ghcr.io/sasha0552/vllm:v0.9.1 linux/amd64

ghcr.io/sasha0552/vllm:v0.9.1 - 国内下载镜像源 浏览次数:15

该镜像 ghcr.io/sasha0552/vllm 包含了 vLLM 的 Docker 容器镜像。vLLM 是一个用于高效运行大型语言模型 (LLM) 的库,它专注于在资源受限的环境中提供良好的性能。此镜像提供了一种便捷的方式来部署和使用 vLLM。

源镜像 ghcr.io/sasha0552/vllm:v0.9.1
国内镜像 swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/sasha0552/vllm:v0.9.1
镜像ID sha256:3cfa4bda17ee27078f8288b81c383df48591fbf6d2e9db5d4149f06dc0bc8205
镜像TAG v0.9.1
大小 15.88GB
镜像源 ghcr.io
CMD
启动入口 python3 -m vllm.entrypoints.openai.api_server
工作目录 /vllm-workspace
OS/平台 linux/amd64
浏览量 15 次
贡献者
镜像创建 2025-08-23T14:37:48.953377334Z
同步时间 2025-10-10 00:24
更新时间 2025-10-10 17:07
环境变量
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>=12.1 brand=tesla,driver>=470,driver<471 brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 brand=tesla,driver>=525,driver<526 brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 NV_CUDA_CUDART_VERSION=12.1.55-1 NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-1 CUDA_VERSION=12.1.0 LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64 NVIDIA_VISIBLE_DEVICES=all NVIDIA_DRIVER_CAPABILITIES=compute,utility NV_CUDA_LIB_VERSION=12.1.0-1 NV_NVTX_VERSION=12.1.66-1 NV_LIBNPP_VERSION=12.0.2.50-1 NV_LIBNPP_PACKAGE=libnpp-12-1=12.0.2.50-1 NV_LIBCUSPARSE_VERSION=12.0.2.55-1 NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-1 NV_LIBCUBLAS_VERSION=12.1.0.26-1 NV_LIBCUBLAS_PACKAGE=libcublas-12-1=12.1.0.26-1 NV_LIBNCCL_PACKAGE_NAME=libnccl2 NV_LIBNCCL_PACKAGE_VERSION=2.17.1-1 NCCL_VERSION=2.17.1-1 NV_LIBNCCL_PACKAGE=libnccl2=2.17.1-1+cuda12.1 NVIDIA_PRODUCT_NAME=CUDA NVIDIA_CUDA_END_OF_LIFE=1 NV_CUDA_CUDART_DEV_VERSION=12.1.55-1 NV_NVML_DEV_VERSION=12.1.55-1 NV_LIBCUSPARSE_DEV_VERSION=12.0.2.55-1 NV_LIBNPP_DEV_VERSION=12.0.2.50-1 NV_LIBNPP_DEV_PACKAGE=libnpp-dev-12-1=12.0.2.50-1 NV_LIBCUBLAS_DEV_VERSION=12.1.0.26-1 NV_LIBCUBLAS_DEV_PACKAGE_NAME=libcublas-dev-12-1 NV_LIBCUBLAS_DEV_PACKAGE=libcublas-dev-12-1=12.1.0.26-1 NV_CUDA_NSIGHT_COMPUTE_VERSION=12.1.0-1 NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-12-1=12.1.0-1 NV_NVPROF_VERSION=12.1.55-1 NV_NVPROF_DEV_PACKAGE=cuda-nvprof-12-1=12.1.55-1 NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-dev NV_LIBNCCL_DEV_PACKAGE_VERSION=2.17.1-1 NV_LIBNCCL_DEV_PACKAGE=libnccl-dev=2.17.1-1+cuda12.1 LIBRARY_PATH=/usr/local/cuda/lib64/stubs DEBIAN_FRONTEND=noninteractive UV_HTTP_TIMEOUT=500 UV_INDEX_STRATEGY=unsafe-best-match 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

Docker拉取命令

docker pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/sasha0552/vllm:v0.9.1
docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/sasha0552/vllm:v0.9.1  ghcr.io/sasha0552/vllm:v0.9.1

Containerd拉取命令

ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/sasha0552/vllm:v0.9.1
ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/sasha0552/vllm:v0.9.1  ghcr.io/sasha0552/vllm:v0.9.1

Shell快速替换命令

sed -i 's#ghcr.io/sasha0552/vllm:v0.9.1#swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/sasha0552/vllm:v0.9.1#' deployment.yaml

Ansible快速分发-Docker

#ansible k8s -m shell -a 'docker pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/sasha0552/vllm:v0.9.1 && docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/sasha0552/vllm:v0.9.1  ghcr.io/sasha0552/vllm:v0.9.1'

Ansible快速分发-Containerd

#ansible k8s -m shell -a 'ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/sasha0552/vllm:v0.9.1 && ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/sasha0552/vllm:v0.9.1  ghcr.io/sasha0552/vllm:v0.9.1'

镜像构建历史


# 2025-08-23 22:37:48  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["python3" "-m" "vllm.entrypoints.openai.api_server"]
                        
# 2025-08-23 22:37:48  0.00B 设置环境变量 VLLM_USAGE_SOURCE
ENV VLLM_USAGE_SOURCE=production-docker-image
                        
# 2025-08-23 22:37:48  292.59MB 执行命令并创建新的镜像层
RUN |3 CUDA_VERSION=12.1.0 PYTHON_VERSION=3.12 TARGETPLATFORM=linux/amd64 /bin/bash -c if [ "$TARGETPLATFORM" = "linux/arm64" ]; then         uv pip install --system accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.42.0' 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3];     else         uv pip install --system accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.45.3' 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3];     fi # buildkit
                        
# 2025-08-23 22:37:45  0.00B 设置环境变量 UV_HTTP_TIMEOUT
ENV UV_HTTP_TIMEOUT=500
                        
# 2025-08-23 22:37:45  0.00B 定义构建参数
ARG TARGETPLATFORM=linux/amd64
                        
# 2025-08-23 22:37:45  74.75MB 执行命令并创建新的镜像层
RUN |3 CUDA_VERSION=12.1.0 PYTHON_VERSION=3.12 TARGETPLATFORM=linux/amd64 /bin/bash -c uv pip install --system -r requirements/build.txt     --extra-index-url https://download.pytorch.org/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') # buildkit
                        
# 2025-08-23 22:37:43  159.00B 复制新文件或目录到容器中
COPY requirements/build.txt requirements/build.txt # buildkit
                        
# 2025-08-23 22:37:43  0.00B 执行命令并创建新的镜像层
RUN |3 CUDA_VERSION=12.1.0 PYTHON_VERSION=3.12 TARGETPLATFORM=linux/amd64 /bin/bash -c . /etc/environment && uv pip list # buildkit
                        
# 2025-08-23 22:37:43  28.29KB 复制新文件或目录到容器中
COPY ./vllm/collect_env.py . # buildkit
                        
# 2025-08-23 22:37:42  540.34KB 复制新文件或目录到容器中
COPY benchmarks benchmarks # buildkit
                        
# 2025-08-23 22:37:42  599.88KB 复制新文件或目录到容器中
COPY examples examples # buildkit
                        
# 2025-08-23 22:37:42  29.79MB 执行命令并创建新的镜像层
RUN |3 CUDA_VERSION=12.1.0 PYTHON_VERSION=3.12 TARGETPLATFORM=linux/amd64 /bin/bash -c . /etc/environment && if [ "$TARGETPLATFORM" != "linux/arm64" ]; then     if [[ "$CUDA_VERSION" == 12.8* ]]; then         uv pip install --system https://download.pytorch.org/whl/cu128/flashinfer/flashinfer_python-0.2.5%2Bcu128torch2.7-cp38-abi3-linux_x86_64.whl;     else         export TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0+PTX';         CUDA_MAJOR="${CUDA_VERSION%%.*}";         if [ "$CUDA_MAJOR" -lt 12 ]; then             export FLASHINFER_ENABLE_SM90=0;         fi;         uv pip install --system --no-build-isolation "git+https://github.com/flashinfer-ai/flashinfer@21ea1d2545f74782b91eb8c08fd503ac4c0743fc" ;     fi fi # buildkit
                        
# 2025-08-23 22:37:28  7.54GB 执行命令并创建新的镜像层
RUN |3 CUDA_VERSION=12.1.0 PYTHON_VERSION=3.12 TARGETPLATFORM=linux/amd64 /bin/bash -c uv pip install --system dist/*.whl --verbose     --extra-index-url https://download.pytorch.org/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') &&     export PIP_EXTRA_INDEX_URL="https://sasha0552.github.io/pascal-pkgs-ci/" &&     python3 -m pip install transient-package &&     transient-package install --source triton --target triton-pascal &&     sed -e "s/.major < 7/.major < 6/g"         -e "s/.major >= 7/.major >= 6/g"         -i         /usr/local/lib/python3.12/dist-packages/torch/_inductor/scheduler.py         /usr/local/lib/python3.12/dist-packages/torch/utils/_triton.py # buildkit
                        
# 2025-08-23 22:36:38  0.00B 执行命令并创建新的镜像层
RUN |3 CUDA_VERSION=12.1.0 PYTHON_VERSION=3.12 TARGETPLATFORM=linux/amd64 /bin/bash -c if [ "$TARGETPLATFORM" = "linux/arm64" ]; then         uv pip install --system --index-url https://download.pytorch.org/whl/nightly/cu128 "torch==2.8.0.dev20250318+cu128" "torchvision==0.22.0.dev20250319";          uv pip install --system --index-url https://download.pytorch.org/whl/nightly/cu128 --pre pytorch_triton==3.3.0+gitab727c40;     fi # buildkit
                        
# 2025-08-23 22:36:37  56.86KB 执行命令并创建新的镜像层
RUN |3 CUDA_VERSION=12.1.0 PYTHON_VERSION=3.12 TARGETPLATFORM=linux/amd64 /bin/bash -c ldconfig /usr/local/cuda-$(echo $CUDA_VERSION | cut -d. -f1,2)/compat/ # buildkit
                        
# 2025-08-23 22:36:37  0.00B 设置环境变量 UV_INDEX_STRATEGY
ENV UV_INDEX_STRATEGY=unsafe-best-match
                        
# 2025-08-23 22:36:37  0.00B 设置环境变量 UV_HTTP_TIMEOUT
ENV UV_HTTP_TIMEOUT=500
                        
# 2025-08-23 22:36:37  68.17MB 执行命令并创建新的镜像层
RUN |3 CUDA_VERSION=12.1.0 PYTHON_VERSION=3.12 TARGETPLATFORM=linux/amd64 /bin/bash -c python3 -m pip install uv # buildkit
                        
# 2025-08-23 22:36:36  840.00MB 执行命令并创建新的镜像层
RUN |3 CUDA_VERSION=12.1.0 PYTHON_VERSION=3.12 TARGETPLATFORM=linux/amd64 /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     && for i in 1 2 3; do         add-apt-repository -y ppa:deadsnakes/ppa && break ||         { echo "Attempt $i failed, retrying in 5s..."; sleep 5; };     done     && apt-get update -y     && apt-get install -y python${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${PYTHON_VERSION}-config /usr/bin/python3-config     && curl -sS https://bootstrap.pypa.io/get-pip.py | python${PYTHON_VERSION}     && python3 --version && python3 -m pip --version # buildkit
                        
# 2025-08-23 22:35:46  136.00B 执行命令并创建新的镜像层
RUN |3 CUDA_VERSION=12.1.0 PYTHON_VERSION=3.12 TARGETPLATFORM=linux/amd64 /bin/bash -c PYTHON_VERSION_STR=$(echo ${PYTHON_VERSION} | sed 's/\.//g') &&     echo "export PYTHON_VERSION_STR=${PYTHON_VERSION_STR}" >> /etc/environment # buildkit
                        
# 2025-08-23 22:35:46  0.00B 
SHELL [/bin/bash -c]
                        
# 2025-08-23 22:35:46  0.00B 定义构建参数
ARG TARGETPLATFORM=linux/amd64
                        
# 2025-08-23 22:35:46  0.00B 设置环境变量 DEBIAN_FRONTEND
ENV DEBIAN_FRONTEND=noninteractive
                        
# 2025-08-23 22:35:46  0.00B 设置工作目录为/vllm-workspace
WORKDIR /vllm-workspace
                        
# 2025-08-23 22:35:46  0.00B 定义构建参数
ARG PYTHON_VERSION=3.12
                        
# 2025-08-23 22:35:46  0.00B 定义构建参数
ARG CUDA_VERSION=12.1.0
                        
# 2023-11-10 14:02:16  0.00B 设置环境变量 LIBRARY_PATH
ENV LIBRARY_PATH=/usr/local/cuda/lib64/stubs
                        
# 2023-11-10 14:02:16  385.64KB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-mark hold ${NV_LIBCUBLAS_DEV_PACKAGE_NAME} ${NV_LIBNCCL_DEV_PACKAGE_NAME} # buildkit
                        
# 2023-11-10 14:02:04  4.81GB 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-dev-12-1=${NV_CUDA_CUDART_DEV_VERSION}     cuda-command-line-tools-12-1=${NV_CUDA_LIB_VERSION}     cuda-minimal-build-12-1=${NV_CUDA_LIB_VERSION}     cuda-libraries-dev-12-1=${NV_CUDA_LIB_VERSION}     cuda-nvml-dev-12-1=${NV_NVML_DEV_VERSION}     ${NV_NVPROF_DEV_PACKAGE}     ${NV_LIBNPP_DEV_PACKAGE}     libcusparse-dev-12-1=${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
                        
# 2023-11-10 14:02:04  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2023-11-10 14:02:04  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2023-11-10 14:02:04  0.00B 设置环境变量 NV_LIBNCCL_DEV_PACKAGE
ENV NV_LIBNCCL_DEV_PACKAGE=libnccl-dev=2.17.1-1+cuda12.1
                        
# 2023-11-10 14:02:04  0.00B 设置环境变量 NCCL_VERSION
ENV NCCL_VERSION=2.17.1-1
                        
# 2023-11-10 14:02:04  0.00B 设置环境变量 NV_LIBNCCL_DEV_PACKAGE_VERSION
ENV NV_LIBNCCL_DEV_PACKAGE_VERSION=2.17.1-1
                        
# 2023-11-10 14:02:04  0.00B 设置环境变量 NV_LIBNCCL_DEV_PACKAGE_NAME
ENV NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-dev
                        
# 2023-11-10 14:02:04  0.00B 设置环境变量 NV_NVPROF_DEV_PACKAGE
ENV NV_NVPROF_DEV_PACKAGE=cuda-nvprof-12-1=12.1.55-1
                        
# 2023-11-10 14:02:04  0.00B 设置环境变量 NV_NVPROF_VERSION
ENV NV_NVPROF_VERSION=12.1.55-1
                        
# 2023-11-10 14:02:04  0.00B 设置环境变量 NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE
ENV NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-12-1=12.1.0-1
                        
# 2023-11-10 14:02:04  0.00B 设置环境变量 NV_CUDA_NSIGHT_COMPUTE_VERSION
ENV NV_CUDA_NSIGHT_COMPUTE_VERSION=12.1.0-1
                        
# 2023-11-10 14:02:04  0.00B 设置环境变量 NV_LIBCUBLAS_DEV_PACKAGE
ENV NV_LIBCUBLAS_DEV_PACKAGE=libcublas-dev-12-1=12.1.0.26-1
                        
# 2023-11-10 14:02:04  0.00B 设置环境变量 NV_LIBCUBLAS_DEV_PACKAGE_NAME
ENV NV_LIBCUBLAS_DEV_PACKAGE_NAME=libcublas-dev-12-1
                        
# 2023-11-10 14:02:04  0.00B 设置环境变量 NV_LIBCUBLAS_DEV_VERSION
ENV NV_LIBCUBLAS_DEV_VERSION=12.1.0.26-1
                        
# 2023-11-10 14:02:04  0.00B 设置环境变量 NV_LIBNPP_DEV_PACKAGE
ENV NV_LIBNPP_DEV_PACKAGE=libnpp-dev-12-1=12.0.2.50-1
                        
# 2023-11-10 14:02:04  0.00B 设置环境变量 NV_LIBNPP_DEV_VERSION
ENV NV_LIBNPP_DEV_VERSION=12.0.2.50-1
                        
# 2023-11-10 14:02:04  0.00B 设置环境变量 NV_LIBCUSPARSE_DEV_VERSION
ENV NV_LIBCUSPARSE_DEV_VERSION=12.0.2.55-1
                        
# 2023-11-10 14:02:04  0.00B 设置环境变量 NV_NVML_DEV_VERSION
ENV NV_NVML_DEV_VERSION=12.1.55-1
                        
# 2023-11-10 14:02:04  0.00B 设置环境变量 NV_CUDA_CUDART_DEV_VERSION
ENV NV_CUDA_CUDART_DEV_VERSION=12.1.55-1
                        
# 2023-11-10 14:02:04  0.00B 设置环境变量 NV_CUDA_LIB_VERSION
ENV NV_CUDA_LIB_VERSION=12.1.0-1
                        
# 2023-11-10 13:49:20  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
                        
# 2023-11-10 13:49:20  0.00B 设置环境变量 NVIDIA_CUDA_END_OF_LIFE
ENV NVIDIA_CUDA_END_OF_LIFE=1
                        
# 2023-11-10 13:49:20  0.00B 设置环境变量 NVIDIA_PRODUCT_NAME
ENV NVIDIA_PRODUCT_NAME=CUDA
                        
# 2023-11-10 13:49:20  2.53KB 复制新文件或目录到容器中
COPY nvidia_entrypoint.sh /opt/nvidia/ # buildkit
                        
# 2023-11-10 13:49:20  3.06KB 复制新文件或目录到容器中
COPY entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit
                        
# 2023-11-10 13:49:20  261.38KB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-mark hold ${NV_LIBCUBLAS_PACKAGE_NAME} ${NV_LIBNCCL_PACKAGE_NAME} # buildkit
                        
# 2023-11-10 13:49:19  1.99GB 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-libraries-12-1=${NV_CUDA_LIB_VERSION}     ${NV_LIBNPP_PACKAGE}     cuda-nvtx-12-1=${NV_NVTX_VERSION}     libcusparse-12-1=${NV_LIBCUSPARSE_VERSION}     ${NV_LIBCUBLAS_PACKAGE}     ${NV_LIBNCCL_PACKAGE}     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2023-11-10 13:49:19  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2023-11-10 13:49:19  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2023-11-10 13:49:19  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE
ENV NV_LIBNCCL_PACKAGE=libnccl2=2.17.1-1+cuda12.1
                        
# 2023-11-10 13:49:19  0.00B 设置环境变量 NCCL_VERSION
ENV NCCL_VERSION=2.17.1-1
                        
# 2023-11-10 13:49:19  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_VERSION
ENV NV_LIBNCCL_PACKAGE_VERSION=2.17.1-1
                        
# 2023-11-10 13:49:19  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_NAME
ENV NV_LIBNCCL_PACKAGE_NAME=libnccl2
                        
# 2023-11-10 13:49:19  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE
ENV NV_LIBCUBLAS_PACKAGE=libcublas-12-1=12.1.0.26-1
                        
# 2023-11-10 13:49:19  0.00B 设置环境变量 NV_LIBCUBLAS_VERSION
ENV NV_LIBCUBLAS_VERSION=12.1.0.26-1
                        
# 2023-11-10 13:49:19  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE_NAME
ENV NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-1
                        
# 2023-11-10 13:49:19  0.00B 设置环境变量 NV_LIBCUSPARSE_VERSION
ENV NV_LIBCUSPARSE_VERSION=12.0.2.55-1
                        
# 2023-11-10 13:49:19  0.00B 设置环境变量 NV_LIBNPP_PACKAGE
ENV NV_LIBNPP_PACKAGE=libnpp-12-1=12.0.2.50-1
                        
# 2023-11-10 13:49:19  0.00B 设置环境变量 NV_LIBNPP_VERSION
ENV NV_LIBNPP_VERSION=12.0.2.50-1
                        
# 2023-11-10 13:49:19  0.00B 设置环境变量 NV_NVTX_VERSION
ENV NV_NVTX_VERSION=12.1.66-1
                        
# 2023-11-10 13:49:19  0.00B 设置环境变量 NV_CUDA_LIB_VERSION
ENV NV_CUDA_LIB_VERSION=12.1.0-1
                        
# 2023-11-10 13:44:29  0.00B 设置环境变量 NVIDIA_DRIVER_CAPABILITIES
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
                        
# 2023-11-10 13:44:29  0.00B 设置环境变量 NVIDIA_VISIBLE_DEVICES
ENV NVIDIA_VISIBLE_DEVICES=all
                        
# 2023-11-10 13:44:29  17.29KB 复制新文件或目录到容器中
COPY NGC-DL-CONTAINER-LICENSE / # buildkit
                        
# 2023-11-10 13:44:29  0.00B 设置环境变量 LD_LIBRARY_PATH
ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64
                        
# 2023-11-10 13:44:29  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
                        
# 2023-11-10 13:44:29  46.00B 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c echo "/usr/local/nvidia/lib" >> /etc/ld.so.conf.d/nvidia.conf     && echo "/usr/local/nvidia/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit
                        
# 2023-11-10 13:44:29  149.59MB 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-12-1=${NV_CUDA_CUDART_VERSION}     ${NV_CUDA_COMPAT_PACKAGE}     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2023-11-10 13:44:18  0.00B 设置环境变量 CUDA_VERSION
ENV CUDA_VERSION=12.1.0
                        
# 2023-11-10 13:44:18  10.56MB 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 -fsSLO https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/${NVARCH}/cuda-keyring_1.0-1_all.deb &&     dpkg -i cuda-keyring_1.0-1_all.deb &&     apt-get purge --autoremove -y curl     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2023-11-10 13:44:18  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2023-11-10 13:44:18  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2023-11-10 13:44:18  0.00B 设置环境变量 NV_CUDA_COMPAT_PACKAGE
ENV NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-1
                        
# 2023-11-10 13:44:18  0.00B 设置环境变量 NV_CUDA_CUDART_VERSION
ENV NV_CUDA_CUDART_VERSION=12.1.55-1
                        
# 2023-11-10 13:44:18  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
ENV NVIDIA_REQUIRE_CUDA=cuda>=12.1 brand=tesla,driver>=470,driver<471 brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 brand=tesla,driver>=525,driver<526 brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526
                        
# 2023-11-10 13:44:18  0.00B 设置环境变量 NVARCH
ENV NVARCH=x86_64
                        
# 2023-10-05 15:33:32  0.00B 
/bin/sh -c #(nop)  CMD ["/bin/bash"]
                        
# 2023-10-05 15:33:32  77.82MB 
/bin/sh -c #(nop) ADD file:63d5ab3ef0aab308c0e71cb67292c5467f60deafa9b0418cbb220affcd078444 in / 
                        
# 2023-10-05 15:33:30  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.version=22.04
                        
# 2023-10-05 15:33:30  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.ref.name=ubuntu
                        
# 2023-10-05 15:33:30  0.00B 
/bin/sh -c #(nop)  ARG LAUNCHPAD_BUILD_ARCH
                        
# 2023-10-05 15:33:30  0.00B 
/bin/sh -c #(nop)  ARG RELEASE
                        
                    

镜像信息

{
    "Id": "sha256:3cfa4bda17ee27078f8288b81c383df48591fbf6d2e9db5d4149f06dc0bc8205",
    "RepoTags": [
        "ghcr.io/sasha0552/vllm:v0.9.1",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/sasha0552/vllm:v0.9.1"
    ],
    "RepoDigests": [
        "ghcr.io/sasha0552/vllm@sha256:aa9a3299b21aa80c65e6abf17081a9642b5f4b687d38c59e9df65a4d3cca814e",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/sasha0552/vllm@sha256:7e1e966cd8615c293638a731c182d31f08292faf99e010ca729c4ce0a424762b"
    ],
    "Parent": "",
    "Comment": "buildkit.dockerfile.v0",
    "Created": "2025-08-23T14:37:48.953377334Z",
    "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=12.1 brand=tesla,driver\u003e=470,driver\u003c471 brand=unknown,driver\u003e=470,driver\u003c471 brand=nvidia,driver\u003e=470,driver\u003c471 brand=nvidiartx,driver\u003e=470,driver\u003c471 brand=geforce,driver\u003e=470,driver\u003c471 brand=geforcertx,driver\u003e=470,driver\u003c471 brand=quadro,driver\u003e=470,driver\u003c471 brand=quadrortx,driver\u003e=470,driver\u003c471 brand=titan,driver\u003e=470,driver\u003c471 brand=titanrtx,driver\u003e=470,driver\u003c471 brand=tesla,driver\u003e=525,driver\u003c526 brand=unknown,driver\u003e=525,driver\u003c526 brand=nvidia,driver\u003e=525,driver\u003c526 brand=nvidiartx,driver\u003e=525,driver\u003c526 brand=geforce,driver\u003e=525,driver\u003c526 brand=geforcertx,driver\u003e=525,driver\u003c526 brand=quadro,driver\u003e=525,driver\u003c526 brand=quadrortx,driver\u003e=525,driver\u003c526 brand=titan,driver\u003e=525,driver\u003c526 brand=titanrtx,driver\u003e=525,driver\u003c526",
            "NV_CUDA_CUDART_VERSION=12.1.55-1",
            "NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-1",
            "CUDA_VERSION=12.1.0",
            "LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64",
            "NVIDIA_VISIBLE_DEVICES=all",
            "NVIDIA_DRIVER_CAPABILITIES=compute,utility",
            "NV_CUDA_LIB_VERSION=12.1.0-1",
            "NV_NVTX_VERSION=12.1.66-1",
            "NV_LIBNPP_VERSION=12.0.2.50-1",
            "NV_LIBNPP_PACKAGE=libnpp-12-1=12.0.2.50-1",
            "NV_LIBCUSPARSE_VERSION=12.0.2.55-1",
            "NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-1",
            "NV_LIBCUBLAS_VERSION=12.1.0.26-1",
            "NV_LIBCUBLAS_PACKAGE=libcublas-12-1=12.1.0.26-1",
            "NV_LIBNCCL_PACKAGE_NAME=libnccl2",
            "NV_LIBNCCL_PACKAGE_VERSION=2.17.1-1",
            "NCCL_VERSION=2.17.1-1",
            "NV_LIBNCCL_PACKAGE=libnccl2=2.17.1-1+cuda12.1",
            "NVIDIA_PRODUCT_NAME=CUDA",
            "NVIDIA_CUDA_END_OF_LIFE=1",
            "NV_CUDA_CUDART_DEV_VERSION=12.1.55-1",
            "NV_NVML_DEV_VERSION=12.1.55-1",
            "NV_LIBCUSPARSE_DEV_VERSION=12.0.2.55-1",
            "NV_LIBNPP_DEV_VERSION=12.0.2.50-1",
            "NV_LIBNPP_DEV_PACKAGE=libnpp-dev-12-1=12.0.2.50-1",
            "NV_LIBCUBLAS_DEV_VERSION=12.1.0.26-1",
            "NV_LIBCUBLAS_DEV_PACKAGE_NAME=libcublas-dev-12-1",
            "NV_LIBCUBLAS_DEV_PACKAGE=libcublas-dev-12-1=12.1.0.26-1",
            "NV_CUDA_NSIGHT_COMPUTE_VERSION=12.1.0-1",
            "NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-12-1=12.1.0-1",
            "NV_NVPROF_VERSION=12.1.55-1",
            "NV_NVPROF_DEV_PACKAGE=cuda-nvprof-12-1=12.1.55-1",
            "NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-dev",
            "NV_LIBNCCL_DEV_PACKAGE_VERSION=2.17.1-1",
            "NV_LIBNCCL_DEV_PACKAGE=libnccl-dev=2.17.1-1+cuda12.1",
            "LIBRARY_PATH=/usr/local/cuda/lib64/stubs",
            "DEBIAN_FRONTEND=noninteractive",
            "UV_HTTP_TIMEOUT=500",
            "UV_INDEX_STRATEGY=unsafe-best-match",
            "VLLM_USAGE_SOURCE=production-docker-image"
        ],
        "Cmd": null,
        "Image": "",
        "Volumes": null,
        "WorkingDir": "/vllm-workspace",
        "Entrypoint": [
            "python3",
            "-m",
            "vllm.entrypoints.openai.api_server"
        ],
        "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": "amd64",
    "Os": "linux",
    "Size": 15880808659,
    "GraphDriver": {
        "Data": {
            "LowerDir": "/var/lib/docker/overlay2/8e808a579c5e6328abeec779d8bdf1b41d12a080a343a7d9312d7a099448005c/diff:/var/lib/docker/overlay2/53ea69a2c76fbb854a87380e1a68cb0201f783f4e8d470b22c8bdc00dbe3fa69/diff:/var/lib/docker/overlay2/00492caec52c0a5e69542a286bf9252e1e72fb1af9a48a4ab4e32be441eb2a4a/diff:/var/lib/docker/overlay2/4cd3cf1542030f4dcb0eb339d2507d21f2acf904830a7c32309c002e6ff1ea13/diff:/var/lib/docker/overlay2/a9dfa6b5d0b939ec2ca75f82fdf1e52bc12d396be365926ad1995e4cc6f9a855/diff:/var/lib/docker/overlay2/28cade4a9494c28056fed375509dcd138a2f36fac307d3078c5c094c8fcad2a5/diff:/var/lib/docker/overlay2/5d36fa415755fc2b39d87168cecf5bd43699610a9845a869685663d6ebb1949c/diff:/var/lib/docker/overlay2/120cc45b67109213fa7917380ebb67f5cc30ddfa33d41a83dcfe1127e3ff4625/diff:/var/lib/docker/overlay2/4d56345e5f2e1db663c6ca39a53bc58e14bc357d141fa9d3ba0b0ea23f8e2e77/diff:/var/lib/docker/overlay2/775d6ec94f76c7778b8e5e54c9ad860cdf09468a3d5dce7a20ec632217b59dc2/diff:/var/lib/docker/overlay2/4fc094fc527867f68232d7811ed023ca522b30c481d032b9e9902d446a40d6de/diff:/var/lib/docker/overlay2/8c0884d83b330de4d8fed36bd2741dc8cd5c6007668a1be5586e01c3be93ec7c/diff:/var/lib/docker/overlay2/f15c1682fd4a82a11bbf51beb197e01cc1886c204cbbbdaefcc24679309ff8db/diff:/var/lib/docker/overlay2/ff36a799f54a08ef3eee1d397f5cd848e09012c9d29d374a1e5f176bc643ba15/diff:/var/lib/docker/overlay2/db4304e16362bbe4a55ceb219bf233fe5df3e485e6bf1af9834a9a1528b1106d/diff:/var/lib/docker/overlay2/67ca3729ca02464ea59c4eafe4f081930bf15605d02024d4d3558e09b600c5c3/diff:/var/lib/docker/overlay2/ad9909645812c361e364bef3d3d61ae213a9a0041fe70d565729395c475803b8/diff:/var/lib/docker/overlay2/3c6d5ea9f0137b810f2c5e9b2257e63f58baacba2c75b4c4722277357320216b/diff:/var/lib/docker/overlay2/2a4834c047db7ca33b0935fcf59cac785026edf2e275d07c484267f9dc406a9a/diff:/var/lib/docker/overlay2/6b5a2a88bc3906ccf1dd2ff2b3a48162e98f477f8153c2a3f46a4803c2a30c64/diff:/var/lib/docker/overlay2/86c98ab0ed88b61b06cf59d67d016cbf05a2c7cea2a7a4fe53a6be12a6bb87d7/diff:/var/lib/docker/overlay2/dddcc2c36b2b15125b046f443eaf956385215dd4fe1629756f29c2e1077ee125/diff:/var/lib/docker/overlay2/7c0ec148c160c668fe5b36bcb65f7d5badb55eb5dcdea8490e826c2a41b578a9/diff:/var/lib/docker/overlay2/b213e3c8abc27592f101ffbb1d0f2c437b5effe9b384d0f550f46a4f894f180d/diff:/var/lib/docker/overlay2/f2905627b4505cda033dd62b5a5dc1676edda5a6e1bda7cd6e6e2048fcf5aee0/diff",
            "MergedDir": "/var/lib/docker/overlay2/b8901b69cd89b900a870ae987a36deb926f21ec36674f18e131e73ea3b55463e/merged",
            "UpperDir": "/var/lib/docker/overlay2/b8901b69cd89b900a870ae987a36deb926f21ec36674f18e131e73ea3b55463e/diff",
            "WorkDir": "/var/lib/docker/overlay2/b8901b69cd89b900a870ae987a36deb926f21ec36674f18e131e73ea3b55463e/work"
        },
        "Name": "overlay2"
    },
    "RootFS": {
        "Type": "layers",
        "Layers": [
            "sha256:256d88da41857db513b95b50ba9a9b28491b58c954e25477d5dad8abb465430b",
            "sha256:7b9433fba79bfc9269aab8277ea9975364db1c1f775a7ee6b14b5dffa045b294",
            "sha256:765423415d690bf8ca1510e7147d5b86dba15dcf1a3b1a515f1a85cc5dd439bb",
            "sha256:e4b1bddcbe6378dfa58bf1faa040813b74938129eb4bb06cbf083240335c5c54",
            "sha256:cd77f58b80cdcfac5fcdef06b2033fedc1115073afae035a14b6692cb5cd6650",
            "sha256:8d113b7b997c1bc18469d2373662f02c8bbcf7182f8c5d8e0e1eea082cc234a4",
            "sha256:40f0eb1871b906cf31a54649bf4f7657e2a60da6d6a9adfb8598a469b8495e77",
            "sha256:6ac15100dff644720d396a534fcd373774b1aefca621211930855e5db5ebae52",
            "sha256:600c676771a0a21056d45f5fb4441c538380564d4a7127a41e260d74fc6b0519",
            "sha256:57b23d1076fd4d119609493ebbd5b837d9553387d081148c8d908f1245e2bb55",
            "sha256:6667c783780703607df00f8f7dafcfd77402d54db003c392f3ea743f9eabe359",
            "sha256:ac22c3a05dbb2affa36abec88208b4feb7531a9be811a9844b1f8368c453b299",
            "sha256:58a1f141621d11d4424873f1d9505662f6ade3a4868f96e98191e57da7324c26",
            "sha256:8aac6d11bc38c25a47aadfbe6c2a3609cef2f1c322471a7b739119d231333fa5",
            "sha256:fdd187fdcf09591e03f1b955458f36b507da37dd8adcec3fa02883284eafb66d",
            "sha256:66c40662c5b6d8ea3b66e561bcc401753b99dcf1fec16b23637ffab8bb5d4b57",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:454aa20c003066f90318e761fa8877d53a0353232d3516f9ec2089109920ae5f",
            "sha256:52b9d0b83b80210c9e8dba9123711f4a6612f42a2f2c3024119c6f1f6da76468",
            "sha256:fbd0a53217a1e5b52db04021242b043d9f927dffb6391044633495b65b116f27",
            "sha256:4321b86eac6b5ed981f11117ed6f2c4536f7d113852c1be40ca53068defdc8a8",
            "sha256:5130e6782bfcc59e295c4f5e02f91d5a68a1e29f6ac6f4d3212aefaa44d3b7a8",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:344f5436a36e4eeaccc02ea7ec7b1030542bf4bff918667fa7b16f133a465193",
            "sha256:b4db46ea2ee1c5b6ce9c4cd9a0bfb2fc94ee4ae2bdce839e3f5ea21e425c27c3",
            "sha256:7e07a5cdf58a29b2dfe4d0398703a67e0e4c8249295bcd9d9c2d5359e09873fb"
        ]
    },
    "Metadata": {
        "LastTagTime": "2025-10-10T00:14:10.650501457+08:00"
    }
}

更多版本

ghcr.io/sasha0552/vllm:v0.8.5

linux/amd64 ghcr.io16.51GB2025-07-19 01:37
303

ghcr.io/sasha0552/vllm:v0.9.1

linux/amd64 ghcr.io15.88GB2025-10-10 00:24
14