docker.io/lmsysorg/sglang:latest linux/amd64

docker.io/lmsysorg/sglang:latest - 国内下载镜像源浏览次数:310

sglang 是一个基于 LMSYS 的 Shell Grammar Language 环境容器镜像。

源镜像	docker.io/lmsysorg/sglang:latest
国内镜像	swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/lmsysorg/sglang:latest
镜像ID	sha256:a103a729631857f6ca7ec4a6aa6472b1ea65218765bc2c2d3cb33844329c59a2
镜像TAG	latest
大小	15.95GB
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	/sgl-workspace
OS/平台	linux/amd64
浏览量	310 次
贡献者	ya*****n@tslsmart.com
镜像创建	2024-10-25T18:11:36.728469677Z
同步时间	2024-10-29 01:12
更新时间	2025-02-22 02:27

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=12.1.105-1 NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-1 CUDA_VERSION=12.1.1 LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64 NVIDIA_VISIBLE_DEVICES=all NVIDIA_DRIVER_CAPABILITIES=compute,utility NV_CUDA_LIB_VERSION=12.1.1-1 NV_NVTX_VERSION=12.1.105-1 NV_LIBNPP_VERSION=12.1.0.40-1 NV_LIBNPP_PACKAGE=libnpp-12-1=12.1.0.40-1 NV_LIBCUSPARSE_VERSION=12.1.0.106-1 NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-1 NV_LIBCUBLAS_VERSION=12.1.3.1-1 NV_LIBCUBLAS_PACKAGE=libcublas-12-1=12.1.3.1-1 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 NV_CUDA_CUDART_DEV_VERSION=12.1.105-1 NV_NVML_DEV_VERSION=12.1.105-1 NV_LIBCUSPARSE_DEV_VERSION=12.1.0.106-1 NV_LIBNPP_DEV_VERSION=12.1.0.40-1 NV_LIBNPP_DEV_PACKAGE=libnpp-dev-12-1=12.1.0.40-1 NV_LIBCUBLAS_DEV_VERSION=12.1.3.1-1 NV_LIBCUBLAS_DEV_PACKAGE_NAME=libcublas-dev-12-1 NV_LIBCUBLAS_DEV_PACKAGE=libcublas-dev-12-1=12.1.3.1-1 NV_CUDA_NSIGHT_COMPUTE_VERSION=12.1.1-1 NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-12-1=12.1.1-1 NV_NVPROF_VERSION=12.1.105-1 NV_NVPROF_DEV_PACKAGE=cuda-nvprof-12-1=12.1.105-1 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=interactive

镜像标签

NVIDIA CORPORATION <cudatools@nvidia.com>: maintainer ubuntu: org.opencontainers.image.ref.name 20.04: org.opencontainers.image.version

镜像安全扫描查看Trivy扫描报告

系统OS: ubuntu 20.04 扫描引擎: Trivy 扫描时间: 2024-10-29 03:22

低危漏洞:187

中危漏洞:1523

高危漏洞:31

严重漏洞:0

docker.io/lmsysorg/sglang:latest (ubuntu 20.04) (ubuntu)

Java (jar)

Python (python-pkg)

阿里云高校计划(￥300代金券)领取

阿里云2核2G高性能云服务器 99元/年❤️

华为云2核4G2M云服务器，惊爆价99元1年

腾讯云2核2G云服务器，惊爆价99元1年

Ucloud 2核2G4M 59元/年❤️ 香港专线400G流量/月服务器 93元/年❤️

GPU创意AI画图炼丹服务器

GPT人工智能60G学习资料❤️

Docker拉取命令无权限下载?点我修复

docker pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/lmsysorg/sglang:latest
docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/lmsysorg/sglang:latest  docker.io/lmsysorg/sglang:latest

Containerd拉取命令

ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/lmsysorg/sglang:latest
ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/lmsysorg/sglang:latest  docker.io/lmsysorg/sglang:latest

Shell快速替换命令

sed -i 's#lmsysorg/sglang:latest#swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/lmsysorg/sglang:latest#' 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/lmsysorg/sglang:latest && docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/lmsysorg/sglang:latest  docker.io/lmsysorg/sglang:latest'

Ansible快速分发-Containerd

#ansible k8s -m shell -a 'ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/lmsysorg/sglang:latest && ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/lmsysorg/sglang:latest  docker.io/lmsysorg/sglang:latest'

镜像构建历史


# 2024-10-26 02:11:36  0.00B 设置环境变量 DEBIAN_FRONTEND
ENV DEBIAN_FRONTEND=interactive
                        
# 2024-10-26 02:11:36  0.00B 执行命令并创建新的镜像层
RUN |2 BUILD_TYPE=all CUDA_VERSION=12.1.1 /bin/sh -c python3 -m pip cache purge # buildkit
                        
# 2024-10-26 02:11:36  1.84GB 执行命令并创建新的镜像层
RUN |2 BUILD_TYPE=all CUDA_VERSION=12.1.1 /bin/sh -c if [ "$CUDA_VERSION" = "12.1.1" ]; then         export CUDA_IDENTIFIER=cu121 &&         python3 -m pip --no-cache-dir install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/;     elif [ "$CUDA_VERSION" = "12.4.1" ]; then         export CUDA_IDENTIFIER=cu124 &&         python3 -m pip --no-cache-dir install flashinfer -i https://flashinfer.ai/whl/cu124/torch2.4/;     elif [ "$CUDA_VERSION" = "11.8.0" ]; then         export CUDA_IDENTIFIER=cu118 &&         python3 -m pip install torch==2.4.0 --index-url https://download.pytorch.org/whl/cu118 &&         python3 -m pip --no-cache-dir install flashinfer -i https://flashinfer.ai/whl/cu118/torch2.4/;     else         echo "Unsupported CUDA version: $CUDA_VERSION" && exit 1;     fi # buildkit
                        
# 2024-10-26 02:11:11  0.00B 定义构建参数
ARG CUDA_VERSION
                        
# 2024-10-26 02:11:11  6.81GB 执行命令并创建新的镜像层
RUN |1 BUILD_TYPE=all /bin/sh -c python3 -m pip install --upgrade pip setuptools wheel html5lib six     && git clone --depth=1 https://github.com/sgl-project/sglang.git     && cd sglang     && if [ "$BUILD_TYPE" = "srt" ]; then          python3 -m pip --no-cache-dir install -e "python[srt]";        else          python3 -m pip --no-cache-dir install -e "python[all]";        fi # buildkit
                        
# 2024-10-26 02:09:19  0.00B 设置工作目录为/sgl-workspace
WORKDIR /sgl-workspace
                        
# 2024-10-26 02:09:19  31.56MB 执行命令并创建新的镜像层
RUN |1 BUILD_TYPE=all /bin/sh -c pip3 install datamodel_code_generator # buildkit
                        
# 2024-10-26 02:09:15  247.79MB 执行命令并创建新的镜像层
RUN |1 BUILD_TYPE=all /bin/sh -c echo 'tzdata tzdata/Areas select America' | debconf-set-selections     && echo 'tzdata tzdata/Zones/America select Los_Angeles' | debconf-set-selections     && apt update -y     && apt install software-properties-common -y     && add-apt-repository ppa:deadsnakes/ppa -y && apt update     && apt install python3.10 python3.10-dev -y     && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.8 1 && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 2     && update-alternatives --set python3 /usr/bin/python3.10 && apt install python3.10-distutils -y     && apt install curl git sudo libibverbs-dev -y     && curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py && python3 get-pip.py     && python3 --version     && python3 -m pip --version     && rm -rf /var/lib/apt/lists/*     && apt clean # buildkit
                        
# 2024-10-26 02:09:15  0.00B 设置环境变量 DEBIAN_FRONTEND
ENV DEBIAN_FRONTEND=noninteractive
                        
# 2024-10-26 02:09:15  0.00B 定义构建参数
ARG BUILD_TYPE=all
                        
# 2023-11-10 13:25:45  0.00B 设置环境变量 LIBRARY_PATH
ENV LIBRARY_PATH=/usr/local/cuda/lib64/stubs
                        
# 2023-11-10 13:25:45  379.49KB 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 13:25:42  4.77GB 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     libtinfo5 libncursesw5     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 13:25:42  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2023-11-10 13:25:42  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2023-11-10 13:25:42  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 13:25:42  0.00B 设置环境变量 NCCL_VERSION
ENV NCCL_VERSION=2.17.1-1
                        
# 2023-11-10 13:25:42  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 13:25:42  0.00B 设置环境变量 NV_LIBNCCL_DEV_PACKAGE_NAME
ENV NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-dev
                        
# 2023-11-10 13:25:42  0.00B 设置环境变量 NV_NVPROF_DEV_PACKAGE
ENV NV_NVPROF_DEV_PACKAGE=cuda-nvprof-12-1=12.1.105-1
                        
# 2023-11-10 13:25:42  0.00B 设置环境变量 NV_NVPROF_VERSION
ENV NV_NVPROF_VERSION=12.1.105-1
                        
# 2023-11-10 13:25:42  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=12.1.1-1
                        
# 2023-11-10 13:25:42  0.00B 设置环境变量 NV_CUDA_NSIGHT_COMPUTE_VERSION
ENV NV_CUDA_NSIGHT_COMPUTE_VERSION=12.1.1-1
                        
# 2023-11-10 13:25:42  0.00B 设置环境变量 NV_LIBCUBLAS_DEV_PACKAGE
ENV NV_LIBCUBLAS_DEV_PACKAGE=libcublas-dev-12-1=12.1.3.1-1
                        
# 2023-11-10 13:25:42  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 13:25:42  0.00B 设置环境变量 NV_LIBCUBLAS_DEV_VERSION
ENV NV_LIBCUBLAS_DEV_VERSION=12.1.3.1-1
                        
# 2023-11-10 13:25:42  0.00B 设置环境变量 NV_LIBNPP_DEV_PACKAGE
ENV NV_LIBNPP_DEV_PACKAGE=libnpp-dev-12-1=12.1.0.40-1
                        
# 2023-11-10 13:25:42  0.00B 设置环境变量 NV_LIBNPP_DEV_VERSION
ENV NV_LIBNPP_DEV_VERSION=12.1.0.40-1
                        
# 2023-11-10 13:25:42  0.00B 设置环境变量 NV_LIBCUSPARSE_DEV_VERSION
ENV NV_LIBCUSPARSE_DEV_VERSION=12.1.0.106-1
                        
# 2023-11-10 13:25:42  0.00B 设置环境变量 NV_NVML_DEV_VERSION
ENV NV_NVML_DEV_VERSION=12.1.105-1
                        
# 2023-11-10 13:25:42  0.00B 设置环境变量 NV_CUDA_CUDART_DEV_VERSION
ENV NV_CUDA_CUDART_DEV_VERSION=12.1.105-1
                        
# 2023-11-10 13:25:42  0.00B 设置环境变量 NV_CUDA_LIB_VERSION
ENV NV_CUDA_LIB_VERSION=12.1.1-1
                        
# 2023-11-10 13:14:24  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
                        
# 2023-11-10 13:14:24  0.00B 设置环境变量 NVIDIA_PRODUCT_NAME
ENV NVIDIA_PRODUCT_NAME=CUDA
                        
# 2023-11-10 13:14:24  2.53KB 复制新文件或目录到容器中
COPY nvidia_entrypoint.sh /opt/nvidia/ # buildkit
                        
# 2023-11-10 13:14:24  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 13:14:24  259.50KB 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 13:14:23  2.01GB 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 13:14:23  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2023-11-10 13:14:23  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2023-11-10 13:14:23  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 13:14:23  0.00B 设置环境变量 NCCL_VERSION
ENV NCCL_VERSION=2.17.1-1
                        
# 2023-11-10 13:14:23  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_VERSION
ENV NV_LIBNCCL_PACKAGE_VERSION=2.17.1-1
                        
# 2023-11-10 13:14:23  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_NAME
ENV NV_LIBNCCL_PACKAGE_NAME=libnccl2
                        
# 2023-11-10 13:14:23  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE
ENV NV_LIBCUBLAS_PACKAGE=libcublas-12-1=12.1.3.1-1
                        
# 2023-11-10 13:14:23  0.00B 设置环境变量 NV_LIBCUBLAS_VERSION
ENV NV_LIBCUBLAS_VERSION=12.1.3.1-1
                        
# 2023-11-10 13:14:23  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE_NAME
ENV NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-1
                        
# 2023-11-10 13:14:23  0.00B 设置环境变量 NV_LIBCUSPARSE_VERSION
ENV NV_LIBCUSPARSE_VERSION=12.1.0.106-1
                        
# 2023-11-10 13:14:23  0.00B 设置环境变量 NV_LIBNPP_PACKAGE
ENV NV_LIBNPP_PACKAGE=libnpp-12-1=12.1.0.40-1
                        
# 2023-11-10 13:14:23  0.00B 设置环境变量 NV_LIBNPP_VERSION
ENV NV_LIBNPP_VERSION=12.1.0.40-1
                        
# 2023-11-10 13:14:23  0.00B 设置环境变量 NV_NVTX_VERSION
ENV NV_NVTX_VERSION=12.1.105-1
                        
# 2023-11-10 13:14:23  0.00B 设置环境变量 NV_CUDA_LIB_VERSION
ENV NV_CUDA_LIB_VERSION=12.1.1-1
                        
# 2023-11-10 13:07:30  0.00B 设置环境变量 NVIDIA_DRIVER_CAPABILITIES
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
                        
# 2023-11-10 13:07:30  0.00B 设置环境变量 NVIDIA_VISIBLE_DEVICES
ENV NVIDIA_VISIBLE_DEVICES=all
                        
# 2023-11-10 13:07:30  17.29KB 复制新文件或目录到容器中
COPY NGC-DL-CONTAINER-LICENSE / # buildkit
                        
# 2023-11-10 13:07:29  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 13:07:29  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 13:07:29  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 13:07:29  149.60MB 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 13:07:08  0.00B 设置环境变量 CUDA_VERSION
ENV CUDA_VERSION=12.1.1
                        
# 2023-11-10 13:07:08  18.32MB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends     gnupg2 curl ca-certificates &&     curl -fsSL https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/${NVARCH}/3bf863cc.pub | apt-key add - &&     echo "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/${NVARCH} /" > /etc/apt/sources.list.d/cuda.list &&     apt-get purge --autoremove -y curl     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2023-11-10 13:07:08  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2023-11-10 13:07:08  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2023-11-10 13:07:08  0.00B 设置环境变量 NV_CUDA_COMPAT_PACKAGE
ENV NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-1
                        
# 2023-11-10 13:07:08  0.00B 设置环境变量 NV_CUDA_CUDART_VERSION
ENV NV_CUDA_CUDART_VERSION=12.1.105-1
                        
# 2023-11-10 13:07:08  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 13:07:08  0.00B 设置环境变量 NVARCH
ENV NVARCH=x86_64
                        
# 2023-10-03 18:45:52  0.00B 
/bin/sh -c #(nop)  CMD ["/bin/bash"]
                        
# 2023-10-03 18:45:51  72.79MB 
/bin/sh -c #(nop) ADD file:4809da414c2d478b4d991cbdaa2df457f2b3d07d0ff6cf673f09a66f90833e81 in / 
                        
# 2023-10-03 18:45:50  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.version=20.04
                        
# 2023-10-03 18:45:50  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.ref.name=ubuntu
                        
# 2023-10-03 18:45:50  0.00B 
/bin/sh -c #(nop)  ARG LAUNCHPAD_BUILD_ARCH
                        
# 2023-10-03 18:45:50  0.00B 
/bin/sh -c #(nop)  ARG RELEASE

镜像信息

{
    "Id": "sha256:a103a729631857f6ca7ec4a6aa6472b1ea65218765bc2c2d3cb33844329c59a2",
    "RepoTags": [
        "lmsysorg/sglang:latest",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/lmsysorg/sglang:latest"
    ],
    "RepoDigests": [
        "lmsysorg/sglang@sha256:703a5b23080fd92454dc2cc938005f3f52d08aea808715568769b90143602c21",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/lmsysorg/sglang@sha256:cab0668104932b67553ae73435226953cb7f10e85b2e5ce407a2de32541819fb"
    ],
    "Parent": "",
    "Comment": "buildkit.dockerfile.v0",
    "Created": "2024-10-25T18:11:36.728469677Z",
    "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=12.1.105-1",
            "NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-1",
            "CUDA_VERSION=12.1.1",
            "LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64",
            "NVIDIA_VISIBLE_DEVICES=all",
            "NVIDIA_DRIVER_CAPABILITIES=compute,utility",
            "NV_CUDA_LIB_VERSION=12.1.1-1",
            "NV_NVTX_VERSION=12.1.105-1",
            "NV_LIBNPP_VERSION=12.1.0.40-1",
            "NV_LIBNPP_PACKAGE=libnpp-12-1=12.1.0.40-1",
            "NV_LIBCUSPARSE_VERSION=12.1.0.106-1",
            "NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-1",
            "NV_LIBCUBLAS_VERSION=12.1.3.1-1",
            "NV_LIBCUBLAS_PACKAGE=libcublas-12-1=12.1.3.1-1",
            "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",
            "NV_CUDA_CUDART_DEV_VERSION=12.1.105-1",
            "NV_NVML_DEV_VERSION=12.1.105-1",
            "NV_LIBCUSPARSE_DEV_VERSION=12.1.0.106-1",
            "NV_LIBNPP_DEV_VERSION=12.1.0.40-1",
            "NV_LIBNPP_DEV_PACKAGE=libnpp-dev-12-1=12.1.0.40-1",
            "NV_LIBCUBLAS_DEV_VERSION=12.1.3.1-1",
            "NV_LIBCUBLAS_DEV_PACKAGE_NAME=libcublas-dev-12-1",
            "NV_LIBCUBLAS_DEV_PACKAGE=libcublas-dev-12-1=12.1.3.1-1",
            "NV_CUDA_NSIGHT_COMPUTE_VERSION=12.1.1-1",
            "NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-12-1=12.1.1-1",
            "NV_NVPROF_VERSION=12.1.105-1",
            "NV_NVPROF_DEV_PACKAGE=cuda-nvprof-12-1=12.1.105-1",
            "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=interactive"
        ],
        "Cmd": null,
        "Image": "",
        "Volumes": null,
        "WorkingDir": "/sgl-workspace",
        "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": "20.04"
        }
    },
    "Architecture": "amd64",
    "Os": "linux",
    "Size": 15952034552,
    "GraphDriver": {
        "Data": {
            "LowerDir": "/var/lib/docker/overlay2/8a1cf6f700d5e4e0591f42b6221b2c6660fefefd8b982be1a57564d58eedcce9/diff:/var/lib/docker/overlay2/fad169fa1ca1e12f11c8dd6e31f88e42b06999fb781e50480735fa2ca00993fb/diff:/var/lib/docker/overlay2/f2d790fc9b153abb04c50053f45ee51477665bc503af6be3f2ef55c8ef9d585b/diff:/var/lib/docker/overlay2/52dc34ec7c99e4f97be9fed9118080f8081130ed36fe61426a13661d99f39a0d/diff:/var/lib/docker/overlay2/2e043bbb71ae943864caaebff5e7b72c95e717559f2b54a46ef17e4e8e0b7281/diff:/var/lib/docker/overlay2/9f47ae689f60382ba8ae9bce3ce7990eedb53a20d51e37e6f7f6f9f03f91ff67/diff:/var/lib/docker/overlay2/3cd716618510824b062f97275d39d8c27612ca5562402fa901c9dc11539c68ba/diff:/var/lib/docker/overlay2/0c00a86ea1571366551efdda34d703a1f6ce372848b7188038d764748556ce7c/diff:/var/lib/docker/overlay2/8817184477cd4e057cf7d24a93725640a4e773a37e236a03a585cf0466d65b7c/diff:/var/lib/docker/overlay2/ad0a3312ad23f4e75ee123227cbaf05caa916150120bb9923eabfe36cf8e6639/diff:/var/lib/docker/overlay2/c515a8cc3c305507cfc9e79f58cb8368b9d941c22e92e64e567fcb2ae388f183/diff:/var/lib/docker/overlay2/2770558d6311665f80421733f45dc677f82cb23dc4a01334a89095449a1a443b/diff:/var/lib/docker/overlay2/627abd53a0fc4ef39d01207190fcc5b6f89a60c3c70a5751581956987cf54387/diff:/var/lib/docker/overlay2/ff1b39c26abb6bcf1a3bee03f550d1b8b534a48c0baead7dbfa4f29f40e3d046/diff:/var/lib/docker/overlay2/50982a33834878119291489f84ee2c7373c8499d4984e2faeafeedeb4a775372/diff:/var/lib/docker/overlay2/5408abd3ec726f4d055e10fddd8f488a8839c8a355fe1fb064cdc9fee660e07b/diff",
            "MergedDir": "/var/lib/docker/overlay2/1f65814e327ec433ce186c731781e9220ffad1a3e2d0d7675f6d9699f7028b50/merged",
            "UpperDir": "/var/lib/docker/overlay2/1f65814e327ec433ce186c731781e9220ffad1a3e2d0d7675f6d9699f7028b50/diff",
            "WorkDir": "/var/lib/docker/overlay2/1f65814e327ec433ce186c731781e9220ffad1a3e2d0d7675f6d9699f7028b50/work"
        },
        "Name": "overlay2"
    },
    "RootFS": {
        "Type": "layers",
        "Layers": [
            "sha256:6c3e7df31590f02f10cb71fc4eb27653e9b428df2e6e5421a455b062bd2e39f9",
            "sha256:5c0359201b8f5316a9c120cc074c134e6294e6351b6ba4384a843006f6716dd0",
            "sha256:f620bf47e83df6cb9d61bf1728402f88549bca976b3047f9cb69d03be03dc21b",
            "sha256:8d78458ccbe218dba1de0b340767e15e4693d7041f6407b69b82caed09c08e0b",
            "sha256:9dbd6d766fae94f829384e71cf3ff5fedfea9f448d4069d0ce87f3d544d19ecc",
            "sha256:379cd604fb89fd203f52b15d2f09fb14f70fc08cbe9655154a4f478ab72c5d93",
            "sha256:82adc44e81b3913c7215be048da7cae287149aba6fdcaf08065662a15d8b4e85",
            "sha256:cca411d699bf4af0a4bc8f047be6f79365f026d1458f74be6a9b2d80de2514de",
            "sha256:226146661e721e03f1d7fc62bbc58adf2e8185f06c3b794624b6f5efefc28b9c",
            "sha256:0e5e6a7b15e48919ddbaf00ab643e058050d95a02f4e2f0fc84b8a1a0f56e552",
            "sha256:ad6bf06f23c6a368ade44418b3fa62a77964c45a9df1a0533434ec5ea1670a65",
            "sha256:5a585d13dc1fb66787f87d5bedd1e468ec76c5a858222f491938eca3bd30a15d",
            "sha256:559dd10a629c99f2be39e45f7fa00c93bdcf0a537f00a2cef27d8afb1f27e847",
            "sha256:9bb1628dc8959682bb85660f24ddda46208597c424242f7a46d9daf682d1175e",
            "sha256:0673b2e11d8921bda4daf802d4a447f252ccfe8a731b2cfeda8f7382abd36ff0",
            "sha256:cfe81495caff576d0fddf6efb8f1cad3412af199103d3f19966fa25aa8fbaf48",
            "sha256:92bc5e72509ac4dfe197550ee4fa25c2fd8077f079587acc8567654b6b85ceef"
        ]
    },
    "Metadata": {
        "LastTagTime": "2024-10-29T01:06:53.499181044+08:00"
    }
}

更多版本

docker.io/lmsysorg/sglang:v0.2.0-cu124

linux/amd64 docker.io16.10GB2024-07-26 19:20

637

docker.io/lmsysorg/sglang:v0.3.0-cu121

linux/amd64 docker.io15.88GB2024-09-12 00:53

206

docker.io/lmsysorg/sglang:v0.3.0-cu124

linux/amd64 docker.io16.12GB2024-09-13 01:38

155

docker.io/lmsysorg/sglang:latest

linux/amd64 docker.io15.95GB2024-10-29 01:12