docker.io/openmmlab/lmdeploy:v0.8.0-cu11 linux/amd64

docker.io/openmmlab/lmdeploy:v0.8.0-cu11 - 国内下载镜像源 浏览次数:12

镜像描述:

lmdeploy

LM Deploy

LM Deploy 是 OpenMMLab 开发的用于模型部署和在线服务构建的工具。它提供了一个简洁易用的界面,帮助用户快速搭建和部署机器学习模型,包括图像分类、检测、分割等任务。在这个镜像中,你可以找到 LM Deploy 的相关组件和配置,以便你在自己的环境中使用和扩展它。

源镜像 docker.io/openmmlab/lmdeploy:v0.8.0-cu11
国内镜像 swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/openmmlab/lmdeploy:v0.8.0-cu11
镜像ID sha256:8fc9fd845d9f4304c672d2e6ac7b78c2b07318665ba73def1ec0ed21cd19ad15
镜像TAG v0.8.0-cu11
大小 16.30GB
镜像源 docker.io
项目信息 Docker-Hub主页 🚀项目TAG 🚀
CMD
启动入口 /opt/nvidia/nvidia_entrypoint.sh
工作目录 /opt/lmdeploy
OS/平台 linux/amd64
浏览量 12 次
贡献者 17********5@163.com
镜像创建 2025-05-04T06:08:56.317424866Z
同步时间 2025-06-06 00:36
更新时间 2025-06-06 23:47
环境变量
PATH=/opt/lmdeploy/install/bin:/opt/py3/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/openmpi/bin NVARCH=x86_64 NVIDIA_REQUIRE_CUDA=cuda>=11.8 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 NV_CUDA_CUDART_VERSION=11.8.89-1 NV_CUDA_COMPAT_PACKAGE=cuda-compat-11-8 CUDA_VERSION=11.8.0 LD_LIBRARY_PATH=/opt/lmdeploy/install/lib:/usr/local/nccl/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/openmpi/lib NVIDIA_VISIBLE_DEVICES=all NVIDIA_DRIVER_CAPABILITIES=compute,utility NV_CUDA_LIB_VERSION=11.8.0-1 NV_NVTX_VERSION=11.8.86-1 NV_LIBNPP_VERSION=11.8.0.86-1 NV_LIBNPP_PACKAGE=libnpp-11-8=11.8.0.86-1 NV_LIBCUSPARSE_VERSION=11.7.5.86-1 NV_LIBCUBLAS_PACKAGE_NAME=libcublas-11-8 NV_LIBCUBLAS_VERSION=11.11.3.6-1 NV_LIBCUBLAS_PACKAGE=libcublas-11-8=11.11.3.6-1 NV_LIBNCCL_PACKAGE_NAME=libnccl2 NV_LIBNCCL_PACKAGE_VERSION=2.15.5-1 NCCL_VERSION=2.15.5-1 NV_LIBNCCL_PACKAGE=libnccl2=2.15.5-1+cuda11.8 NVIDIA_PRODUCT_NAME=CUDA NV_CUDA_CUDART_DEV_VERSION=11.8.89-1 NV_NVML_DEV_VERSION=11.8.86-1 NV_LIBCUSPARSE_DEV_VERSION=11.7.5.86-1 NV_LIBNPP_DEV_VERSION=11.8.0.86-1 NV_LIBNPP_DEV_PACKAGE=libnpp-dev-11-8=11.8.0.86-1 NV_LIBCUBLAS_DEV_VERSION=11.11.3.6-1 NV_LIBCUBLAS_DEV_PACKAGE_NAME=libcublas-dev-11-8 NV_LIBCUBLAS_DEV_PACKAGE=libcublas-dev-11-8=11.11.3.6-1 NV_CUDA_NSIGHT_COMPUTE_VERSION=11.8.0-1 NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-11-8=11.8.0-1 NV_NVPROF_VERSION=11.8.87-1 NV_NVPROF_DEV_PACKAGE=cuda-nvprof-11-8=11.8.87-1 NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-dev NV_LIBNCCL_DEV_PACKAGE_VERSION=2.15.5-1 NV_LIBNCCL_DEV_PACKAGE=libnccl-dev=2.15.5-1+cuda11.8 LIBRARY_PATH=/usr/local/cuda/lib64/stubs CUDA_VERSION_SHORT=cu118 NCCL_LAUNCH_MODE=GROUP TRITON_PTXAS_PATH=/usr/local/cuda/bin/ptxas
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/docker.io/openmmlab/lmdeploy:v0.8.0-cu11
docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/openmmlab/lmdeploy:v0.8.0-cu11  docker.io/openmmlab/lmdeploy:v0.8.0-cu11

Containerd拉取命令

ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/openmmlab/lmdeploy:v0.8.0-cu11
ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/openmmlab/lmdeploy:v0.8.0-cu11  docker.io/openmmlab/lmdeploy:v0.8.0-cu11

Shell快速替换命令

sed -i 's#openmmlab/lmdeploy:v0.8.0-cu11#swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/openmmlab/lmdeploy:v0.8.0-cu11#' 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/openmmlab/lmdeploy:v0.8.0-cu11 && docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/openmmlab/lmdeploy:v0.8.0-cu11  docker.io/openmmlab/lmdeploy:v0.8.0-cu11'

Ansible快速分发-Containerd

#ansible k8s -m shell -a 'ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/openmmlab/lmdeploy:v0.8.0-cu11 && ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/openmmlab/lmdeploy:v0.8.0-cu11  docker.io/openmmlab/lmdeploy:v0.8.0-cu11'

镜像构建历史


# 2025-05-04 14:08:56  0.00B 设置环境变量 TRITON_PTXAS_PATH
ENV TRITON_PTXAS_PATH=/usr/local/cuda/bin/ptxas
                        
# 2025-05-04 14:08:56  0.00B 设置环境变量 PATH
ENV PATH=/opt/lmdeploy/install/bin:/opt/py3/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/openmpi/bin
                        
# 2025-05-04 14:08:56  0.00B 设置环境变量 LD_LIBRARY_PATH
ENV LD_LIBRARY_PATH=/opt/lmdeploy/install/lib:/usr/local/nccl/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/openmpi/lib
                        
# 2025-05-04 14:08:56  0.00B 执行命令并创建新的镜像层
RUN |1 PYTHON_VERSION=3.10 /bin/sh -c if [ "$CUDA_VERSION_SHORT" = "cu118" ]; then python3 -m pip uninstall -y nvidia-nccl-cu11 ; fi # buildkit
                        
# 2025-05-04 14:08:55  6.79GB 执行命令并创建新的镜像层
RUN |1 PYTHON_VERSION=3.10 /bin/sh -c cd /opt/lmdeploy &&    python3 -m pip install -r requirements_cuda.txt --extra-index-url https://download.pytorch.org/whl/${CUDA_VERSION_SHORT} &&    mkdir -p build && cd build &&    sh ../generate.sh &&    ninja -j$(nproc) && ninja install &&    cd .. &&    python3 -m pip install -e . &&    rm -rf build # buildkit
                        
# 2025-05-04 13:54:06  0.00B 设置工作目录为/opt/lmdeploy
WORKDIR /opt/lmdeploy
                        
# 2025-05-04 13:54:06  7.76MB 复制新文件或目录到容器中
COPY . /opt/lmdeploy # buildkit
                        
# 2025-05-04 13:54:05  0.00B 设置环境变量 NCCL_LAUNCH_MODE
ENV NCCL_LAUNCH_MODE=GROUP
                        
# 2025-05-04 13:54:05  84.12MB 执行命令并创建新的镜像层
RUN |1 PYTHON_VERSION=3.10 /bin/sh -c python3 -m pip install --upgrade pip setuptools==69.5.1 &&    python3 -m pip install cmake packaging wheel # buildkit
                        
# 2025-05-04 13:54:00  0.00B 设置环境变量 LD_LIBRARY_PATH
ENV LD_LIBRARY_PATH=/usr/local/nccl/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/openmpi/lib
                        
# 2025-05-04 13:54:00  532.50MB 执行命令并创建新的镜像层
RUN |1 PYTHON_VERSION=3.10 /bin/sh -c if [ "$CUDA_VERSION_SHORT" = "cu118" ]; then     git clone --depth=1 --branch v2.22.3-1 https://github.com/NVIDIA/nccl.git &&    cd nccl && make -j$(nproc) src.build &&    mv build/include/* /usr/local/include &&    mkdir -p /usr/local/nccl/lib &&    mv build/lib/lib* /usr/local/nccl/lib/ &&    cd .. && rm -rf nccl ;     fi # buildkit
                        
# 2025-05-04 13:17:10  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/openmpi/lib
                        
# 2025-05-04 13:17:10  0.00B 设置环境变量 PATH
ENV PATH=/opt/py3/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/openmpi/bin
                        
# 2025-05-04 13:17:10  13.04MB 执行命令并创建新的镜像层
RUN |1 PYTHON_VERSION=3.10 /bin/sh -c wget https://download.open-mpi.org/release/open-mpi/v4.1/openmpi-4.1.5.tar.gz &&    tar xf openmpi-4.1.5.tar.gz && cd openmpi-4.1.5 && ./configure --prefix=/usr/local/openmpi &&    make -j$(nproc) && make install && cd .. && rm -rf openmpi-4.1.5* # buildkit
                        
# 2025-05-04 13:12:13  0.00B 设置环境变量 PATH
ENV PATH=/opt/py3/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
                        
# 2025-05-04 13:12:13  1.50GB 执行命令并创建新的镜像层
RUN |1 PYTHON_VERSION=3.10 /bin/sh -c apt-get update -y && apt-get install -y software-properties-common wget vim git curl openssh-server ssh sudo &&    apt-get install libibverbs1 ibverbs-providers ibverbs-utils librdmacm1 libibverbs-dev rdma-core -y &&    curl https://sh.rustup.rs -sSf | sh -s -- -y &&    add-apt-repository ppa:deadsnakes/ppa -y && apt-get update -y && apt-get install -y --no-install-recommends     ninja-build rapidjson-dev libgoogle-glog-dev gdb python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv     && apt-get clean -y && rm -rf /var/lib/apt/lists/* && cd /opt && python3 -m venv py3 # buildkit
                        
# 2025-05-04 13:12:13  0.00B 定义构建参数
ARG PYTHON_VERSION=3.10
                        
# 2025-05-04 13:12:13  0.00B 设置环境变量 CUDA_VERSION_SHORT
ENV CUDA_VERSION_SHORT=cu118
                        
# 2023-11-10 14:55:21  0.00B 设置环境变量 LIBRARY_PATH
ENV LIBRARY_PATH=/usr/local/cuda/lib64/stubs
                        
# 2023-11-10 14:55:21  383.52KB 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 14:55:17  4.72GB 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-11-8=${NV_CUDA_CUDART_DEV_VERSION}     cuda-command-line-tools-11-8=${NV_CUDA_LIB_VERSION}     cuda-minimal-build-11-8=${NV_CUDA_LIB_VERSION}     cuda-libraries-dev-11-8=${NV_CUDA_LIB_VERSION}     cuda-nvml-dev-11-8=${NV_NVML_DEV_VERSION}     ${NV_NVPROF_DEV_PACKAGE}     ${NV_LIBNPP_DEV_PACKAGE}     libcusparse-dev-11-8=${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 14:55:17  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2023-11-10 14:55:17  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2023-11-10 14:55:17  0.00B 设置环境变量 NV_LIBNCCL_DEV_PACKAGE
ENV NV_LIBNCCL_DEV_PACKAGE=libnccl-dev=2.15.5-1+cuda11.8
                        
# 2023-11-10 14:55:17  0.00B 设置环境变量 NCCL_VERSION
ENV NCCL_VERSION=2.15.5-1
                        
# 2023-11-10 14:55:17  0.00B 设置环境变量 NV_LIBNCCL_DEV_PACKAGE_VERSION
ENV NV_LIBNCCL_DEV_PACKAGE_VERSION=2.15.5-1
                        
# 2023-11-10 14:55:17  0.00B 设置环境变量 NV_LIBNCCL_DEV_PACKAGE_NAME
ENV NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-dev
                        
# 2023-11-10 14:55:17  0.00B 设置环境变量 NV_NVPROF_DEV_PACKAGE
ENV NV_NVPROF_DEV_PACKAGE=cuda-nvprof-11-8=11.8.87-1
                        
# 2023-11-10 14:55:17  0.00B 设置环境变量 NV_NVPROF_VERSION
ENV NV_NVPROF_VERSION=11.8.87-1
                        
# 2023-11-10 14:55:17  0.00B 设置环境变量 NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE
ENV NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-11-8=11.8.0-1
                        
# 2023-11-10 14:55:17  0.00B 设置环境变量 NV_CUDA_NSIGHT_COMPUTE_VERSION
ENV NV_CUDA_NSIGHT_COMPUTE_VERSION=11.8.0-1
                        
# 2023-11-10 14:55:17  0.00B 设置环境变量 NV_LIBCUBLAS_DEV_PACKAGE
ENV NV_LIBCUBLAS_DEV_PACKAGE=libcublas-dev-11-8=11.11.3.6-1
                        
# 2023-11-10 14:55:17  0.00B 设置环境变量 NV_LIBCUBLAS_DEV_PACKAGE_NAME
ENV NV_LIBCUBLAS_DEV_PACKAGE_NAME=libcublas-dev-11-8
                        
# 2023-11-10 14:55:17  0.00B 设置环境变量 NV_LIBCUBLAS_DEV_VERSION
ENV NV_LIBCUBLAS_DEV_VERSION=11.11.3.6-1
                        
# 2023-11-10 14:55:17  0.00B 设置环境变量 NV_LIBNPP_DEV_PACKAGE
ENV NV_LIBNPP_DEV_PACKAGE=libnpp-dev-11-8=11.8.0.86-1
                        
# 2023-11-10 14:55:17  0.00B 设置环境变量 NV_LIBNPP_DEV_VERSION
ENV NV_LIBNPP_DEV_VERSION=11.8.0.86-1
                        
# 2023-11-10 14:55:17  0.00B 设置环境变量 NV_LIBCUSPARSE_DEV_VERSION
ENV NV_LIBCUSPARSE_DEV_VERSION=11.7.5.86-1
                        
# 2023-11-10 14:55:17  0.00B 设置环境变量 NV_NVML_DEV_VERSION
ENV NV_NVML_DEV_VERSION=11.8.86-1
                        
# 2023-11-10 14:55:17  0.00B 设置环境变量 NV_CUDA_CUDART_DEV_VERSION
ENV NV_CUDA_CUDART_DEV_VERSION=11.8.89-1
                        
# 2023-11-10 14:55:17  0.00B 设置环境变量 NV_CUDA_LIB_VERSION
ENV NV_CUDA_LIB_VERSION=11.8.0-1
                        
# 2023-11-10 14:42:37  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
                        
# 2023-11-10 14:42:37  0.00B 设置环境变量 NVIDIA_PRODUCT_NAME
ENV NVIDIA_PRODUCT_NAME=CUDA
                        
# 2023-11-10 14:42:37  2.53KB 复制新文件或目录到容器中
COPY nvidia_entrypoint.sh /opt/nvidia/ # buildkit
                        
# 2023-11-10 14:42:37  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 14:42:37  260.16KB 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 14:42:36  2.41GB 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-11-8=${NV_CUDA_LIB_VERSION}     ${NV_LIBNPP_PACKAGE}     cuda-nvtx-11-8=${NV_NVTX_VERSION}     libcusparse-11-8=${NV_LIBCUSPARSE_VERSION}     ${NV_LIBCUBLAS_PACKAGE}     ${NV_LIBNCCL_PACKAGE}     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2023-11-10 14:42:36  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2023-11-10 14:42:36  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2023-11-10 14:42:36  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE
ENV NV_LIBNCCL_PACKAGE=libnccl2=2.15.5-1+cuda11.8
                        
# 2023-11-10 14:42:36  0.00B 设置环境变量 NCCL_VERSION
ENV NCCL_VERSION=2.15.5-1
                        
# 2023-11-10 14:42:36  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_VERSION
ENV NV_LIBNCCL_PACKAGE_VERSION=2.15.5-1
                        
# 2023-11-10 14:42:36  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_NAME
ENV NV_LIBNCCL_PACKAGE_NAME=libnccl2
                        
# 2023-11-10 14:42:36  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE
ENV NV_LIBCUBLAS_PACKAGE=libcublas-11-8=11.11.3.6-1
                        
# 2023-11-10 14:42:36  0.00B 设置环境变量 NV_LIBCUBLAS_VERSION
ENV NV_LIBCUBLAS_VERSION=11.11.3.6-1
                        
# 2023-11-10 14:42:36  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE_NAME
ENV NV_LIBCUBLAS_PACKAGE_NAME=libcublas-11-8
                        
# 2023-11-10 14:42:36  0.00B 设置环境变量 NV_LIBCUSPARSE_VERSION
ENV NV_LIBCUSPARSE_VERSION=11.7.5.86-1
                        
# 2023-11-10 14:42:36  0.00B 设置环境变量 NV_LIBNPP_PACKAGE
ENV NV_LIBNPP_PACKAGE=libnpp-11-8=11.8.0.86-1
                        
# 2023-11-10 14:42:36  0.00B 设置环境变量 NV_LIBNPP_VERSION
ENV NV_LIBNPP_VERSION=11.8.0.86-1
                        
# 2023-11-10 14:42:36  0.00B 设置环境变量 NV_NVTX_VERSION
ENV NV_NVTX_VERSION=11.8.86-1
                        
# 2023-11-10 14:42:36  0.00B 设置环境变量 NV_CUDA_LIB_VERSION
ENV NV_CUDA_LIB_VERSION=11.8.0-1
                        
# 2023-11-10 14:37:16  0.00B 设置环境变量 NVIDIA_DRIVER_CAPABILITIES
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
                        
# 2023-11-10 14:37:16  0.00B 设置环境变量 NVIDIA_VISIBLE_DEVICES
ENV NVIDIA_VISIBLE_DEVICES=all
                        
# 2023-11-10 14:37:16  17.29KB 复制新文件或目录到容器中
COPY NGC-DL-CONTAINER-LICENSE / # buildkit
                        
# 2023-11-10 14:37:16  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 14:37:16  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 14:37:16  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 14:37:16  150.67MB 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-11-8=${NV_CUDA_CUDART_VERSION}     ${NV_CUDA_COMPAT_PACKAGE}     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2023-11-10 14:37:01  0.00B 设置环境变量 CUDA_VERSION
ENV CUDA_VERSION=11.8.0
                        
# 2023-11-10 14:37:01  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 14:37:01  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2023-11-10 14:37:01  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2023-11-10 14:37:01  0.00B 设置环境变量 NV_CUDA_COMPAT_PACKAGE
ENV NV_CUDA_COMPAT_PACKAGE=cuda-compat-11-8
                        
# 2023-11-10 14:37:01  0.00B 设置环境变量 NV_CUDA_CUDART_VERSION
ENV NV_CUDA_CUDART_VERSION=11.8.89-1
                        
# 2023-11-10 14:37:01  0.00B 设置环境变量 NVIDIA_REQUIRE_CUDA brand brand brand brand brand brand brand brand brand brand
ENV NVIDIA_REQUIRE_CUDA=cuda>=11.8 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
                        
# 2023-11-10 14:37:01  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": "sha256:8fc9fd845d9f4304c672d2e6ac7b78c2b07318665ba73def1ec0ed21cd19ad15",
    "RepoTags": [
        "openmmlab/lmdeploy:v0.8.0-cu11",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/openmmlab/lmdeploy:v0.8.0-cu11"
    ],
    "RepoDigests": [
        "openmmlab/lmdeploy@sha256:a9023a65de25e7d29ed93b5282cd37d4bb61d441186bee8ce8113970f8c6131b",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/openmmlab/lmdeploy@sha256:47a3d03c82b299ba28832e4ead94b0857b8f65242d8829886ebea6fa2a605738"
    ],
    "Parent": "",
    "Comment": "buildkit.dockerfile.v0",
    "Created": "2025-05-04T06:08:56.317424866Z",
    "Container": "",
    "ContainerConfig": null,
    "DockerVersion": "",
    "Author": "",
    "Config": {
        "Hostname": "",
        "Domainname": "",
        "User": "",
        "AttachStdin": false,
        "AttachStdout": false,
        "AttachStderr": false,
        "Tty": false,
        "OpenStdin": false,
        "StdinOnce": false,
        "Env": [
            "PATH=/opt/lmdeploy/install/bin:/opt/py3/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/openmpi/bin",
            "NVARCH=x86_64",
            "NVIDIA_REQUIRE_CUDA=cuda\u003e=11.8 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",
            "NV_CUDA_CUDART_VERSION=11.8.89-1",
            "NV_CUDA_COMPAT_PACKAGE=cuda-compat-11-8",
            "CUDA_VERSION=11.8.0",
            "LD_LIBRARY_PATH=/opt/lmdeploy/install/lib:/usr/local/nccl/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/openmpi/lib",
            "NVIDIA_VISIBLE_DEVICES=all",
            "NVIDIA_DRIVER_CAPABILITIES=compute,utility",
            "NV_CUDA_LIB_VERSION=11.8.0-1",
            "NV_NVTX_VERSION=11.8.86-1",
            "NV_LIBNPP_VERSION=11.8.0.86-1",
            "NV_LIBNPP_PACKAGE=libnpp-11-8=11.8.0.86-1",
            "NV_LIBCUSPARSE_VERSION=11.7.5.86-1",
            "NV_LIBCUBLAS_PACKAGE_NAME=libcublas-11-8",
            "NV_LIBCUBLAS_VERSION=11.11.3.6-1",
            "NV_LIBCUBLAS_PACKAGE=libcublas-11-8=11.11.3.6-1",
            "NV_LIBNCCL_PACKAGE_NAME=libnccl2",
            "NV_LIBNCCL_PACKAGE_VERSION=2.15.5-1",
            "NCCL_VERSION=2.15.5-1",
            "NV_LIBNCCL_PACKAGE=libnccl2=2.15.5-1+cuda11.8",
            "NVIDIA_PRODUCT_NAME=CUDA",
            "NV_CUDA_CUDART_DEV_VERSION=11.8.89-1",
            "NV_NVML_DEV_VERSION=11.8.86-1",
            "NV_LIBCUSPARSE_DEV_VERSION=11.7.5.86-1",
            "NV_LIBNPP_DEV_VERSION=11.8.0.86-1",
            "NV_LIBNPP_DEV_PACKAGE=libnpp-dev-11-8=11.8.0.86-1",
            "NV_LIBCUBLAS_DEV_VERSION=11.11.3.6-1",
            "NV_LIBCUBLAS_DEV_PACKAGE_NAME=libcublas-dev-11-8",
            "NV_LIBCUBLAS_DEV_PACKAGE=libcublas-dev-11-8=11.11.3.6-1",
            "NV_CUDA_NSIGHT_COMPUTE_VERSION=11.8.0-1",
            "NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-11-8=11.8.0-1",
            "NV_NVPROF_VERSION=11.8.87-1",
            "NV_NVPROF_DEV_PACKAGE=cuda-nvprof-11-8=11.8.87-1",
            "NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-dev",
            "NV_LIBNCCL_DEV_PACKAGE_VERSION=2.15.5-1",
            "NV_LIBNCCL_DEV_PACKAGE=libnccl-dev=2.15.5-1+cuda11.8",
            "LIBRARY_PATH=/usr/local/cuda/lib64/stubs",
            "CUDA_VERSION_SHORT=cu118",
            "NCCL_LAUNCH_MODE=GROUP",
            "TRITON_PTXAS_PATH=/usr/local/cuda/bin/ptxas"
        ],
        "Cmd": null,
        "Image": "",
        "Volumes": null,
        "WorkingDir": "/opt/lmdeploy",
        "Entrypoint": [
            "/opt/nvidia/nvidia_entrypoint.sh"
        ],
        "OnBuild": null,
        "Labels": {
            "maintainer": "NVIDIA CORPORATION \u003ccudatools@nvidia.com\u003e",
            "org.opencontainers.image.ref.name": "ubuntu",
            "org.opencontainers.image.version": "22.04"
        }
    },
    "Architecture": "amd64",
    "Os": "linux",
    "Size": 16295092623,
    "GraphDriver": {
        "Data": {
            "LowerDir": "/var/lib/docker/overlay2/ab3c31503c3c66c33d8dc3b34565e850ff70da3dcf08ba6f0cfabef931bfc781/diff:/var/lib/docker/overlay2/9524aa4f8127ffbb74f18c53fb87095972333d8d55472b0e5d6081a8fda8d376/diff:/var/lib/docker/overlay2/3a6406aeeea62529c4a998cb9fe3cb351e3338a3a40e91e9e5951f82f1ca283a/diff:/var/lib/docker/overlay2/96b9724118f139f4e6e69446ffb83ea7013a44b43932724afdc0096ece040735/diff:/var/lib/docker/overlay2/43ee4548a55a81bf1903b843e712db645bee33d407b12db9edf0e2044d47e528/diff:/var/lib/docker/overlay2/a7f935b55c563d7e6cb1a2d6c42a82792bda93d748325597ed05005bb28d6f65/diff:/var/lib/docker/overlay2/0960ee4acba91c18096b029d1ddf13f5fe7e573660b8d2047dc668eb9eba3a09/diff:/var/lib/docker/overlay2/3acef4e240085ce45af786d7e725c09ac013f0d9a8893a5cd360ee5b099f9738/diff:/var/lib/docker/overlay2/d5724d244c79a192a67a8567b9c62eafa9b8653a6a4630666c1dcd17137f56d6/diff:/var/lib/docker/overlay2/7478ccb55d5dfe13861ff116874f156660ede9837872cc8764ae50aa9c5a2643/diff:/var/lib/docker/overlay2/f871f834b06ed3be2f2480ae05e54440ebd03167995fa5afe1789f53c5b87b26/diff:/var/lib/docker/overlay2/018534e64a47d38414904733de6a226a84ff7642b9138e0b3886c4614be0939f/diff:/var/lib/docker/overlay2/c9bd387db790508d31d5686f301ec9bf168df8775b43a3e0e4a2685e751eefe3/diff:/var/lib/docker/overlay2/e82ec86304233c70626de85db86f37871408fe6d5d30a0c4ef527fe22a61e254/diff:/var/lib/docker/overlay2/8d92641e79577adb975b895f850f294a0cf2618e206b0d9f6f78a348cc893270/diff:/var/lib/docker/overlay2/ef7f864040c15ee5635b928f56d1fb2e285908a9d6590a7a322c03bcb12c01eb/diff:/var/lib/docker/overlay2/b6628679832b97593ba73a7966b97f40b2a5da22f99ce52b7265fab985bf3cf0/diff:/var/lib/docker/overlay2/f2905627b4505cda033dd62b5a5dc1676edda5a6e1bda7cd6e6e2048fcf5aee0/diff",
            "MergedDir": "/var/lib/docker/overlay2/a8dd9228f2856d5a872d727b2ad0a5eaed8af6bb2f763e997aaf9fa6fab3a491/merged",
            "UpperDir": "/var/lib/docker/overlay2/a8dd9228f2856d5a872d727b2ad0a5eaed8af6bb2f763e997aaf9fa6fab3a491/diff",
            "WorkDir": "/var/lib/docker/overlay2/a8dd9228f2856d5a872d727b2ad0a5eaed8af6bb2f763e997aaf9fa6fab3a491/work"
        },
        "Name": "overlay2"
    },
    "RootFS": {
        "Type": "layers",
        "Layers": [
            "sha256:256d88da41857db513b95b50ba9a9b28491b58c954e25477d5dad8abb465430b",
            "sha256:e6c05e83c163d632918d1c4906ee088b1e0d93a5bb3acfc6a268da52e76cc945",
            "sha256:d6b19a46b795f8b562888c6e2826a6b11f744ab98543268b4d45ee1af05ed1cf",
            "sha256:c0e21dcee62311c36e1f025307b3186a4b4a034f0b52011704402b39623b6587",
            "sha256:498bbcc60d01b2080fd6fc35117cb82c80ddd4eb8a654ee330dd91587b7ec90b",
            "sha256:bc352a27a0e47d42df7bc06e702351a4f3102d20016484c9613644dba63239e0",
            "sha256:399d155a03b034314cd9ea52e4e1feca44be4cf92ae172ba9c6ce14f5897f0a2",
            "sha256:dcb0f55f81ad931bb976c65730e4bafe7a03936d1fd1bd0fec6a9bcfde23561d",
            "sha256:345cfa465206a6d1cc0812481df7edbc4553b64a26c63ccda0e5b11b0f2bf81b",
            "sha256:23d753990c8d9e30e33dc706e188972e17fd21ae60b51bbce058d6d74aa08d29",
            "sha256:64758552f6fa927694d06ecab82c2a3d1f55e6bfb09c715b6d37f2963eaaa62c",
            "sha256:c556846514653541ecefa27fe146cbc486c3a232d5bcd9f22526c461a1f4913c",
            "sha256:430f60eb61e496ae8be06c4592cd97d4796fb553772020c606ccc126dea43ff2",
            "sha256:ce8e69e93ed0034be3d2d4784b4d0013dcb1ee2524bbf3a42cb3e638f187f9b5",
            "sha256:843bbcc0fb986ca461ce1fd75d3ccf4c28943bb09e72997c481138c6ebf1b5df",
            "sha256:a0e4c7abd8191468afc949fef671631f840c477497ae0248986ba342fca7ba7b",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:6c30f24f50809b8b485f23b5b12bab44515ba1da08ea4c716d61bea984233473",
            "sha256:eb69a7bb4835a2aadbca36aa1575bc335352bb2d3fe70f4c62faacdf3d124d14"
        ]
    },
    "Metadata": {
        "LastTagTime": "2025-06-06T00:26:27.343632572+08:00"
    }
}

更多版本

docker.io/openmmlab/lmdeploy:v0.6.1-cu11

linux/amd64 docker.io16.62GB2024-09-30 11:49
304

docker.io/openmmlab/lmdeploy:v0.6.3.post1-cu12

linux/amd64 docker.io16.08GB2024-11-30 00:20
201

docker.io/openmmlab/lmdeploy:v0.7.1-cu12

linux/amd64 docker.io15.62GB2025-03-02 00:24
193

docker.io/openmmlab/lmdeploy:v0.7.2-cu12

linux/amd64 docker.io15.33GB2025-03-29 00:24
152

docker.io/openmmlab/lmdeploy:v0.8.0-cu12

linux/amd64 docker.io15.46GB2025-05-27 01:22
35

docker.io/openmmlab/lmdeploy:latest

linux/amd64 docker.io15.46GB2025-05-27 02:44
39

docker.io/openmmlab/lmdeploy:v0.8.0-cu11

linux/amd64 docker.io16.30GB2025-06-06 00:36
11