docker.io/vllm/vllm-openai:v0.11.1 linux/arm64

docker.io/vllm/vllm-openai:v0.11.1 - 国内下载镜像源 浏览次数:8 温馨提示: 这是一个 linux/arm64 系统架构镜像
这是镜像描述:

vllm/openai

基于 OpenAI 的 GPT-3 模型的 API 服务，支持自然语言处理等功能。

源镜像 docker.io/vllm/vllm-openai:v0.11.1
国内镜像 swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/vllm/vllm-openai:v0.11.1-linuxarm64
镜像ID sha256:76cb87b30b283ba1538822aa26918abdf6ec2b256d861adcd6b15c6e0cae6207
镜像TAG v0.11.1-linuxarm64
大小 26.54GB
镜像源 docker.io
项目信息 Docker-Hub主页 🚀项目TAG 🚀
CMD
启动入口 vllm serve
工作目录 /vllm-workspace
OS/平台 linux/arm64
浏览量 8 次
贡献者 th******r@163.com
镜像创建 2025-11-18T19:41:24.186877184Z
同步时间 2025-11-22 01:23
更新时间 2025-11-22 02:08
环境变量
PATH=/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin NVARCH=sbsa NVIDIA_REQUIRE_CUDA=cuda>=12.9 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>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 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 NV_CUDA_CUDART_VERSION=12.9.79-1 CUDA_VERSION=12.9.1 LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64 NVIDIA_VISIBLE_DEVICES=all NVIDIA_DRIVER_CAPABILITIES=compute,utility NV_CUDA_LIB_VERSION=12.9.1-1 NV_NVTX_VERSION=12.9.79-1 NV_LIBNPP_VERSION=12.4.1.87-1 NV_LIBNPP_PACKAGE=libnpp-12-9=12.4.1.87-1 NV_LIBCUSPARSE_VERSION=12.5.10.65-1 NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-9 NV_LIBCUBLAS_VERSION=12.9.1.4-1 NV_LIBCUBLAS_PACKAGE=libcublas-12-9=12.9.1.4-1 NV_LIBNCCL_PACKAGE_NAME=libnccl2 NV_LIBNCCL_PACKAGE_VERSION=2.27.3-1 NCCL_VERSION=2.27.3-1 NV_LIBNCCL_PACKAGE=libnccl2=2.27.3-1+cuda12.9 NVIDIA_PRODUCT_NAME=CUDA NV_CUDA_CUDART_DEV_VERSION=12.9.79-1 NV_NVML_DEV_VERSION=12.9.79-1 NV_LIBCUSPARSE_DEV_VERSION=12.5.10.65-1 NV_LIBNPP_DEV_VERSION=12.4.1.87-1 NV_LIBNPP_DEV_PACKAGE=libnpp-dev-12-9=12.4.1.87-1 NV_LIBCUBLAS_DEV_PACKAGE_NAME=libcublas-dev-12-9 NV_LIBCUBLAS_DEV_VERSION=12.9.1.4-1 NV_LIBCUBLAS_DEV_PACKAGE=libcublas-dev-12-9=12.9.1.4-1 NV_CUDA_NSIGHT_COMPUTE_VERSION=12.9.1-1 NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-12-9=12.9.1-1 NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-dev NV_LIBNCCL_DEV_PACKAGE_VERSION=2.27.3-1 NV_LIBNCCL_DEV_PACKAGE=libnccl-dev=2.27.3-1+cuda12.9 LIBRARY_PATH=/usr/local/cuda/lib64/stubs DEBIAN_FRONTEND=noninteractive UV_HTTP_TIMEOUT=500 UV_INDEX_STRATEGY=unsafe-best-match UV_LINK_MODE=copy CUDA_HOME=/usr/local/cuda VLLM_USAGE_SOURCE=production-docker-image
镜像标签
NVIDIA CORPORATION <cudatools@nvidia.com>: maintainer ubuntu: org.opencontainers.image.ref.name 22.04: org.opencontainers.image.version
无权限下载?点我修复 生成Docker Run命令 生成Kubernetes YAML资源

Docker拉取命令 

docker pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/vllm/vllm-openai:v0.11.1-linuxarm64
docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/vllm/vllm-openai:v0.11.1-linuxarm64  docker.io/vllm/vllm-openai:v0.11.1

Containerd拉取命令 

ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/vllm/vllm-openai:v0.11.1-linuxarm64
ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/vllm/vllm-openai:v0.11.1-linuxarm64  docker.io/vllm/vllm-openai:v0.11.1

Shell快速替换命令 

sed -i 's#vllm/vllm-openai:v0.11.1#swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/vllm/vllm-openai:v0.11.1-linuxarm64#' 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/vllm/vllm-openai:v0.11.1-linuxarm64 && docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/vllm/vllm-openai:v0.11.1-linuxarm64  docker.io/vllm/vllm-openai:v0.11.1'

Ansible快速分发-Containerd 

#ansible k8s -m shell -a 'ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/vllm/vllm-openai:v0.11.1-linuxarm64 && ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/vllm/vllm-openai:v0.11.1-linuxarm64  docker.io/vllm/vllm-openai:v0.11.1'

镜像构建历史 


# 2025-11-19 03:41:24  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["vllm" "serve"]
                        
# 2025-11-19 03:41:24  0.00B 设置环境变量 VLLM_USAGE_SOURCE
ENV VLLM_USAGE_SOURCE=production-docker-image
                        
# 2025-11-19 03:41:24  667.07MB 执行命令并创建新的镜像层
RUN |6 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= /bin/bash -c if [ "$INSTALL_KV_CONNECTORS" = "true" ]; then         uv pip install --system -r requirements/kv_connectors.txt;     fi;     if [ "$TARGETPLATFORM" = "linux/arm64" ]; then         BITSANDBYTES_VERSION="0.42.0";     else         BITSANDBYTES_VERSION="0.46.1";     fi;     uv pip install --system accelerate hf_transfer modelscope "bitsandbytes>=${BITSANDBYTES_VERSION}" 'timm>=1.0.17' 'runai-model-streamer[s3,gcs]>=0.15.0' # buildkit
                        
# 2025-11-19 03:40:51  59.00B 复制新文件或目录到容器中
COPY requirements/kv_connectors.txt requirements/kv_connectors.txt # buildkit
                        
# 2025-11-19 03:40:51  0.00B 设置环境变量 UV_HTTP_TIMEOUT
ENV UV_HTTP_TIMEOUT=500
                        
# 2025-11-19 03:40:51  0.00B 定义构建参数
ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
                        
# 2025-11-19 03:40:51  0.00B 定义构建参数
ARG PIP_INDEX_URL UV_INDEX_URL
                        
# 2025-11-19 03:40:51  0.00B 定义构建参数
ARG INSTALL_KV_CONNECTORS=false
                        
# 2025-11-19 03:40:51  0.00B 定义构建参数
ARG TARGETPLATFORM
                        
# 2025-11-19 03:40:51  0.00B 设置环境变量 LD_LIBRARY_PATH
ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64
                        
# 2025-11-19 03:40:51  989.66MB 执行命令并创建新的镜像层
RUN |18 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true TARGETPLATFORM=linux/arm64 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL=https://download.pytorch.org/whl/nightly PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled DEEPGEMM_GIT_REF= /bin/bash -c export TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST:-9.0a 10.0a+PTX}"     && bash install_python_libraries.sh # buildkit
                        
# 2025-11-19 03:33:36  0.00B 设置环境变量 CUDA_HOME
ENV CUDA_HOME=/usr/local/cuda
                        
# 2025-11-19 03:33:36  3.78KB 复制新文件或目录到容器中
COPY tools/ep_kernels/install_python_libraries.sh install_python_libraries.sh # buildkit
                        
# 2025-11-19 03:33:36  2.65MB 执行命令并创建新的镜像层
RUN |18 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true TARGETPLATFORM=linux/arm64 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL=https://download.pytorch.org/whl/nightly PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled DEEPGEMM_GIT_REF= /bin/bash -c set -eux;     case "${TARGETPLATFORM}" in       linux/arm64) UUARCH="aarch64" ;;       linux/amd64) UUARCH="x64" ;;       *) echo "Unsupported TARGETPLATFORM: ${TARGETPLATFORM}" >&2; exit 1 ;;     esac;     ./install_gdrcopy.sh "${GDRCOPY_OS_VERSION}" "${GDRCOPY_CUDA_VERSION}" "${UUARCH}";     rm ./install_gdrcopy.sh # buildkit
                        
# 2025-11-19 03:33:32  1.44KB 复制新文件或目录到容器中
COPY tools/install_gdrcopy.sh install_gdrcopy.sh # buildkit
                        
# 2025-11-19 03:33:32  44.78MB 执行命令并创建新的镜像层
RUN |18 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true TARGETPLATFORM=linux/arm64 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL=https://download.pytorch.org/whl/nightly PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled DEEPGEMM_GIT_REF= /bin/bash -c VLLM_DOCKER_BUILD_CONTEXT=1 TORCH_CUDA_ARCH_LIST="9.0a 10.0a" /tmp/install_deepgemm.sh --cuda-version "${CUDA_VERSION}" ${DEEPGEMM_GIT_REF:+--ref "$DEEPGEMM_GIT_REF"} # buildkit
                        
# 2025-11-19 03:32:39  3.27KB 复制新文件或目录到容器中
COPY tools/install_deepgemm.sh /tmp/install_deepgemm.sh # buildkit
                        
# 2025-11-19 03:32:39  0.00B 定义构建参数
ARG DEEPGEMM_GIT_REF
                        
# 2025-11-19 03:32:39  509.90MB 执行命令并创建新的镜像层
RUN |17 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true TARGETPLATFORM=linux/arm64 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL=https://download.pytorch.org/whl/nightly PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled /bin/bash -c uv pip install --system -r requirements/build.txt         --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') # buildkit
                        
# 2025-11-19 03:32:34  165.00B 复制新文件或目录到容器中
COPY requirements/build.txt requirements/build.txt # buildkit
                        
# 2025-11-19 03:32:34  0.00B 执行命令并创建新的镜像层
RUN |17 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true TARGETPLATFORM=linux/arm64 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL=https://download.pytorch.org/whl/nightly PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled /bin/bash -c . /etc/environment && uv pip list # buildkit
                        
# 2025-11-19 03:32:33  28.05KB 复制新文件或目录到容器中
COPY ./vllm/collect_env.py . # buildkit
                        
# 2025-11-19 03:32:33  749.14KB 复制新文件或目录到容器中
COPY benchmarks benchmarks # buildkit
                        
# 2025-11-19 03:32:33  965.88KB 复制新文件或目录到容器中
COPY examples examples # buildkit
                        
# 2025-11-19 03:32:33  5.40GB 执行命令并创建新的镜像层
RUN |17 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true TARGETPLATFORM=linux/arm64 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL=https://download.pytorch.org/whl/nightly PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled /bin/bash -c uv pip install --system flashinfer-cubin==0.5.2     && uv pip install --system flashinfer-jit-cache==0.5.2         --extra-index-url https://flashinfer.ai/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')     && flashinfer show-config # buildkit
                        
# 2025-11-19 03:30:24  8.84GB 执行命令并创建新的镜像层
RUN |17 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true TARGETPLATFORM=linux/arm64 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL=https://download.pytorch.org/whl/nightly PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled /bin/bash -c 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 '.') # buildkit
                        
# 2025-11-19 03:09:29  521.60MB 执行命令并创建新的镜像层
RUN |17 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true TARGETPLATFORM=linux/arm64 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL=https://download.pytorch.org/whl/nightly PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled /bin/bash -c if [ "$TARGETPLATFORM" = "linux/arm64" ]; then         uv pip install --system             --index-url ${PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')             "torch==2.8.0.dev20250318+cu128" "torchvision==0.22.0.dev20250319" ;         uv pip install --system             --index-url ${PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')             --pre pytorch_triton==3.3.0+gitab727c40 ;     fi # buildkit
                        
# 2025-11-19 03:09:17  56.14KB 执行命令并创建新的镜像层
RUN |17 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true TARGETPLATFORM=linux/arm64 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL=https://download.pytorch.org/whl/nightly PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled /bin/bash -c ldconfig /usr/local/cuda-$(echo $CUDA_VERSION | cut -d. -f1,2)/compat/ # buildkit
                        
# 2025-11-19 03:09:16  0.00B 设置环境变量 UV_LINK_MODE
ENV UV_LINK_MODE=copy
                        
# 2025-11-19 03:09:16  0.00B 设置环境变量 UV_INDEX_STRATEGY
ENV UV_INDEX_STRATEGY=unsafe-best-match
                        
# 2025-11-19 03:09:16  0.00B 设置环境变量 UV_HTTP_TIMEOUT
ENV UV_HTTP_TIMEOUT=500
                        
# 2025-11-19 03:09:16  66.36MB 执行命令并创建新的镜像层
RUN |17 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true TARGETPLATFORM=linux/arm64 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL=https://download.pytorch.org/whl/nightly PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled /bin/bash -c python3 -m pip install uv # buildkit
                        
# 2025-11-19 03:09:13  0.00B 定义构建参数
ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER
                        
# 2025-11-19 03:09:13  0.00B 定义构建参数
ARG PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL
                        
# 2025-11-19 03:09:13  0.00B 定义构建参数
ARG PYTORCH_CUDA_INDEX_BASE_URL
                        
# 2025-11-19 03:09:13  0.00B 定义构建参数
ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
                        
# 2025-11-19 03:09:13  0.00B 定义构建参数
ARG PIP_INDEX_URL UV_INDEX_URL
                        
# 2025-11-19 03:09:13  746.29MB 执行命令并创建新的镜像层
RUN |9 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true TARGETPLATFORM=linux/arm64 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/bash -c echo 'tzdata tzdata/Areas select America' | debconf-set-selections     && echo 'tzdata tzdata/Zones/America select Los_Angeles' | debconf-set-selections     && apt-get update -y     && apt-get install -y ccache software-properties-common git curl wget sudo vim python3-pip     && apt-get install -y 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 $i failed, retrying in 5s..."; sleep 5; };         done ;     fi     && apt-get update -y     && apt-get install -y python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv libibverbs-dev     && 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     && curl -sS ${GET_PIP_URL} | python${PYTHON_VERSION}     && python3 --version && python3 -m pip --version # buildkit
                        
# 2025-11-19 03:05:35  136.00B 执行命令并创建新的镜像层
RUN |9 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true TARGETPLATFORM=linux/arm64 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/bash -c PYTHON_VERSION_STR=$(echo ${PYTHON_VERSION} | sed 's/\.//g') &&     echo "export PYTHON_VERSION_STR=${PYTHON_VERSION_STR}" >> /etc/environment # buildkit
                        
# 2025-11-19 03:05:34  0.00B 定义构建参数
ARG GET_PIP_URL
                        
# 2025-11-19 03:05:34  0.00B 定义构建参数
ARG DEADSNAKES_GPGKEY_URL
                        
# 2025-11-19 03:05:34  0.00B 定义构建参数
ARG DEADSNAKES_MIRROR_URL
                        
# 2025-11-19 03:05:34  0.00B 
SHELL [/bin/bash -c]
                        
# 2025-11-19 03:05:34  0.00B 定义构建参数
ARG GDRCOPY_OS_VERSION=Ubuntu22_04
                        
# 2025-11-19 03:05:34  0.00B 定义构建参数
ARG GDRCOPY_CUDA_VERSION=12.8
                        
# 2025-11-19 03:05:34  0.00B 定义构建参数
ARG TARGETPLATFORM
                        
# 2025-11-19 03:05:34  0.00B 设置环境变量 DEBIAN_FRONTEND
ENV DEBIAN_FRONTEND=noninteractive
                        
# 2025-11-19 03:05:34  0.00B 设置工作目录为/vllm-workspace
WORKDIR /vllm-workspace
                        
# 2025-11-19 03:05:34  0.00B 定义构建参数
ARG INSTALL_KV_CONNECTORS=false
                        
# 2025-11-19 03:05:34  0.00B 定义构建参数
ARG PYTHON_VERSION
                        
# 2025-11-19 03:05:34  0.00B 定义构建参数
ARG CUDA_VERSION
                        
# 2025-07-19 04:36:00  0.00B 设置环境变量 LIBRARY_PATH
ENV LIBRARY_PATH=/usr/local/cuda/lib64/stubs
                        
# 2025-07-19 04:36:00  388.47KB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=arm64 /bin/sh -c apt-mark hold ${NV_LIBCUBLAS_DEV_PACKAGE_NAME} ${NV_LIBNCCL_DEV_PACKAGE_NAME} # buildkit
                        
# 2025-07-19 04:35:59  5.11GB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=arm64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends     cuda-cudart-dev-12-9=${NV_CUDA_CUDART_DEV_VERSION}     cuda-command-line-tools-12-9=${NV_CUDA_LIB_VERSION}     cuda-minimal-build-12-9=${NV_CUDA_LIB_VERSION}     cuda-libraries-dev-12-9=${NV_CUDA_LIB_VERSION}     cuda-nvml-dev-12-9=${NV_NVML_DEV_VERSION}     ${NV_NVPROF_DEV_PACKAGE}     ${NV_LIBNPP_DEV_PACKAGE}     libcusparse-dev-12-9=${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
                        
# 2025-07-19 04:35:59  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2025-07-19 04:35:59  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2025-07-19 04:35:59  0.00B 设置环境变量 NV_LIBNCCL_DEV_PACKAGE
ENV NV_LIBNCCL_DEV_PACKAGE=libnccl-dev=2.27.3-1+cuda12.9
                        
# 2025-07-19 04:35:59  0.00B 设置环境变量 NCCL_VERSION
ENV NCCL_VERSION=2.27.3-1
                        
# 2025-07-19 04:35:59  0.00B 设置环境变量 NV_LIBNCCL_DEV_PACKAGE_VERSION
ENV NV_LIBNCCL_DEV_PACKAGE_VERSION=2.27.3-1
                        
# 2025-07-19 04:35:59  0.00B 设置环境变量 NV_LIBNCCL_DEV_PACKAGE_NAME
ENV NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-dev
                        
# 2025-07-19 04:35:59  0.00B 设置环境变量 NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE
ENV NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-12-9=12.9.1-1
                        
# 2025-07-19 04:35:59  0.00B 设置环境变量 NV_CUDA_NSIGHT_COMPUTE_VERSION
ENV NV_CUDA_NSIGHT_COMPUTE_VERSION=12.9.1-1
                        
# 2025-07-19 04:35:59  0.00B 设置环境变量 NV_LIBCUBLAS_DEV_PACKAGE
ENV NV_LIBCUBLAS_DEV_PACKAGE=libcublas-dev-12-9=12.9.1.4-1
                        
# 2025-07-19 04:35:59  0.00B 设置环境变量 NV_LIBCUBLAS_DEV_VERSION
ENV NV_LIBCUBLAS_DEV_VERSION=12.9.1.4-1
                        
# 2025-07-19 04:35:59  0.00B 设置环境变量 NV_LIBCUBLAS_DEV_PACKAGE_NAME
ENV NV_LIBCUBLAS_DEV_PACKAGE_NAME=libcublas-dev-12-9
                        
# 2025-07-19 04:35:59  0.00B 设置环境变量 NV_LIBNPP_DEV_PACKAGE
ENV NV_LIBNPP_DEV_PACKAGE=libnpp-dev-12-9=12.4.1.87-1
                        
# 2025-07-19 04:35:59  0.00B 设置环境变量 NV_LIBNPP_DEV_VERSION
ENV NV_LIBNPP_DEV_VERSION=12.4.1.87-1
                        
# 2025-07-19 04:35:59  0.00B 设置环境变量 NV_LIBCUSPARSE_DEV_VERSION
ENV NV_LIBCUSPARSE_DEV_VERSION=12.5.10.65-1
                        
# 2025-07-19 04:35:59  0.00B 设置环境变量 NV_NVML_DEV_VERSION
ENV NV_NVML_DEV_VERSION=12.9.79-1
                        
# 2025-07-19 04:35:59  0.00B 设置环境变量 NV_CUDA_CUDART_DEV_VERSION
ENV NV_CUDA_CUDART_DEV_VERSION=12.9.79-1
                        
# 2025-07-19 04:35:59  0.00B 设置环境变量 NV_CUDA_LIB_VERSION
ENV NV_CUDA_LIB_VERSION=12.9.1-1
                        
# 2025-07-19 04:20:54  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
                        
# 2025-07-19 04:20:54  0.00B 设置环境变量 NVIDIA_PRODUCT_NAME
ENV NVIDIA_PRODUCT_NAME=CUDA
                        
# 2025-07-19 04:20:54  2.53KB 复制新文件或目录到容器中
COPY nvidia_entrypoint.sh /opt/nvidia/ # buildkit
                        
# 2025-07-19 04:20:54  3.06KB 复制新文件或目录到容器中
COPY entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit
                        
# 2025-07-19 04:20:54  262.42KB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=arm64 /bin/sh -c apt-mark hold ${NV_LIBCUBLAS_PACKAGE_NAME} ${NV_LIBNCCL_PACKAGE_NAME} # buildkit
                        
# 2025-07-19 04:20:54  3.28GB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=arm64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends     cuda-libraries-12-9=${NV_CUDA_LIB_VERSION}     ${NV_LIBNPP_PACKAGE}     cuda-nvtx-12-9=${NV_NVTX_VERSION}     libcusparse-12-9=${NV_LIBCUSPARSE_VERSION}     ${NV_LIBCUBLAS_PACKAGE}     ${NV_LIBNCCL_PACKAGE}     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2025-07-19 04:20:54  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2025-07-19 04:20:54  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2025-07-19 04:20:54  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE
ENV NV_LIBNCCL_PACKAGE=libnccl2=2.27.3-1+cuda12.9
                        
# 2025-07-19 04:20:54  0.00B 设置环境变量 NCCL_VERSION
ENV NCCL_VERSION=2.27.3-1
                        
# 2025-07-19 04:20:54  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_VERSION
ENV NV_LIBNCCL_PACKAGE_VERSION=2.27.3-1
                        
# 2025-07-19 04:20:54  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_NAME
ENV NV_LIBNCCL_PACKAGE_NAME=libnccl2
                        
# 2025-07-19 04:20:54  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE
ENV NV_LIBCUBLAS_PACKAGE=libcublas-12-9=12.9.1.4-1
                        
# 2025-07-19 04:20:54  0.00B 设置环境变量 NV_LIBCUBLAS_VERSION
ENV NV_LIBCUBLAS_VERSION=12.9.1.4-1
                        
# 2025-07-19 04:20:54  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE_NAME
ENV NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-9
                        
# 2025-07-19 04:20:54  0.00B 设置环境变量 NV_LIBCUSPARSE_VERSION
ENV NV_LIBCUSPARSE_VERSION=12.5.10.65-1
                        
# 2025-07-19 04:20:54  0.00B 设置环境变量 NV_LIBNPP_PACKAGE
ENV NV_LIBNPP_PACKAGE=libnpp-12-9=12.4.1.87-1
                        
# 2025-07-19 04:20:54  0.00B 设置环境变量 NV_LIBNPP_VERSION
ENV NV_LIBNPP_VERSION=12.4.1.87-1
                        
# 2025-07-19 04:20:54  0.00B 设置环境变量 NV_NVTX_VERSION
ENV NV_NVTX_VERSION=12.9.79-1
                        
# 2025-07-19 04:20:54  0.00B 设置环境变量 NV_CUDA_LIB_VERSION
ENV NV_CUDA_LIB_VERSION=12.9.1-1
                        
# 2025-07-19 04:13:38  0.00B 设置环境变量 NVIDIA_DRIVER_CAPABILITIES
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
                        
# 2025-07-19 04:13:38  0.00B 设置环境变量 NVIDIA_VISIBLE_DEVICES
ENV NVIDIA_VISIBLE_DEVICES=all
                        
# 2025-07-19 04:13:38  17.29KB 复制新文件或目录到容器中
COPY NGC-DL-CONTAINER-LICENSE / # buildkit
                        
# 2025-07-19 04:13:38  0.00B 设置环境变量 LD_LIBRARY_PATH
ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64
                        
# 2025-07-19 04:13:38  0.00B 设置环境变量 PATH
ENV PATH=/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
                        
# 2025-07-19 04:13:38  22.00B 执行命令并创建新的镜像层
RUN |1 TARGETARCH=arm64 /bin/sh -c echo "/usr/local/cuda/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit
                        
# 2025-07-19 04:13:38  293.79MB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=arm64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends     cuda-cudart-12-9=${NV_CUDA_CUDART_VERSION}     cuda-compat-12-9     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2025-07-19 04:12:35  0.00B 设置环境变量 CUDA_VERSION
ENV CUDA_VERSION=12.9.1
                        
# 2025-07-19 04:12:35  10.22MB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=arm64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends     gnupg2 curl ca-certificates &&     curl -fsSLO https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/${NVARCH}/cuda-keyring_1.1-1_all.deb &&     dpkg -i cuda-keyring_1.1-1_all.deb &&     apt-get purge --autoremove -y curl     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2025-07-19 04:12:35  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2025-07-19 04:12:35  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2025-07-19 04:12:35  0.00B 设置环境变量 NV_CUDA_CUDART_VERSION
ENV NV_CUDA_CUDART_VERSION=12.9.79-1
                        
# 2025-07-19 04:12:35  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>=12.9 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>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 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
                        
# 2025-07-19 04:12:35  0.00B 设置环境变量 NVARCH
ENV NVARCH=sbsa
                        
# 2025-07-15 00:34:17  0.00B 
/bin/sh -c #(nop)  CMD ["/bin/bash"]
                        
# 2025-07-15 00:34:16  69.24MB 
/bin/sh -c #(nop) ADD file:834c1c2a4c7753a37759a9b21f64a990572643eee18669b1faa782fee45355ed in / 
                        
# 2025-07-15 00:34:14  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.version=22.04
                        
# 2025-07-15 00:34:14  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.ref.name=ubuntu
                        
# 2025-07-15 00:34:14  0.00B 
/bin/sh -c #(nop)  ARG LAUNCHPAD_BUILD_ARCH
                        
# 2025-07-15 00:34:14  0.00B 
/bin/sh -c #(nop)  ARG RELEASE

镜像信息 

{
    "Id": "sha256:76cb87b30b283ba1538822aa26918abdf6ec2b256d861adcd6b15c6e0cae6207",
    "RepoTags": [
        "vllm/vllm-openai:v0.11.1",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/vllm/vllm-openai:v0.11.1-linuxarm64"
    ],
    "RepoDigests": [
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/vllm/vllm-openai@sha256:d2d3cfdc9f5aec83da1c23621976be433be8d46c7e4939be55897634dcdf2cb9"
    ],
    "Parent": "",
    "Comment": "buildkit.dockerfile.v0",
    "Created": "2025-11-18T19:41:24.186877184Z",
    "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/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",
            "NVARCH=sbsa",
            "NVIDIA_REQUIRE_CUDA=cuda\u003e=12.9 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=560,driver\u003c561 brand=grid,driver\u003e=560,driver\u003c561 brand=tesla,driver\u003e=560,driver\u003c561 brand=nvidia,driver\u003e=560,driver\u003c561 brand=quadro,driver\u003e=560,driver\u003c561 brand=quadrortx,driver\u003e=560,driver\u003c561 brand=nvidiartx,driver\u003e=560,driver\u003c561 brand=vapps,driver\u003e=560,driver\u003c561 brand=vpc,driver\u003e=560,driver\u003c561 brand=vcs,driver\u003e=560,driver\u003c561 brand=vws,driver\u003e=560,driver\u003c561 brand=cloudgaming,driver\u003e=560,driver\u003c561 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",
            "NV_CUDA_CUDART_VERSION=12.9.79-1",
            "CUDA_VERSION=12.9.1",
            "LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64",
            "NVIDIA_VISIBLE_DEVICES=all",
            "NVIDIA_DRIVER_CAPABILITIES=compute,utility",
            "NV_CUDA_LIB_VERSION=12.9.1-1",
            "NV_NVTX_VERSION=12.9.79-1",
            "NV_LIBNPP_VERSION=12.4.1.87-1",
            "NV_LIBNPP_PACKAGE=libnpp-12-9=12.4.1.87-1",
            "NV_LIBCUSPARSE_VERSION=12.5.10.65-1",
            "NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-9",
            "NV_LIBCUBLAS_VERSION=12.9.1.4-1",
            "NV_LIBCUBLAS_PACKAGE=libcublas-12-9=12.9.1.4-1",
            "NV_LIBNCCL_PACKAGE_NAME=libnccl2",
            "NV_LIBNCCL_PACKAGE_VERSION=2.27.3-1",
            "NCCL_VERSION=2.27.3-1",
            "NV_LIBNCCL_PACKAGE=libnccl2=2.27.3-1+cuda12.9",
            "NVIDIA_PRODUCT_NAME=CUDA",
            "NV_CUDA_CUDART_DEV_VERSION=12.9.79-1",
            "NV_NVML_DEV_VERSION=12.9.79-1",
            "NV_LIBCUSPARSE_DEV_VERSION=12.5.10.65-1",
            "NV_LIBNPP_DEV_VERSION=12.4.1.87-1",
            "NV_LIBNPP_DEV_PACKAGE=libnpp-dev-12-9=12.4.1.87-1",
            "NV_LIBCUBLAS_DEV_PACKAGE_NAME=libcublas-dev-12-9",
            "NV_LIBCUBLAS_DEV_VERSION=12.9.1.4-1",
            "NV_LIBCUBLAS_DEV_PACKAGE=libcublas-dev-12-9=12.9.1.4-1",
            "NV_CUDA_NSIGHT_COMPUTE_VERSION=12.9.1-1",
            "NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-12-9=12.9.1-1",
            "NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-dev",
            "NV_LIBNCCL_DEV_PACKAGE_VERSION=2.27.3-1",
            "NV_LIBNCCL_DEV_PACKAGE=libnccl-dev=2.27.3-1+cuda12.9",
            "LIBRARY_PATH=/usr/local/cuda/lib64/stubs",
            "DEBIAN_FRONTEND=noninteractive",
            "UV_HTTP_TIMEOUT=500",
            "UV_INDEX_STRATEGY=unsafe-best-match",
            "UV_LINK_MODE=copy",
            "CUDA_HOME=/usr/local/cuda",
            "VLLM_USAGE_SOURCE=production-docker-image"
        ],
        "Cmd": null,
        "Image": "",
        "Volumes": null,
        "WorkingDir": "/vllm-workspace",
        "Entrypoint": [
            "vllm",
            "serve"
        ],
        "OnBuild": null,
        "Labels": {
            "maintainer": "NVIDIA CORPORATION \u003ccudatools@nvidia.com\u003e",
            "org.opencontainers.image.ref.name": "ubuntu",
            "org.opencontainers.image.version": "22.04"
        },
        "Shell": [
            "/bin/bash",
            "-c"
        ]
    },
    "Architecture": "arm64",
    "Os": "linux",
    "Size": 26544346343,
    "GraphDriver": {
        "Data": {
            "LowerDir": "/var/lib/docker/overlay2/d04fe351fe03a9d6921369ed751d40d2c99308a9bd9fc5963c2b89679dd14e41/diff:/var/lib/docker/overlay2/9746fe50ed9497a6159b0b2ae9400ba49f110f99029f365ad7e99cfc4b1d7d1e/diff:/var/lib/docker/overlay2/60c46ce42f4071b8ac64760f48a61401a1e6edfac6359825057b2df9ae5594f6/diff:/var/lib/docker/overlay2/457c64e29deb7a3f2a9cfb409def4dcfd79c1525923a594854bf8763f039b7ac/diff:/var/lib/docker/overlay2/f08950aa48dc1a0a57f39cc7a69a84ec6f1e445f388641c5b7be09026588577c/diff:/var/lib/docker/overlay2/d60ead6d52f2a048d7d1fc86b15de089e16f2f7c70bcaf2411af0e7a3214ab68/diff:/var/lib/docker/overlay2/ac980a47e8356188d34afc61095eaab1a0b4e3486c0897bae598e0b13df93c54/diff:/var/lib/docker/overlay2/74dac6924e0499a9aec8c9480fb5692e43275356fca615486f3490f5ae4e32b7/diff:/var/lib/docker/overlay2/d0e67a4b51ec0dbac87d6ab388a599a8a3152e2c4c959957c57cf3169bb237e9/diff:/var/lib/docker/overlay2/138e14a0043d340a978ce1e60c5e83417d3f03e5d15dfe62b22d8371238e984c/diff:/var/lib/docker/overlay2/a6e119a6aef6a5e5a6d1ac14844a7ef339153731c848b6903ad743aea2248899/diff:/var/lib/docker/overlay2/199d1cff5cbab240bec1c1f97f8547b7727671c7bbaaa52fa5676e15fabae46d/diff:/var/lib/docker/overlay2/c2de17a070b36837d932b5fd8a6693ebc0d2e43373b8b59a00b5cbb96e07bcd6/diff:/var/lib/docker/overlay2/5a1d3bc415a1451e87c073f64906d23a3c9bade76f30c74148096c83e9428874/diff:/var/lib/docker/overlay2/5a1f196a4acb1bfbd8df0d541ff14117368b575f8860644e11ee593ee21697c6/diff:/var/lib/docker/overlay2/0b38c891f33caa240506fe662fda39ec9d0b8b0bf12821aa79f48f3caae2f36b/diff:/var/lib/docker/overlay2/6ef82e0e6910097f970da373c28f627c70c9f57ed853c62db87605dd86ae9e75/diff:/var/lib/docker/overlay2/122d470854f65ff1ff33330ac5943029b21c57644dc901cb1783935c18c0007d/diff:/var/lib/docker/overlay2/1cfa0e12d145deff92d21ae0f24bfc2755fd0436a9f87b0d51f349f6fc59f9b0/diff:/var/lib/docker/overlay2/a1fc29f223e58193b40ae84f27cf61b2da1148b64dfe5e335123c8d758a7572d/diff:/var/lib/docker/overlay2/3f9f3cf088a50dfe4f9fdbbf2374c76c4529d1233610d1919372cdcd6583afd5/diff:/var/lib/docker/overlay2/3456f22406a63901f9c700b8630588787d5ef708550dbaf0cee981e4a392dfc5/diff:/var/lib/docker/overlay2/60dfd78c575240d31f6d4d1f1de95431c2739038a99d82c044c3ec153569336a/diff:/var/lib/docker/overlay2/dd18a0624fd7f756c805c6d2295511e0baecbb78649cb57c3fe5f60dfd376ecd/diff:/var/lib/docker/overlay2/f0dda942a7ed854f0274ae0f912d088aefa31bdadff336fdb449e6342c2c64c6/diff:/var/lib/docker/overlay2/3e7c9c3b3692794fc77ce124fc07422ca9a78110f5490fe573629b95150715c7/diff:/var/lib/docker/overlay2/0881372c6857da26a5da1a4bf472d605f94f6c62af1f6709b0f283e5cf56a516/diff:/var/lib/docker/overlay2/ed203b022f5b3a256720933b46a9eeee94b005b0befe9113de374526917ea66c/diff:/var/lib/docker/overlay2/7b9d3d9206928711b7ae2db3070ad7a898bc56e1d94cafc962f141acd207c22b/diff:/var/lib/docker/overlay2/54ae8126975f80e15a5227415778f6e5d6e297e9dd8d88126ff045dd82d7b964/diff:/var/lib/docker/overlay2/a7177f50bdce60cb8c0c9680131a2d9e10da2dce36bbf3cc0a2caca0a6670779/diff:/var/lib/docker/overlay2/855afcb3d38eee6ac5e1accd3ab90f3ef7075bd44010628f97784cb5c1fe7364/diff",
            "MergedDir": "/var/lib/docker/overlay2/55d4f14f83fa4464eca0ec493fd7624bc7515a66de3f0746a638711d39a9fd23/merged",
            "UpperDir": "/var/lib/docker/overlay2/55d4f14f83fa4464eca0ec493fd7624bc7515a66de3f0746a638711d39a9fd23/diff",
            "WorkDir": "/var/lib/docker/overlay2/55d4f14f83fa4464eca0ec493fd7624bc7515a66de3f0746a638711d39a9fd23/work"
        },
        "Name": "overlay2"
    },
    "RootFS": {
        "Type": "layers",
        "Layers": [
            "sha256:e437eb226c5d6bbd2c93a89e3708b0c005e0132aa682f109591fca659de658d1",
            "sha256:4c03e8e391d1443f071b295f97260e45b92b3df5f2a248c369434a143a5be1b1",
            "sha256:fdc01e9ff8a2f5cbe11111373e4b5f60a22ece493d2ebb3066e55a0bbabd1fd2",
            "sha256:226cc82ba2cb7de7e7639ceac53fa837b5dda11bcd040041637cd27df8153e35",
            "sha256:455bca42f6ec40ca42fea4bea15c6c17b97101af90413cdd25647de2b9d98960",
            "sha256:ab02e1597fc1a4a939284236746c55763e07a3d39c23f9a96ab4d11acc501ee1",
            "sha256:1bb8fc99a6b0d7e340b92fa530904020f5e1b7c2af4465547274d2840d72dbe5",
            "sha256:f8afbb6ab1ea4d3067f2997e04aa5ea0a8207eb6a57ef1cc6018c69959a32db5",
            "sha256:3d654a443902870864b6d61e7b9b058dfc68a1392870416198b153b1a00942bb",
            "sha256:6622143d3246970d35e771c9b83de933cf69efa61e553e8df9e71c2a4494b83b",
            "sha256:f922ab394c4090e348e739b4ba9181836d278e79cc0c4f9f53b1f369023adec4",
            "sha256:8281589c31c7448877521b26e4fab10f39ba54461db9062fd6665dad1f25a1e7",
            "sha256:77084831eff17c0416a4d87f2d79f4e8be0d701ac1781b4d150dcbe42fe1c28b",
            "sha256:17e5e7ce1dc54fbc5ffcd247c23a13f294dc0f54fed0b0f7566e5f8eb4ae1793",
            "sha256:8db8c84555f975e760a5fa0425b08f5e6998cfed5d411700889dedc037c70df7",
            "sha256:128c4ef2d287d8d815e61342670839bf93fe170b95debb2812d0a7ecb23b3bf7",
            "sha256:b988fa4c4cbdfdb4e3819f198d0236820f071a8ad70bd1e54bc4f2e6cab5b9ae",
            "sha256:4fd7db3974ab960a4fed96e7695c9d35a4f2ddbd7993eda67a213cf977b74104",
            "sha256:495a2d1a58aa96fa950b6bd44af1c96cd1dc9a25f4acb054867d9a106c8be566",
            "sha256:6861abcd483cc0822ac3bf72747fd2c32e524f59c159eb70d2719d1f350eb46a",
            "sha256:982642c7b1c4d0cc725df2f33da05cbdcc07595d2e4e8f8efd452d1a15b6a5c7",
            "sha256:b658b4958cb699324db85fc19e2964d78ffcd885641e5d5a0c2beff3cefab019",
            "sha256:21f86dce28949b6a8b2cdd4f9a473add6c705d11a43abe75e6c079f1948f36a5",
            "sha256:7f3a243a816c6bc2a63fa5701c8ac3f63368507ec377192fae64e15679062461",
            "sha256:5a7565016c175cec009a2762ed7530665d1e2f46509cfddec2fdc37f7f5415c5",
            "sha256:2a41e145ab261c503eae663c9193f133d107386f9111030d6c1e8f7d0bbaee91",
            "sha256:7d1a422e3a8308c9510086d9b7df4574d4bf2c94142f391f645b190b392dc615",
            "sha256:3ec2fec6176048ad1d4591e6efea1ad8a84343b1079d9f5c0e8eb729d551ffd0",
            "sha256:aef212d3676311c34fe1ecea50fb1418215b2573a2e41374fee61cbe57eb78d4",
            "sha256:fcd21bd951cc47e315d94834143edf46b13efc25cdcbf4b27372bec0cfd4a1f7",
            "sha256:677c456fc7a4ee6cf3f7b5fdbf95479e49a74bf677b57e31a444af80e2c2b4a8",
            "sha256:d4c71837d7c589c9c57b8884dd011dfbe5f31b93356d07de487e95d716355362",
            "sha256:012346fd14690418bdd550b0ebdd5c75307e1302ad733ee6c6206b4cbdbcd903"
        ]
    },
    "Metadata": {
        "LastTagTime": "2025-11-22T01:06:19.079705791+08:00"
    }
}

更多版本

docker.io/vllm/vllm-openai:v0.5.4

linux/amd64 docker.io9.90GB2024-09-07 06:20
1589

docker.io/vllm/vllm-openai:v0.6.0

linux/amd64 docker.io9.72GB2024-09-11 01:51
1215

docker.io/vllm/vllm-openai:v0.6.1.post2

linux/amd64 docker.io9.81GB2024-09-24 01:43
828

docker.io/vllm/vllm-openai:latest

linux/amd64 docker.io10.24GB2024-10-11 00:43
3792

docker.io/vllm/vllm-openai:v0.6.4.post1

linux/amd64 docker.io10.64GB2024-11-19 00:42
841

docker.io/vllm/vllm-openai:v0.6.4

linux/amd64 docker.io10.64GB2024-12-11 02:08
726

docker.io/vllm/vllm-openai:v0.6.3

linux/amd64 docker.io10.43GB2024-12-12 02:41
684

docker.io/vllm/vllm-openai:v0.6.6

linux/amd64 docker.io10.23GB2025-01-04 00:37
1148

docker.io/vllm/vllm-openai:v0.6.6.post1

linux/amd64 docker.io10.23GB2025-01-24 00:21
629

docker.io/vllm/vllm-openai:v0.7.1

linux/amd64 docker.io16.53GB2025-02-08 02:05
883

docker.io/vllm/vllm-openai:v0.7.2

linux/amd64 docker.io16.53GB2025-02-09 00:28
2178

docker.io/vllm/vllm-openai:v0.7.3

linux/amd64 docker.io16.43GB2025-02-24 00:50
2893

docker.io/vllm/vllm-openai:v0.8.0

linux/amd64 docker.io16.62GB2025-03-20 00:23
1047

docker.io/vllm/vllm-openai:v0.8.1

linux/amd64 docker.io16.62GB2025-03-21 00:28
884

docker.io/vllm/vllm-openai:v0.8.2

linux/amd64 docker.io16.92GB2025-03-27 01:12
1026

docker.io/vllm/vllm-openai:v0.8.3

linux/amd64 docker.io17.13GB2025-04-08 00:58
1173

docker.io/vllm/vllm-openai:v0.8.4

linux/amd64 docker.io17.16GB2025-04-17 01:16
1465

docker.io/vllm/vllm-openai:v0.8.5

linux/amd64 docker.io17.30GB2025-04-30 02:45
2469

docker.io/vllm/vllm-openai:v0.8.5.post1

linux/amd64 docker.io17.30GB2025-05-07 02:06
2374

docker.io/vllm/vllm-openai:v0.9.0.1

linux/amd64 docker.io20.81GB2025-06-05 01:12
1230

docker.io/vllm/vllm-openai:v0.9.1

linux/amd64 docker.io20.85GB2025-06-12 01:29
2242

docker.io/vllm/vllm-openai:v0.9.2

linux/amd64 docker.io20.76GB2025-07-09 03:00
4285

docker.io/vllm/vllm-openai:v0.10.0

linux/amd64 docker.io26.13GB2025-07-26 03:15
1087

docker.io/vllm/vllm-openai:gptoss

linux/amd64 docker.io33.86GB2025-08-07 01:52
874

docker.io/vllm/vllm-openai:v0.10.1

linux/amd64 docker.io20.25GB2025-08-20 03:05
876

docker.io/vllm/vllm-openai:v0.10.1.1

linux/amd64 docker.io20.26GB2025-08-23 01:43
1116

docker.io/vllm/vllm-openai:v0.10.2

linux/amd64 docker.io22.49GB2025-09-16 03:40
849

docker.io/vllm/vllm-openai:v0.2.7

linux/amd64 docker.io6.34GB2025-10-01 01:07
167

docker.io/vllm/vllm-openai:v0.11.0-x86_64

linux/amd64 docker.io25.86GB2025-10-09 02:14
550

docker.io/vllm/vllm-openai:v0.10.2-x86_64

linux/amd64 docker.io22.49GB2025-10-09 02:22
216

docker.io/vllm/vllm-openai:v0.11.0

linux/amd64 docker.io25.86GB2025-10-09 11:24
897

docker.io/vllm/vllm-openai:v0.11.0

linux/arm64 docker.io24.17GB2025-10-30 00:47
379

docker.io/vllm/vllm-openai:v0.3.3

linux/amd64 docker.io9.13GB2025-11-18 01:01
59

docker.io/vllm/vllm-openai:v0.11.1

linux/amd64 docker.io28.72GB2025-11-21 01:03
40

docker.io/vllm/vllm-openai:v0.11.2

linux/amd64 docker.io28.82GB2025-11-22 00:46
10

docker.io/vllm/vllm-openai:v0.11.1

linux/arm64 docker.io26.54GB2025-11-22 01:23
7

docker.io/vllm/vllm-openai:v0.4.0

linux/amd64 docker.io9.88GB2025-11-22 01:58
5