"
        ]
    },
    "Metadata": {
        "LastTagTime": "2026-06-26T00:39:20.253603034+08:00"
    }
}