ghcr.io/llm-d/llm-d:v0.2.0 linux/amd64

ghcr.io/llm-d/llm-d:v0.2.0 - 国内下载镜像源浏览次数:18

该Docker镜像 ghcr.io/llm-d/llm-d 是LLM-D项目的镜像。LLM-D是一个大型语言模型项目，这个镜像包含了运行LLM-D所需的所有依赖项和代码。

源镜像	ghcr.io/llm-d/llm-d:v0.2.0
国内镜像	swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/llm-d/llm-d:v0.2.0
镜像ID	sha256:9c39422bd12d42d50b098b9cef2788dd48f18032740434f9e619e10b5d388244
镜像TAG	v0.2.0
大小	20.43GB
镜像源	ghcr.io
CMD
启动入口	python -m vllm.entrypoints.openai.api_server
工作目录	/home/vllm
OS/平台	linux/amd64
浏览量	18 次
贡献者
镜像创建	2025-07-25T19:31:43.341788039Z
同步时间	2025-08-19 05:06
更新时间	2025-08-19 13:09

环境变量

container=oci PKG_CMD=yum NVARCH=x86_64 NVIDIA_REQUIRE_CUDA=cuda>=12.8 brand=unknown,driver>=470,driver<471 brand=grid,driver>=470,driver<471 brand=tesla,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=vapps,driver>=470,driver<471 brand=vpc,driver>=470,driver<471 brand=vcs,driver>=470,driver<471 brand=vws,driver>=470,driver<471 brand=cloudgaming,driver>=470,driver<471 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 NV_CUDA_CUDART_VERSION=12.8.90-1 CUDA_VERSION=12.8.1 NVIDIA_VISIBLE_DEVICES=all NVIDIA_DRIVER_CAPABILITIES=compute,utility NV_CUDA_LIB_VERSION=12.8.1-1 NV_NVTX_VERSION=12.8.90-1 NV_LIBNPP_VERSION=12.3.3.100-1 NV_LIBNPP_PACKAGE=libnpp-12-8-12.3.3.100-1 NV_LIBCUBLAS_VERSION=12.8.4.1-1 NV_LIBNCCL_PACKAGE_NAME=libnccl NV_LIBNCCL_PACKAGE_VERSION=2.25.1-1 NV_LIBNCCL_VERSION=2.25.1 NCCL_VERSION=2.25.1 NV_LIBNCCL_PACKAGE=libnccl-2.25.1-1+cuda12.8 NVIDIA_PRODUCT_NAME=CUDA NV_NVPROF_VERSION=12.8.90-1 NV_NVPROF_DEV_PACKAGE=cuda-nvprof-12-8-12.8.90-1 NV_CUDA_CUDART_DEV_VERSION=12.8.90-1 NV_NVML_DEV_VERSION=12.8.90-1 NV_LIBCUBLAS_DEV_VERSION=12.8.4.1-1 NV_LIBNPP_DEV_VERSION=12.3.3.100-1 NV_LIBNPP_DEV_PACKAGE=libnpp-devel-12-8-12.3.3.100-1 NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-devel NV_LIBNCCL_DEV_PACKAGE_VERSION=2.25.1-1 NV_LIBNCCL_DEV_PACKAGE=libnccl-devel-2.25.1-1+cuda12.8 NV_CUDA_NSIGHT_COMPUTE_VERSION=12.8.1-1 NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-12-8-12.8.1-1 LIBRARY_PATH=/usr/local/cuda/lib64/stubs LANG=C.UTF-8 LC_ALL=C.UTF-8 PYTHON_VERSION=3.12 UV_TORCH_BACKEND=cu128 VIRTUAL_ENV=/opt/vllm NVSHMEM_DIR=/opt/nvshmem-3.3.9 LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/lib:/usr/local/lib64:/opt/nvshmem-3.3.9/lib:/usr/local/cuda/lib64 PATH=/opt/vllm/bin:/usr/local/nvidia/bin:/opt/nvshmem-3.3.9/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin CPATH=/opt/nvshmem-3.3.9/include: HOME=/home/vllm VLLM_USAGE_SOURCE=production-docker-image VLLM_WORKER_MULTIPROC_METHOD=fork OUTLINES_CACHE_DIR=/tmp/outlines NUMBA_CACHE_DIR=/tmp/numba TRITON_CACHE_DIR=/tmp/triton TRITON_LIBCUDA_PATH=/usr/lib64 TORCH_NCCL_HEARTBEAT_TIMEOUT_SEC=15 TORCH_NCCL_DUMP_ON_TIMEOUT=0 VLLM_SKIP_P2P_CHECK=1 VLLM_CACHE_ROOT=/tmp/vllm HF_HUB_DISABLE_XET=1

镜像标签

x86_64: architecture 2025-03-13T07:14:50Z: build-date ubi9-container: com.redhat.component https://www.redhat.com/en/about/red-hat-end-user-license-agreements#UBI: com.redhat.license_terms The Universal Base Image is designed and engineered to be the base layer for all of your containerized applications, middleware and utilities. This base image is freely redistributable, but Red Hat only supports Red Hat technologies through subscriptions for Red Hat products. This image is maintained by Red Hat and updated regularly.: description public: distribution-scope 1.40.1: io.buildah.version The Universal Base Image is designed and engineered to be the base layer for all of your containerized applications, middleware and utilities. This base image is freely redistributable, but Red Hat only supports Red Hat technologies through subscriptions for Red Hat products. This image is maintained by Red Hat and updated regularly.: io.k8s.description Red Hat Universal Base Image 9: io.k8s.display-name : io.openshift.expose-services base rhel9: io.openshift.tags NVIDIA CORPORATION <sw-cuda-installer@nvidia.com>: maintainer ubi9: name 1741850090: release Provides the latest release of Red Hat Universal Base Image 9.: summary https://www.redhat.com: url ecbd6d61fc4ddfbae467860a593ee69f34ec1120: vcs-ref git: vcs-type Red Hat, Inc.: vendor 9.5: version

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❤️

硅基流动注册送2000万 Tokens！

GPT人工智能60G学习资料❤️

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/ghcr.io/llm-d/llm-d:v0.2.0
docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/llm-d/llm-d:v0.2.0  ghcr.io/llm-d/llm-d:v0.2.0

Containerd拉取命令

ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/llm-d/llm-d:v0.2.0
ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/llm-d/llm-d:v0.2.0  ghcr.io/llm-d/llm-d:v0.2.0

Shell快速替换命令

sed -i 's#ghcr.io/llm-d/llm-d:v0.2.0#swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/llm-d/llm-d:v0.2.0#' 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/llm-d/llm-d:v0.2.0 && docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/llm-d/llm-d:v0.2.0  ghcr.io/llm-d/llm-d:v0.2.0'

Ansible快速分发-Containerd

#ansible k8s -m shell -a 'ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/llm-d/llm-d:v0.2.0 && ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/llm-d/llm-d:v0.2.0  ghcr.io/llm-d/llm-d:v0.2.0'

镜像构建历史


# 2025-07-26 03:31:43  0.00B 
/bin/sh -c #(nop) ENTRYPOINT ["python", "-m", "vllm.entrypoints.openai.api_server"]
                        
# 2025-07-26 03:31:42  0.00B 
/bin/sh -c #(nop) WORKDIR /home/vllm
                        
# 2025-07-26 03:31:41  0.00B 
/bin/sh -c #(nop) USER 2000
                        
# 2025-07-26 03:31:40  0.00B 
/bin/sh -c #(nop) ENV PATH="${VIRTUAL_ENV}/bin:/usr/local/nvidia/bin:${PATH}"     HOME=/home/vllm     VLLM_USAGE_SOURCE=production-docker-image     VLLM_WORKER_MULTIPROC_METHOD=fork     OUTLINES_CACHE_DIR=/tmp/outlines     NUMBA_CACHE_DIR=/tmp/numba     TRITON_CACHE_DIR=/tmp/triton     TRITON_LIBCUDA_PATH=/usr/lib64     TORCH_NCCL_HEARTBEAT_TIMEOUT_SEC=15     TORCH_NCCL_DUMP_ON_TIMEOUT=0     VLLM_SKIP_P2P_CHECK=1     VLLM_CACHE_ROOT=/tmp/vllm     HF_HUB_DISABLE_XET=1
                        
# 2025-07-26 03:31:38  586.63KB 
|6 CUDA_MAJOR=12 CUDA_MINOR=8 CUDA_PATCH=1 LMCACHE_COMMIT_SHA=c1563bc9c72ea0d71156a3d9a6cd643170828acf NVSHMEM_VERSION=3.3.9 VLLM_COMMIT_SHA=6d8d0a24c02bfd84d46b3016b865a44f048ae84b /bin/sh -c umask 002 &&     useradd --uid 2000 --gid 0 vllm &&     rm -rf /home/vllm &&     mkdir -p /home/vllm &&     chown vllm:root /home/vllm &&     chmod g+rwx /home/vllm
                        
# 2025-07-26 03:31:11  36.40MB 
|6 CUDA_MAJOR=12 CUDA_MINOR=8 CUDA_PATCH=1 LMCACHE_COMMIT_SHA=c1563bc9c72ea0d71156a3d9a6cd643170828acf NVSHMEM_VERSION=3.3.9 VLLM_COMMIT_SHA=6d8d0a24c02bfd84d46b3016b865a44f048ae84b /bin/sh -c dnf remove -y git && dnf autoremove -y && dnf clean all
                        
# 2025-07-26 03:25:45  9.90GB 
|6 CUDA_MAJOR=12 CUDA_MINOR=8 CUDA_PATCH=1 LMCACHE_COMMIT_SHA=c1563bc9c72ea0d71156a3d9a6cd643170828acf NVSHMEM_VERSION=3.3.9 VLLM_COMMIT_SHA=6d8d0a24c02bfd84d46b3016b865a44f048ae84b /bin/sh -c --mount=type=cache,target=/var/cache/git     source /opt/vllm/bin/activate &&         uv pip install cuda-python huggingface_hub[hf_xet] &&         uv pip install /tmp/wheels/*.whl &&         rm -rf /tmp/wheels &&         uv pip install --pre -U vllm==0.10.0 --torch-backend=cu128
                        
# 2025-07-26 03:19:50  0.00B 
/bin/sh -c #(nop) ARG CUDA_MAJOR CUDA_MINOR CUDA_PATCH LMCACHE_COMMIT_SHA NVSHMEM_VERSION VLLM_COMMIT_SHA
                        
# 2025-07-26 03:19:49  0.00B 
/bin/sh -c #(nop) ARG CUDA_MAJOR CUDA_MINOR CUDA_PATCH LMCACHE_COMMIT_SHA NVSHMEM_VERSION
                        
# 2025-07-26 03:19:47  129.69MB 
/bin/sh -c #(nop) COPY multi:7bca86cbbbccc59ad54ac4579dffdb94486221e29ce9786a3856b94b812174a8 in /tmp/wheels/ 
                        
# 2025-07-25 08:17:50  57.62MB 
|4 CUDA_MAJOR=12 CUDA_MINOR=8 CUDA_PATCH=1 NVSHMEM_VERSION=3.3.9 /bin/sh -c python${PYTHON_VERSION} -m venv /opt/vllm &&     ${VIRTUAL_ENV}/bin/pip install --no-cache -U pip wheel uv
                        
# 2025-07-25 08:17:05  34.54KB 
|4 CUDA_MAJOR=12 CUDA_MINOR=8 CUDA_PATCH=1 NVSHMEM_VERSION=3.3.9 /bin/sh -c echo "/usr/local/lib" > /etc/ld.so.conf.d/local.conf &&     echo "/usr/local/lib64" >> /etc/ld.so.conf.d/local.conf &&     echo "/opt/nvshmem-${NVSHMEM_VERSION}/lib" >> /etc/ld.so.conf.d/local.conf &&     echo "/opt/vllm/lib64/python3.12/site-packages/.nixl.mesonpy.libs/plugins" >> /etc/ld.so.conf.d/local.conf &&     ldconfig
                        
# 2025-07-25 08:16:53  257.02MB 
/bin/sh -c #(nop) COPY dir:dfcd12f09aad8928794da1e60ce655d3e1310c77ca53b655d62dd47dc2161f5d in /opt/nvshmem-${NVSHMEM_VERSION}/ 
                        
# 2025-07-25 08:16:41  48.88KB 
/bin/sh -c #(nop) COPY multi:0b662b37e10b2be291d79aaa73088b037487fb4ffa83a76be05dbfd97a8a769f in /usr/local/include/ 
                        
# 2025-07-25 08:16:31  1.81MB 
/bin/sh -c #(nop) COPY dir:03f398f80d160e0eb11e82fb375d18ce262ec3962ea613782bf0b1d8b08b191c in /usr/local/lib64/plugins/ 
                        
# 2025-07-25 08:16:21  22.89KB 
/bin/sh -c #(nop) COPY file:aa33435a6324042f96db4ab1507fcd5e90b8888df549bb69a47b765b2d78d4ae in /usr/local/lib64/ 
                        
# 2025-07-25 08:16:12  36.36KB 
/bin/sh -c #(nop) COPY file:24b1241199e952117911c05eddb89f098eb4f408ff893c19f7ca99ba4a5e31a9 in /usr/local/lib64/ 
                        
# 2025-07-25 08:16:02  1.22MB 
/bin/sh -c #(nop) COPY multi:16efffadf54b35aa563db66275f8e012c8066227262cc68790c51cd8ce2376b5 in /usr/local/lib64/ 
                        
# 2025-07-25 08:15:53  94.03KB 
/bin/sh -c #(nop) COPY multi:4922ed63862e53a5c643772dfa4650e47f8e0d49a88b4b27871c05f822b189ae in /usr/local/lib/ 
                        
# 2025-07-25 08:15:43  31.34KB 
/bin/sh -c #(nop) COPY file:02ac29fd3797b7305df1dadf07cfb25292eaf3571af136c1aa0c17dabe6ee630 in /usr/lib64/ 
                        
# 2025-07-25 08:15:34  436.11KB 
/bin/sh -c #(nop) COPY file:d405286b2a7c7ab592fedf25e3c45f4a6ddcb37c0296384b12e8af4fb717eb6a in /usr/local/lib64/ 
                        
# 2025-07-25 08:15:24  1.09MB 
/bin/sh -c #(nop) COPY dir:193a9f104167b14160441e0bec054ced70433bac8f0f11e17324da1ca8d91d0f in /usr/local/lib/ucx/ 
                        
# 2025-07-25 08:15:15  325.30KB 
/bin/sh -c #(nop) COPY multi:77c33391c2020aa4c87196673a2745136cdcbffdd2097e7163f8c3bc91df7b8a in /usr/local/lib/ 
                        
# 2025-07-25 08:15:05  746.88KB 
/bin/sh -c #(nop) COPY multi:6cefddb3fdddfc5f4dcaa5a326c12f1f81bf0715ccba52495bd8d89ccff83315 in /usr/local/lib/ 
                        
# 2025-07-25 08:14:55  1.30MB 
/bin/sh -c #(nop) COPY multi:f439116e00f33f3ec9c453bfb748611eb43eba5dc31afffb90ae873578002b70 in /usr/local/lib/ 
                        
# 2025-07-25 08:14:46  2.85MB 
/bin/sh -c #(nop) COPY multi:4e2fc224db8303f0260073e4596a18829a7b20458dce5f06ee1e5d6aa954e537 in /usr/local/lib/ 
                        
# 2025-07-25 08:14:13  189.15MB 
|4 CUDA_MAJOR=12 CUDA_MINOR=8 CUDA_PATCH=1 NVSHMEM_VERSION=3.3.9 /bin/sh -c dnf install -y --allowerasing         python${PYTHON_VERSION} python${PYTHON_VERSION}-pip python${PYTHON_VERSION}-devel         rdma-core-devel         numactl-libs         pciutils         procps-ng         git         curl         gcc && dnf clean all
                        
# 2025-07-25 08:12:29  798.94MB 
|4 CUDA_MAJOR=12 CUDA_MINOR=8 CUDA_PATCH=1 NVSHMEM_VERSION=3.3.9 /bin/sh -c dnf update -y && dnf clean all
                        
# 2025-07-25 08:07:17  0.00B 
/bin/sh -c #(nop) ENV LANG=C.UTF-8     LC_ALL=C.UTF-8     PYTHON_VERSION=${PYTHON_VERSION:-3.12}     UV_TORCH_BACKEND=${UV_TORCH_BACKEND:-cu${CUDA_MAJOR}${CUDA_MINOR}}     VIRTUAL_ENV=/opt/vllm     NVSHMEM_DIR="/opt/nvshmem-${NVSHMEM_VERSION}"     LD_LIBRARY_PATH="/usr/local/cuda/lib64:/usr/local/lib:/usr/local/lib64:/opt/nvshmem-${NVSHMEM_VERSION}/lib:${LD_LIBRARY_PATH}"     PATH="/opt/nvshmem-${NVSHMEM_VERSION}/bin:${PATH}"     CPATH="/opt/nvshmem-${NVSHMEM_VERSION}/include:${CPATH}"
                        
# 2025-07-25 08:07:17  0.00B 
/bin/sh -c #(nop) ARG CUDA_MAJOR CUDA_MINOR CUDA_PATCH NVSHMEM_VERSION
                        
# 2025-07-25 07:24:47  0.00B 
/bin/sh -c #(nop) ARG CUDA_MAJOR CUDA_MINOR CUDA_PATCH
                        
# 2025-07-25 07:24:46  0.00B 
/bin/sh -c #(nop) ARG CUDA_MAJOR CUDA_MINOR CUDA_PATCH
                        
# 2025-07-25 07:24:45  0.00B 
/bin/sh -c #(nop) ARG CUDA_MAJOR CUDA_MINOR
                        
# 2025-07-25 07:24:45  0.00B 
/bin/sh -c #(nop) ARG CUDA_MAJOR
                        
# 2025-03-13 22:23:18  0.00B 设置环境变量 LIBRARY_PATH
ENV LIBRARY_PATH=/usr/local/cuda/lib64/stubs
                        
# 2025-03-13 22:23:18  5.48GB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c ${PKG_CMD} install -y     make     findutils     cuda-command-line-tools-12-8-${NV_CUDA_LIB_VERSION}     cuda-libraries-devel-12-8-${NV_CUDA_LIB_VERSION}     cuda-minimal-build-12-8-${NV_CUDA_LIB_VERSION}     cuda-cudart-devel-12-8-${NV_CUDA_CUDART_DEV_VERSION}     ${NV_NVPROF_DEV_PACKAGE}     cuda-nvml-devel-12-8-${NV_NVML_DEV_VERSION}     libcublas-devel-12-8-${NV_LIBCUBLAS_DEV_VERSION}     ${NV_LIBNPP_DEV_PACKAGE}     ${NV_LIBNCCL_DEV_PACKAGE}     ${NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE}     && ${PKG_CMD} clean all     && rm -rf /var/cache/yum/* # buildkit
                        
# 2025-03-13 22:23:18  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <sw-cuda-installer@nvidia.com>
                        
# 2025-03-13 22:23:18  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2025-03-13 22:23:18  0.00B 设置环境变量 NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE
ENV NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-12-8-12.8.1-1
                        
# 2025-03-13 22:23:18  0.00B 设置环境变量 NV_CUDA_NSIGHT_COMPUTE_VERSION
ENV NV_CUDA_NSIGHT_COMPUTE_VERSION=12.8.1-1
                        
# 2025-03-13 22:23:18  0.00B 设置环境变量 NV_LIBNCCL_DEV_PACKAGE
ENV NV_LIBNCCL_DEV_PACKAGE=libnccl-devel-2.25.1-1+cuda12.8
                        
# 2025-03-13 22:23:18  0.00B 设置环境变量 NCCL_VERSION
ENV NCCL_VERSION=2.25.1
                        
# 2025-03-13 22:23:18  0.00B 设置环境变量 NV_LIBNCCL_DEV_PACKAGE_VERSION
ENV NV_LIBNCCL_DEV_PACKAGE_VERSION=2.25.1-1
                        
# 2025-03-13 22:23:18  0.00B 设置环境变量 NV_LIBNCCL_DEV_PACKAGE_NAME
ENV NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-devel
                        
# 2025-03-13 22:23:18  0.00B 设置环境变量 NV_LIBNPP_DEV_PACKAGE
ENV NV_LIBNPP_DEV_PACKAGE=libnpp-devel-12-8-12.3.3.100-1
                        
# 2025-03-13 22:23:18  0.00B 设置环境变量 NV_LIBNPP_DEV_VERSION
ENV NV_LIBNPP_DEV_VERSION=12.3.3.100-1
                        
# 2025-03-13 22:23:18  0.00B 设置环境变量 NV_LIBCUBLAS_DEV_VERSION
ENV NV_LIBCUBLAS_DEV_VERSION=12.8.4.1-1
                        
# 2025-03-13 22:23:18  0.00B 设置环境变量 NV_NVML_DEV_VERSION
ENV NV_NVML_DEV_VERSION=12.8.90-1
                        
# 2025-03-13 22:23:18  0.00B 设置环境变量 NV_CUDA_CUDART_DEV_VERSION
ENV NV_CUDA_CUDART_DEV_VERSION=12.8.90-1
                        
# 2025-03-13 22:23:18  0.00B 设置环境变量 NV_NVPROF_DEV_PACKAGE
ENV NV_NVPROF_DEV_PACKAGE=cuda-nvprof-12-8-12.8.90-1
                        
# 2025-03-13 22:23:18  0.00B 设置环境变量 NV_NVPROF_VERSION
ENV NV_NVPROF_VERSION=12.8.90-1
                        
# 2025-03-13 22:23:18  0.00B 设置环境变量 NV_CUDA_LIB_VERSION
ENV NV_CUDA_LIB_VERSION=12.8.1-1
                        
# 2025-03-13 22:23:18  0.00B 设置环境变量 PKG_CMD
ENV PKG_CMD=yum
                        
# 2025-03-13 22:09:36  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
                        
# 2025-03-13 22:09:36  0.00B 设置环境变量 NVIDIA_PRODUCT_NAME
ENV NVIDIA_PRODUCT_NAME=CUDA
                        
# 2025-03-13 22:09:36  2.53KB 复制新文件或目录到容器中
COPY nvidia_entrypoint.sh /opt/nvidia/ # buildkit
                        
# 2025-03-13 22:09:36  3.06KB 复制新文件或目录到容器中
COPY entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit
                        
# 2025-03-13 22:09:36  3.13GB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c ${PKG_CMD} install -y     cuda-libraries-12-8-${NV_CUDA_LIB_VERSION}     cuda-nvtx-12-8-${NV_NVTX_VERSION}     ${NV_LIBNPP_PACKAGE}     libcublas-12-8-${NV_LIBCUBLAS_VERSION}     ${NV_LIBNCCL_PACKAGE}     && ${PKG_CMD} clean all     && rm -rf /var/cache/yum/* # buildkit
                        
# 2025-03-13 22:09:36  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <sw-cuda-installer@nvidia.com>
                        
# 2025-03-13 22:09:36  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2025-03-13 22:09:36  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE
ENV NV_LIBNCCL_PACKAGE=libnccl-2.25.1-1+cuda12.8
                        
# 2025-03-13 22:09:36  0.00B 设置环境变量 NCCL_VERSION
ENV NCCL_VERSION=2.25.1
                        
# 2025-03-13 22:09:36  0.00B 设置环境变量 NV_LIBNCCL_VERSION
ENV NV_LIBNCCL_VERSION=2.25.1
                        
# 2025-03-13 22:09:36  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_VERSION
ENV NV_LIBNCCL_PACKAGE_VERSION=2.25.1-1
                        
# 2025-03-13 22:09:36  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_NAME
ENV NV_LIBNCCL_PACKAGE_NAME=libnccl
                        
# 2025-03-13 22:09:36  0.00B 设置环境变量 NV_LIBCUBLAS_VERSION
ENV NV_LIBCUBLAS_VERSION=12.8.4.1-1
                        
# 2025-03-13 22:09:36  0.00B 设置环境变量 NV_LIBNPP_PACKAGE
ENV NV_LIBNPP_PACKAGE=libnpp-12-8-12.3.3.100-1
                        
# 2025-03-13 22:09:36  0.00B 设置环境变量 NV_LIBNPP_VERSION
ENV NV_LIBNPP_VERSION=12.3.3.100-1
                        
# 2025-03-13 22:09:36  0.00B 设置环境变量 NV_NVTX_VERSION
ENV NV_NVTX_VERSION=12.8.90-1
                        
# 2025-03-13 22:09:36  0.00B 设置环境变量 NV_CUDA_LIB_VERSION
ENV NV_CUDA_LIB_VERSION=12.8.1-1
                        
# 2025-03-13 22:09:36  0.00B 设置环境变量 PKG_CMD
ENV PKG_CMD=yum
                        
# 2025-03-13 22:07:04  0.00B 设置环境变量 NVIDIA_DRIVER_CAPABILITIES
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
                        
# 2025-03-13 22:07:04  0.00B 设置环境变量 NVIDIA_VISIBLE_DEVICES
ENV NVIDIA_VISIBLE_DEVICES=all
                        
# 2025-03-13 22:07:04  17.29KB 复制新文件或目录到容器中
COPY NGC-DL-CONTAINER-LICENSE / # buildkit
                        
# 2025-03-13 22:07:04  0.00B 设置环境变量 LD_LIBRARY_PATH
ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64
                        
# 2025-03-13 22:07:04  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
                        
# 2025-03-13 22:07:04  22.00B 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c echo "/usr/local/cuda/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit
                        
# 2025-03-13 22:07:04  219.57MB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c ${PKG_CMD} upgrade -y && ${PKG_CMD} install -y     cuda-cudart-12-8-${NV_CUDA_CUDART_VERSION}     cuda-compat-12-8     && ${PKG_CMD} clean all     && rm -rf /var/cache/yum/* # buildkit
                        
# 2025-03-13 22:06:55  0.00B 设置环境变量 CUDA_VERSION
ENV CUDA_VERSION=12.8.1
                        
# 2025-03-13 22:06:55  1.61KB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c NVIDIA_GPGKEY_SUM=d0664fbbdb8c32356d45de36c5984617217b2d0bef41b93ccecd326ba3b80c87 &&     curl -fsSL https://developer.download.nvidia.com/compute/cuda/repos/rhel9/${NVARCH}/D42D0685.pub | sed '/^Version/d' > /etc/pki/rpm-gpg/RPM-GPG-KEY-NVIDIA &&     echo "$NVIDIA_GPGKEY_SUM  /etc/pki/rpm-gpg/RPM-GPG-KEY-NVIDIA" | sha256sum -c --strict - # buildkit
                        
# 2025-03-13 22:06:54  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <sw-cuda-installer@nvidia.com>
                        
# 2025-03-13 22:06:54  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2025-03-13 22:06:54  165.00B 复制新文件或目录到容器中
COPY cuda.repo-x86_64 /etc/yum.repos.d/cuda.repo # buildkit
                        
# 2025-03-13 22:06:54  0.00B 设置环境变量 NV_CUDA_CUDART_VERSION
ENV NV_CUDA_CUDART_VERSION=12.8.90-1
                        
# 2025-03-13 22:06:54  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>=12.8 brand=unknown,driver>=470,driver<471 brand=grid,driver>=470,driver<471 brand=tesla,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=vapps,driver>=470,driver<471 brand=vpc,driver>=470,driver<471 brand=vcs,driver>=470,driver<471 brand=vws,driver>=470,driver<471 brand=cloudgaming,driver>=470,driver<471 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
                        
# 2025-03-13 22:06:54  0.00B 设置环境变量 NVARCH
ENV NVARCH=x86_64
                        
# 2025-03-13 22:06:54  0.00B 设置环境变量 PKG_CMD
ENV PKG_CMD=yum
                        
# 2025-03-13 15:23:30  939.00B 
/bin/sh
                        
# 2025-03-13 15:23:13  225.29MB 
/bin/sh -c #(nop) LABEL "build-date"="2025-03-13T07:22:14" "architecture"="x86_64" "vcs-type"="git" "vcs-ref"="ecbd6d61fc4ddfbae467860a593ee69f34ec1120" "build-date"="2025-03-13T07:14:50Z" "release"="1741850090"
                        
# 2025-03-13 15:23:12  0.00B 
/bin/sh -c #(nop) CMD ["/bin/bash"]
                        
# 2025-03-13 15:23:12  0.00B 
/bin/sh -c #(nop) COPY file:b37d593713ee21ad52a4cd1424dc019a24f7966f85df0ac4b86d234302695328 in /etc/yum.repos.d/. 
                        
# 2025-03-13 15:23:12  0.00B 
/bin/sh -c #(nop) COPY dir:b6f09d3412721254b7ed767053ffd4fe349fe17da114a4689a4b06285bc6f7ad in / 
                        
# 2025-03-13 15:23:10  0.00B 
/bin/sh -c #(nop) ENV container oci
                        
# 2025-03-13 15:23:10  0.00B 
/bin/sh -c #(nop) LABEL io.openshift.tags="base rhel9"
                        
# 2025-03-13 15:23:10  0.00B 
/bin/sh -c #(nop) LABEL io.openshift.expose-services=""
                        
# 2025-03-13 15:23:10  0.00B 
/bin/sh -c #(nop) LABEL io.k8s.display-name="Red Hat Universal Base Image 9"
                        
# 2025-03-13 15:23:10  0.00B 
/bin/sh -c #(nop) LABEL io.k8s.description="The Universal Base Image is designed and engineered to be the base layer for all of your containerized applications, middleware and utilities. This base image is freely redistributable, but Red Hat only supports Red Hat technologies through subscriptions for Red Hat products. This image is maintained by Red Hat and updated regularly."
                        
# 2025-03-13 15:23:10  0.00B 
/bin/sh -c #(nop) LABEL description="The Universal Base Image is designed and engineered to be the base layer for all of your containerized applications, middleware and utilities. This base image is freely redistributable, but Red Hat only supports Red Hat technologies through subscriptions for Red Hat products. This image is maintained by Red Hat and updated regularly."
                        
# 2025-03-13 15:23:10  0.00B 
/bin/sh -c #(nop) LABEL summary="Provides the latest release of Red Hat Universal Base Image 9."
                        
# 2025-03-13 15:23:10  0.00B 
/bin/sh -c #(nop) LABEL com.redhat.license_terms="https://www.redhat.com/en/about/red-hat-end-user-license-agreements#UBI"
                        
# 2025-03-13 15:23:10  0.00B 
/bin/sh -c #(nop) LABEL com.redhat.component="ubi9-container"       name="ubi9"       version="9.5"       distribution-scope="public"
                        
# 2025-03-13 15:23:10  0.00B 
/bin/sh -c #(nop) LABEL url="https://www.redhat.com"
                        
# 2025-03-13 15:23:10  0.00B 
/bin/sh -c #(nop) LABEL maintainer="Red Hat, Inc."       vendor="Red Hat, Inc."

镜像信息

{
    "Id": "sha256:9c39422bd12d42d50b098b9cef2788dd48f18032740434f9e619e10b5d388244",
    "RepoTags": [
        "ghcr.io/llm-d/llm-d:v0.2.0",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/llm-d/llm-d:v0.2.0"
    ],
    "RepoDigests": [
        "ghcr.io/llm-d/llm-d@sha256:3e7f387361a31fb669e42ddbf643b5292d9f2ed3cfc68d986fc6cecd78ab708e",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/llm-d/llm-d@sha256:5d5f7c87d5fae2ad90bef578d971af3916dc17008dde0595da8e0d0da3dd5b92"
    ],
    "Parent": "",
    "Comment": "",
    "Created": "2025-07-25T19:31:43.341788039Z",
    "Container": "",
    "ContainerConfig": null,
    "DockerVersion": "",
    "Author": "",
    "Config": {
        "Hostname": "",
        "Domainname": "",
        "User": "2000",
        "AttachStdin": false,
        "AttachStdout": false,
        "AttachStderr": false,
        "Tty": false,
        "OpenStdin": false,
        "StdinOnce": false,
        "Env": [
            "container=oci",
            "PKG_CMD=yum",
            "NVARCH=x86_64",
            "NVIDIA_REQUIRE_CUDA=cuda\u003e=12.8 brand=unknown,driver\u003e=470,driver\u003c471 brand=grid,driver\u003e=470,driver\u003c471 brand=tesla,driver\u003e=470,driver\u003c471 brand=nvidia,driver\u003e=470,driver\u003c471 brand=quadro,driver\u003e=470,driver\u003c471 brand=quadrortx,driver\u003e=470,driver\u003c471 brand=nvidiartx,driver\u003e=470,driver\u003c471 brand=vapps,driver\u003e=470,driver\u003c471 brand=vpc,driver\u003e=470,driver\u003c471 brand=vcs,driver\u003e=470,driver\u003c471 brand=vws,driver\u003e=470,driver\u003c471 brand=cloudgaming,driver\u003e=470,driver\u003c471 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",
            "NV_CUDA_CUDART_VERSION=12.8.90-1",
            "CUDA_VERSION=12.8.1",
            "NVIDIA_VISIBLE_DEVICES=all",
            "NVIDIA_DRIVER_CAPABILITIES=compute,utility",
            "NV_CUDA_LIB_VERSION=12.8.1-1",
            "NV_NVTX_VERSION=12.8.90-1",
            "NV_LIBNPP_VERSION=12.3.3.100-1",
            "NV_LIBNPP_PACKAGE=libnpp-12-8-12.3.3.100-1",
            "NV_LIBCUBLAS_VERSION=12.8.4.1-1",
            "NV_LIBNCCL_PACKAGE_NAME=libnccl",
            "NV_LIBNCCL_PACKAGE_VERSION=2.25.1-1",
            "NV_LIBNCCL_VERSION=2.25.1",
            "NCCL_VERSION=2.25.1",
            "NV_LIBNCCL_PACKAGE=libnccl-2.25.1-1+cuda12.8",
            "NVIDIA_PRODUCT_NAME=CUDA",
            "NV_NVPROF_VERSION=12.8.90-1",
            "NV_NVPROF_DEV_PACKAGE=cuda-nvprof-12-8-12.8.90-1",
            "NV_CUDA_CUDART_DEV_VERSION=12.8.90-1",
            "NV_NVML_DEV_VERSION=12.8.90-1",
            "NV_LIBCUBLAS_DEV_VERSION=12.8.4.1-1",
            "NV_LIBNPP_DEV_VERSION=12.3.3.100-1",
            "NV_LIBNPP_DEV_PACKAGE=libnpp-devel-12-8-12.3.3.100-1",
            "NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-devel",
            "NV_LIBNCCL_DEV_PACKAGE_VERSION=2.25.1-1",
            "NV_LIBNCCL_DEV_PACKAGE=libnccl-devel-2.25.1-1+cuda12.8",
            "NV_CUDA_NSIGHT_COMPUTE_VERSION=12.8.1-1",
            "NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-12-8-12.8.1-1",
            "LIBRARY_PATH=/usr/local/cuda/lib64/stubs",
            "LANG=C.UTF-8",
            "LC_ALL=C.UTF-8",
            "PYTHON_VERSION=3.12",
            "UV_TORCH_BACKEND=cu128",
            "VIRTUAL_ENV=/opt/vllm",
            "NVSHMEM_DIR=/opt/nvshmem-3.3.9",
            "LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/lib:/usr/local/lib64:/opt/nvshmem-3.3.9/lib:/usr/local/cuda/lib64",
            "PATH=/opt/vllm/bin:/usr/local/nvidia/bin:/opt/nvshmem-3.3.9/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",
            "CPATH=/opt/nvshmem-3.3.9/include:",
            "HOME=/home/vllm",
            "VLLM_USAGE_SOURCE=production-docker-image",
            "VLLM_WORKER_MULTIPROC_METHOD=fork",
            "OUTLINES_CACHE_DIR=/tmp/outlines",
            "NUMBA_CACHE_DIR=/tmp/numba",
            "TRITON_CACHE_DIR=/tmp/triton",
            "TRITON_LIBCUDA_PATH=/usr/lib64",
            "TORCH_NCCL_HEARTBEAT_TIMEOUT_SEC=15",
            "TORCH_NCCL_DUMP_ON_TIMEOUT=0",
            "VLLM_SKIP_P2P_CHECK=1",
            "VLLM_CACHE_ROOT=/tmp/vllm",
            "HF_HUB_DISABLE_XET=1"
        ],
        "Cmd": null,
        "Image": "",
        "Volumes": null,
        "WorkingDir": "/home/vllm",
        "Entrypoint": [
            "python",
            "-m",
            "vllm.entrypoints.openai.api_server"
        ],
        "OnBuild": null,
        "Labels": {
            "architecture": "x86_64",
            "build-date": "2025-03-13T07:14:50Z",
            "com.redhat.component": "ubi9-container",
            "com.redhat.license_terms": "https://www.redhat.com/en/about/red-hat-end-user-license-agreements#UBI",
            "description": "The Universal Base Image is designed and engineered to be the base layer for all of your containerized applications, middleware and utilities. This base image is freely redistributable, but Red Hat only supports Red Hat technologies through subscriptions for Red Hat products. This image is maintained by Red Hat and updated regularly.",
            "distribution-scope": "public",
            "io.buildah.version": "1.40.1",
            "io.k8s.description": "The Universal Base Image is designed and engineered to be the base layer for all of your containerized applications, middleware and utilities. This base image is freely redistributable, but Red Hat only supports Red Hat technologies through subscriptions for Red Hat products. This image is maintained by Red Hat and updated regularly.",
            "io.k8s.display-name": "Red Hat Universal Base Image 9",
            "io.openshift.expose-services": "",
            "io.openshift.tags": "base rhel9",
            "maintainer": "NVIDIA CORPORATION \u003csw-cuda-installer@nvidia.com\u003e",
            "name": "ubi9",
            "release": "1741850090",
            "summary": "Provides the latest release of Red Hat Universal Base Image 9.",
            "url": "https://www.redhat.com",
            "vcs-ref": "ecbd6d61fc4ddfbae467860a593ee69f34ec1120",
            "vcs-type": "git",
            "vendor": "Red Hat, Inc.",
            "version": "9.5"
        }
    },
    "Architecture": "amd64",
    "Os": "linux",
    "Size": 20434269963,
    "GraphDriver": {
        "Data": {
            "LowerDir": "/var/lib/docker/overlay2/f408c5a068f6dbbd4005ae2889b85614d61e125555c9ae7851c4e4697b73991b/diff:/var/lib/docker/overlay2/4ce8c7603f87814cbb600da926375ea00acbe39690be9d7f63c9ab642486d60e/diff:/var/lib/docker/overlay2/b1b2e33e1173c0a3f3a07412e68dd241142533cf82d830dfa8bfc4f4693b9f2b/diff:/var/lib/docker/overlay2/26f8752ac6a0cafec8d5ffb3a52a825704a441e5cc38cb46690b37eb61e756e2/diff:/var/lib/docker/overlay2/592c08c2a3aa08599ad6f9fb142e286afdf20e2b92c01ecebba3e51a06b9f44b/diff:/var/lib/docker/overlay2/4c24bc81027e52fdf47aa973dcacb44c160011661e2d69a977d618ac09178a18/diff:/var/lib/docker/overlay2/ee319a841a60ec29f3dec1b72747be927d9639a88711c1479a0e0b77d99a101a/diff:/var/lib/docker/overlay2/c4782a0d1b6336560d6d5510d308da37c6c337fe895853ec56680845caaa1c32/diff:/var/lib/docker/overlay2/bd56763e63f24960b87d94875c3a6da83e2e6d603d8e8e3b47feb34f943b53b7/diff:/var/lib/docker/overlay2/f162b415859135cb72887a87a251d1d5069979777c227af757a3704c9f85eec0/diff:/var/lib/docker/overlay2/4c99c7a2a44c57df986baecc77de179387ab8f16b7f116b681ad6152eb2c0227/diff:/var/lib/docker/overlay2/dcf73fff88c602a879031e8bd1d01257fd6f221249f2054446df998c932daeb8/diff:/var/lib/docker/overlay2/248944d692454365f188e05c4761f2ede891edce5f393e88e9285c91240d45d4/diff:/var/lib/docker/overlay2/8f4472bdbf398f4034ed5575666abd995da919dbd7f527d4d6467b86a2addd33/diff:/var/lib/docker/overlay2/7b62e98b0fba0f1e488df3db15952c06184523491ada4f19b33ce678bf394f03/diff:/var/lib/docker/overlay2/7e8c7237cd96635efa12998166e6d9a2b1aa4d5e9b6e987b190ebc529d1efa9e/diff:/var/lib/docker/overlay2/0abb24e21f3c4c8cafde423f07cd3034b0d24b063fc31981ecabe020930ae2cb/diff:/var/lib/docker/overlay2/cc20689110cc495aaca741caacfd5905ce6f01b39d0456ca5951164f10d945b5/diff:/var/lib/docker/overlay2/800c63ef483d82fd9653c520c8452edda28f66ae277080d5554709d4d4c709d9/diff:/var/lib/docker/overlay2/f0ac9da4c4c3fab8f3c4b57b43c09b8282d4317824f9dd3239fed563d78bfa68/diff:/var/lib/docker/overlay2/240a536e30e4daab07ebebb4af7ef56744acf97cb5619a666313aa1b67ded98e/diff:/var/lib/docker/overlay2/e36ebc47035b1a102fc11b18a6c5ed964ebc8e7fdd64c6f259f054b59e5da7f4/diff:/var/lib/docker/overlay2/4b64cd623f8251076788beefb385258021d6e4fed06d9bc9e8b6935da9d974b1/diff:/var/lib/docker/overlay2/f42766dd571cf800762850da251212d840c1c4170c47e48464eabddb615234b1/diff:/var/lib/docker/overlay2/1f8c85dbe917bd0c43c9b67c11653c8261eba35ad673e4bfdda340503e9705ed/diff:/var/lib/docker/overlay2/0cd5746146270f0531cea908c014463f5df4db4cee994da32e11fd1418045720/diff:/var/lib/docker/overlay2/a8017aefabc8d1975db32d5d7998bc2fe7565eecbf0086114c8e74b5928cdfc4/diff:/var/lib/docker/overlay2/44097d1839c7e72fb9b45917a092d72e74ddbbd8e42fd2466e8641b78049d8e1/diff:/var/lib/docker/overlay2/0386a2efca77197f154bb4ad497cbb269d6f3627cfdcde55dfda367e322365bb/diff:/var/lib/docker/overlay2/720b8c172b6a9c5feffd7a2e436791d62aca934e9ae4d98e0bd8ec998c2e7523/diff:/var/lib/docker/overlay2/c2680c9f8b311b76801181fc2f77872cf6f4af4eabd8a6bbe1a9b35cc56ff459/diff:/var/lib/docker/overlay2/16d5db5c2c037db9de128ee20e332f845ff89b8d475a0f0c54083de5c7c08a87/diff",
            "MergedDir": "/var/lib/docker/overlay2/b66cd9f0f778d4a5500212cc3cf15dc9c1058dfc0ddaa918b7ac904133f6ff4e/merged",
            "UpperDir": "/var/lib/docker/overlay2/b66cd9f0f778d4a5500212cc3cf15dc9c1058dfc0ddaa918b7ac904133f6ff4e/diff",
            "WorkDir": "/var/lib/docker/overlay2/b66cd9f0f778d4a5500212cc3cf15dc9c1058dfc0ddaa918b7ac904133f6ff4e/work"
        },
        "Name": "overlay2"
    },
    "RootFS": {
        "Type": "layers",
        "Layers": [
            "sha256:5ab036872dd7cc27d1d24fc1cccc763a8827061155e08ae1ccaf067ec5a755a2",
            "sha256:4bf5c942f2b4253bf750308d5aa91441d2900be420286156e8efd3d31f059877",
            "sha256:11628162f15cf0a2cd611ceb3e73ec25e29ff58c88cb11a792f954b007c6475f",
            "sha256:89cf9df74c3f6a97734444a92264432df474c3b4b45a73cdfa01511433caf622",
            "sha256:202af8e961f5a3a1fc81e162bfb433571fe18ed7c4eb1e6a06ee0b541e9627c7",
            "sha256:db0a66a66e392a5a3dbed6208bfa7a82b8c7cea5ad49fc3cc3c382111f861ef3",
            "sha256:94a99a25d7069405277be3f51f21564ad41708cf854662981625e7213bb46d4e",
            "sha256:8843905e055415fc2f4ba4ca144b05f00ab4282d5df1d534e04837bc5cac7444",
            "sha256:ce0915fe32c0bc1b53225587c1abef0287de4f89a7360eb56d0b8d61a9eb54bf",
            "sha256:18d7b57257ab35738b884eff54d8586ec5c8e62e62b3dd6340bf3a7f405c2592",
            "sha256:214c7898b8cfdbad8cca6cc909e266f5b50d593a20de587cfe56e25686c5bcbb",
            "sha256:8d95c265ab336b6382f17e830119e89da6a0326d52583cac1ab4c075bf581176",
            "sha256:9068544c4baee19c9728a79959dfcf488330deeca018705913961986aeeda722",
            "sha256:fb22e3652ef46c5e90b9afab3f55e9508398da796075acaafc233c585a3bec3b",
            "sha256:76debf2625105bfeee8c3330b57ab0df967675d492b76d0836233e86500787a5",
            "sha256:ccd0c5673fcd147d95d712c3e48c3f2d352b0cc01a77d83261abf5d543cc6c5c",
            "sha256:bd36fb73ef53b76be3c82ee6af2b3185dbb55b4bdd6e59348ab31a7b3b025c96",
            "sha256:e82249617c4911422c06867523aa39f86990ed4ecc28f874d4d1b703188dd54f",
            "sha256:fe63ed15164ae1531d4cc12018d2ddb49824b8fe8aacde7e842739fc84bb5019",
            "sha256:eb017e24418cb8e3b1df2f8e5aa9d1e4dbc1bd3185ad79a61e062af21c9f2f21",
            "sha256:d95c0bcfde03de0b543fd816916999a87cf86df2ab1a51358a43658622055afe",
            "sha256:c0f4697aaa62a600091a87453b6c0c60eeaf55e342a5ea072620ecc8d7124cf8",
            "sha256:761fafbff1dce8eb81d3390feae91670ee6796eb631fd3704b78744416f53438",
            "sha256:fb6d5f0bba250e4756fe84f4de3575d2af5e930f703d7416eeb156bc187c335f",
            "sha256:6e17b47d6c0a812b90f47c22adf51416eb12cd0a795dbebb9f4b5bf4f4803f46",
            "sha256:b7e651df00b80d5a22ceabc9854f18c8faa50a95e3a5ccea80921a4a70deb409",
            "sha256:650db694e7465bfaa2cf2a80c83e22081e977c8c146fb6c55f431d217a882d1f",
            "sha256:4c9cf47f127c8432c279f9fc2053c3ce39560e7120b835df3806e0a436a6ef40",
            "sha256:3f43898df035bbb46f5ca5ffdf81dd12f3fb0f9e63cf6ace520330909aa363e5",
            "sha256:c3433fcd1a48a6caea28cf4bbb5ab6c66b605fc973fdc0613ea0ccb847767d35",
            "sha256:4deebc3a59c5efe8d6348096e7e04ddd45a01c28750df791758be3601a73cd09",
            "sha256:77660715be5abf037fd28ec8f4175cf85d62b1c6feaf351f5464fee38ba31cee",
            "sha256:0d51c543dedb924f0545e9731e7a02f692b145f75381b77b69207a410e529acd"
        ]
    },
    "Metadata": {
        "LastTagTime": "2025-08-19T04:42:39.863234994+08:00"
    }
}

更多版本

ghcr.io/llm-d/llm-d:v0.2.0

linux/amd64 ghcr.io20.43GB2025-08-19 05:06