ghcr.io/ggerganov/llama.cpp:server-cuda-b4563 - 镜像下载

ghcr.io/ggerganov/llama.cpp:server-cuda-b4563

linux/amd64 ghcr.io

这里是镜像ghcr.io/ggerganov/llama.cpp 的描述信息：

LLaMA 是一个由 Google 的研究人员开发的预训练语言模型，旨在通过生成高质量、相关的内容来改善人机对话和文本理解。该模型以其高效的计算性能、广泛的知识覆盖范围以及简单易用的界面而闻名。使用 LLaMA 可以实现各种应用，如智能客服、内容创作、自然语言处理等。

805

浏览次数

2.68GB

镜像大小

国内镜像

swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda-b4563

源镜像

ghcr.io/ggerganov/llama.cpp:server-cuda-b4563

镜像ID

sha256:78c129adf471687c9ed1fd9f24aff7f324d263266e602e8f52f9c30123842986

镜像 TAG

server-cuda-b4563

镜像大小

2.68GB

平台架构

linux/amd64

镜像源

ghcr.io

CMD

启动入口

/app/llama-server

工作目录

/app

OS/平台

linux/amd64

镜像创建

2025-01-27T04:53:22.541527017Z

同步时间

2025-02-10 16:54

浏览量

805 次

贡献者

⚙️ 环境变量 22

Key	Value
`PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin`	`0`
`NVARCH=x86_64`	`1`
NVIDIA_REQUIRE_CUDA=cuda>=12.6 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	`2`
`NV_CUDA_CUDART_VERSION=12.6.37-1`	`3`
`CUDA_VERSION=12.6.0`	`4`
`LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64`	`5`
`NVIDIA_VISIBLE_DEVICES=all`	`6`
`NVIDIA_DRIVER_CAPABILITIES=compute,utility`	`7`
`NV_CUDA_LIB_VERSION=12.6.0-1`	`8`
`NV_NVTX_VERSION=12.6.37-1`	`9`
`NV_LIBNPP_VERSION=12.3.1.23-1`	`10`
`NV_LIBNPP_PACKAGE=libnpp-12-6=12.3.1.23-1`	`11`
`NV_LIBCUSPARSE_VERSION=12.5.2.23-1`	`12`
`NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-6`	`13`
`NV_LIBCUBLAS_VERSION=12.6.0.22-1`	`14`
`NV_LIBCUBLAS_PACKAGE=libcublas-12-6=12.6.0.22-1`	`15`
`NV_LIBNCCL_PACKAGE_NAME=libnccl2`	`16`
`NV_LIBNCCL_PACKAGE_VERSION=2.22.3-1`	`17`
`NCCL_VERSION=2.22.3-1`	`18`
`NV_LIBNCCL_PACKAGE=libnccl2=2.22.3-1+cuda12.6`	`19`
`NVIDIA_PRODUCT_NAME=CUDA`	`20`
`LLAMA_ARG_HOST=0.0.0.0`	`21`

🏷️ 镜像标签 3

Key	Value
`NVIDIA CORPORATION <cudatools@nvidia.com>`	`maintainer`
`ubuntu`	`org.opencontainers.image.ref.name`
`22.04`	`org.opencontainers.image.version`

🛡️ 镜像安全扫描

ubuntu 22.04 Trivy 2025-02-10 16:54 查看完整报告

低危 LOW

中危 MEDIUM

高危 HIGH

严重 CRITICAL

受影响目标 (1)

ghcr.io/ggerganov/llama.cpp:server-cuda-b4563 (ubuntu 22.04) ubuntu

Chatgpt|Claude一站式支持平台提供先进的AI镜像服务，助你在国内优雅的使用Chatgpt和Claude等AI服务

无权限下载？点我修复生成 Docker Run 命令生成 Kubernetes YAML

Docker拉取命令

docker pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda-b4563
docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda-b4563  ghcr.io/ggerganov/llama.cpp:server-cuda-b4563

Containerd拉取命令

ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda-b4563
ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda-b4563  ghcr.io/ggerganov/llama.cpp:server-cuda-b4563

Shell快速替换命令

sed -i 's#ghcr.io/ggerganov/llama.cpp:server-cuda-b4563#swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda-b4563#' 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/ggerganov/llama.cpp:server-cuda-b4563 && docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda-b4563  ghcr.io/ggerganov/llama.cpp:server-cuda-b4563'

Ansible快速分发-Containerd

#ansible k8s -m shell -a 'ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda-b4563 && ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda-b4563  ghcr.io/ggerganov/llama.cpp:server-cuda-b4563'

镜像构建历史


# 2025-01-27 12:53:22  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/app/llama-server"]
                        
# 2025-01-27 12:53:22  0.00B 指定检查容器健康状态的命令
HEALTHCHECK &{["CMD" "curl" "-f" "http://localhost:8080/health"] "0s" "0s" "0s" "0s" '\x00'}
                        
# 2025-01-27 12:53:22  0.00B 设置工作目录为/app
WORKDIR /app
                        
# 2025-01-27 12:53:22  3.70MB 复制新文件或目录到容器中
COPY /app/full/llama-server /app # buildkit
                        
# 2025-01-27 12:53:22  0.00B 设置环境变量 LLAMA_ARG_HOST
ENV LLAMA_ARG_HOST=0.0.0.0
                        
# 2025-01-27 12:46:04  366.11MB 复制新文件或目录到容器中
COPY /app/lib/ /app # buildkit
                        
# 2025-01-27 12:46:03  3.83MB 执行命令并创建新的镜像层
RUN /bin/sh -c apt-get update     && apt-get install -y libgomp1 curl    && apt autoremove -y     && apt clean -y     && rm -rf /tmp/* /var/tmp/*     && find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete     && find /var/cache -type f -delete # buildkit
                        
# 2024-08-10 01:43:33  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
                        
# 2024-08-10 01:43:33  0.00B 设置环境变量 NVIDIA_PRODUCT_NAME
ENV NVIDIA_PRODUCT_NAME=CUDA
                        
# 2024-08-10 01:43:33  2.53KB 复制新文件或目录到容器中
COPY nvidia_entrypoint.sh /opt/nvidia/ # buildkit
                        
# 2024-08-10 01:43:33  3.06KB 复制新文件或目录到容器中
COPY entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit
                        
# 2024-08-10 01:43:33  262.99KB 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
                        
# 2024-08-10 01:43:32  2.05GB 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-12-6=${NV_CUDA_LIB_VERSION}     ${NV_LIBNPP_PACKAGE}     cuda-nvtx-12-6=${NV_NVTX_VERSION}     libcusparse-12-6=${NV_LIBCUSPARSE_VERSION}     ${NV_LIBCUBLAS_PACKAGE}     ${NV_LIBNCCL_PACKAGE}     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2024-08-10 01:43:32  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2024-08-10 01:43:32  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2024-08-10 01:43:32  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE
ENV NV_LIBNCCL_PACKAGE=libnccl2=2.22.3-1+cuda12.6
                        
# 2024-08-10 01:43:32  0.00B 设置环境变量 NCCL_VERSION
ENV NCCL_VERSION=2.22.3-1
                        
# 2024-08-10 01:43:32  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_VERSION
ENV NV_LIBNCCL_PACKAGE_VERSION=2.22.3-1
                        
# 2024-08-10 01:43:32  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_NAME
ENV NV_LIBNCCL_PACKAGE_NAME=libnccl2
                        
# 2024-08-10 01:43:32  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE
ENV NV_LIBCUBLAS_PACKAGE=libcublas-12-6=12.6.0.22-1
                        
# 2024-08-10 01:43:32  0.00B 设置环境变量 NV_LIBCUBLAS_VERSION
ENV NV_LIBCUBLAS_VERSION=12.6.0.22-1
                        
# 2024-08-10 01:43:32  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE_NAME
ENV NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-6
                        
# 2024-08-10 01:43:32  0.00B 设置环境变量 NV_LIBCUSPARSE_VERSION
ENV NV_LIBCUSPARSE_VERSION=12.5.2.23-1
                        
# 2024-08-10 01:43:32  0.00B 设置环境变量 NV_LIBNPP_PACKAGE
ENV NV_LIBNPP_PACKAGE=libnpp-12-6=12.3.1.23-1
                        
# 2024-08-10 01:43:32  0.00B 设置环境变量 NV_LIBNPP_VERSION
ENV NV_LIBNPP_VERSION=12.3.1.23-1
                        
# 2024-08-10 01:43:32  0.00B 设置环境变量 NV_NVTX_VERSION
ENV NV_NVTX_VERSION=12.6.37-1
                        
# 2024-08-10 01:43:32  0.00B 设置环境变量 NV_CUDA_LIB_VERSION
ENV NV_CUDA_LIB_VERSION=12.6.0-1
                        
# 2024-08-10 01:38:07  0.00B 设置环境变量 NVIDIA_DRIVER_CAPABILITIES
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
                        
# 2024-08-10 01:38:07  0.00B 设置环境变量 NVIDIA_VISIBLE_DEVICES
ENV NVIDIA_VISIBLE_DEVICES=all
                        
# 2024-08-10 01:38:07  17.29KB 复制新文件或目录到容器中
COPY NGC-DL-CONTAINER-LICENSE / # buildkit
                        
# 2024-08-10 01:38:07  0.00B 设置环境变量 LD_LIBRARY_PATH
ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64
                        
# 2024-08-10 01:38:07  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
                        
# 2024-08-10 01:38:07  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
                        
# 2024-08-10 01:38:07  161.58MB 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-12-6=${NV_CUDA_CUDART_VERSION}     cuda-compat-12-6     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2024-08-10 01:37:56  0.00B 设置环境变量 CUDA_VERSION
ENV CUDA_VERSION=12.6.0
                        
# 2024-08-10 01:37:56  10.57MB 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_1.1-1_all.deb &&     dpkg -i cuda-keyring_1.1-1_all.deb &&     apt-get purge --autoremove -y curl     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2024-08-10 01:37:56  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2024-08-10 01:37:56  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2024-08-10 01:37:56  0.00B 设置环境变量 NV_CUDA_CUDART_VERSION
ENV NV_CUDA_CUDART_VERSION=12.6.37-1
                        
# 2024-08-10 01:37:56  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
ENV NVIDIA_REQUIRE_CUDA=cuda>=12.6 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
                        
# 2024-08-10 01:37:56  0.00B 设置环境变量 NVARCH
ENV NVARCH=x86_64
                        
# 2024-06-28 04:10:12  0.00B 
/bin/sh -c #(nop)  CMD ["/bin/bash"]
                        
# 2024-06-28 04:10:12  77.86MB 
/bin/sh -c #(nop) ADD file:d5da92199726e42da09a6f75a778befb607fe3f79e4afaf7ef5188329b26b386 in / 
                        
# 2024-06-28 04:10:10  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.version=22.04
                        
# 2024-06-28 04:10:10  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.ref.name=ubuntu
                        
# 2024-06-28 04:10:10  0.00B 
/bin/sh -c #(nop)  ARG LAUNCHPAD_BUILD_ARCH
                        
# 2024-06-28 04:10:10  0.00B 
/bin/sh -c #(nop)  ARG RELEASE

镜像信息

{
    "Id": "sha256:78c129adf471687c9ed1fd9f24aff7f324d263266e602e8f52f9c30123842986",
    "RepoTags": [
        "ghcr.io/ggerganov/llama.cpp:server-cuda-b4563",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda-b4563"
    ],
    "RepoDigests": [
        "ghcr.io/ggerganov/llama.cpp@sha256:a8b9e669c1ec80c1fda59d0aff5843387375b7d3cd1affee1fa72f7d4e9bc8fa",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp@sha256:bb9db9928260633c006ece31834720c225c84d2d5ced7eb1f228f2020d88d238"
    ],
    "Parent": "",
    "Comment": "buildkit.dockerfile.v0",
    "Created": "2025-01-27T04:53:22.541527017Z",
    "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=12.6 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",
            "NV_CUDA_CUDART_VERSION=12.6.37-1",
            "CUDA_VERSION=12.6.0",
            "LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64",
            "NVIDIA_VISIBLE_DEVICES=all",
            "NVIDIA_DRIVER_CAPABILITIES=compute,utility",
            "NV_CUDA_LIB_VERSION=12.6.0-1",
            "NV_NVTX_VERSION=12.6.37-1",
            "NV_LIBNPP_VERSION=12.3.1.23-1",
            "NV_LIBNPP_PACKAGE=libnpp-12-6=12.3.1.23-1",
            "NV_LIBCUSPARSE_VERSION=12.5.2.23-1",
            "NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-6",
            "NV_LIBCUBLAS_VERSION=12.6.0.22-1",
            "NV_LIBCUBLAS_PACKAGE=libcublas-12-6=12.6.0.22-1",
            "NV_LIBNCCL_PACKAGE_NAME=libnccl2",
            "NV_LIBNCCL_PACKAGE_VERSION=2.22.3-1",
            "NCCL_VERSION=2.22.3-1",
            "NV_LIBNCCL_PACKAGE=libnccl2=2.22.3-1+cuda12.6",
            "NVIDIA_PRODUCT_NAME=CUDA",
            "LLAMA_ARG_HOST=0.0.0.0"
        ],
        "Cmd": null,
        "Healthcheck": {
            "Test": [
                "CMD",
                "curl",
                "-f",
                "http://localhost:8080/health"
            ]
        },
        "Image": "",
        "Volumes": null,
        "WorkingDir": "/app",
        "Entrypoint": [
            "/app/llama-server"
        ],
        "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": 2677358383,
    "GraphDriver": {
        "Data": {
            "LowerDir": "/var/lib/docker/overlay2/907c30cf2ee339cf5329c323499393afceffb735d7759bb9b2f9b3d9038a5cf2/diff:/var/lib/docker/overlay2/7fc6c1e55a7fc21b893ed8c2416bf43f59f38112408d17429f67d2ceac52b85f/diff:/var/lib/docker/overlay2/a20df99da0eb229ea1a1ee3559afba5a32dea911cb8ead5fa1dc8ea39175e72f/diff:/var/lib/docker/overlay2/9f3fd5e696c96cf9521ad4297c8bbc0bf8ff171e4795bb5baa6713f36667d88b/diff:/var/lib/docker/overlay2/8e95a91c7611e1a73703c9b7baed02badd0290ac97810e037f8f408b55bae2b1/diff:/var/lib/docker/overlay2/b1496b35a09869f549ffbb2dbd291f6dc6db59f5f034c440971a587b7e77bfc4/diff:/var/lib/docker/overlay2/5e495ea3198b9d7d94da7954ff7281736c837b9227bae22611b151e94e27a5a9/diff:/var/lib/docker/overlay2/b059ac22ee77f453be33ffa6ca8e06d52d4ea973a1d9ded92b6c387104a5ac4b/diff:/var/lib/docker/overlay2/b7b5eedb2e9739aa1de5ae27556242b7971e07984e9f67f2e0a1114551150c4b/diff:/var/lib/docker/overlay2/10282ae269c49b13a7d1f0d22b66740ab6fc72530e24ec2bc869438b80ba90a2/diff:/var/lib/docker/overlay2/fce9300be3d1db0e43d535c901ab0a216e914563da9fbc7c81729b37f14630fe/diff:/var/lib/docker/overlay2/a87f4e197f50eba5d3c155f8f71198b5efc5a79a132e68b6fdd236bf36dd0a45/diff",
            "MergedDir": "/var/lib/docker/overlay2/d42d3e7f795ee8e13aa55a76ec7348a2aee8b52d1c46dd2d1f00c86249c1e036/merged",
            "UpperDir": "/var/lib/docker/overlay2/d42d3e7f795ee8e13aa55a76ec7348a2aee8b52d1c46dd2d1f00c86249c1e036/diff",
            "WorkDir": "/var/lib/docker/overlay2/d42d3e7f795ee8e13aa55a76ec7348a2aee8b52d1c46dd2d1f00c86249c1e036/work"
        },
        "Name": "overlay2"
    },
    "RootFS": {
        "Type": "layers",
        "Layers": [
            "sha256:931b7ff0cb6f494b27d31a4cbec3efe62ac54676add9c7469560302f1541ecaf",
            "sha256:1e9c40c384ef892c8b044b8deea344d77213ef86e5e2e10556b176e3b66cd7e3",
            "sha256:2591292aa496711009497eef309bd42371956b22e56756c512c18b326162f9c3",
            "sha256:cc51bf61b66d15057d4c73ba89e3c3ba387cdeaac86d594c98a042b55455ee17",
            "sha256:3b6bc3c2c74bad1746ed46ebdcf13c564d4efd61b1198ca172bfaebea05f8843",
            "sha256:eca6787b9f1f10205282688c75d49c132662217890128118be425b229f8815f0",
            "sha256:92caa6c8a151862616e064ad09df5a7388c6e6e50f78bb48bb10f6804b412d69",
            "sha256:12799c4e382b7cf61cda8157b8f3cb7306e6443eb0b34a5f60615a31039d260d",
            "sha256:8b3e2824dc15bac5d49e6ae466686963e32446313cefcd29ca000e7346169d64",
            "sha256:5496f228ed0614d9f36112b8a4cb2ee676dd289bf92dcc0d6a3aa0d62ffd8350",
            "sha256:5f72b09db51b9b79ed9d10055caf9a549820255d114c59c778b68a15940d0785",
            "sha256:2f3dc35e882ca9a0fb54a253b69d6ed2b53ddef0503a120ff2ab6c9f0fefd3fa",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef"
        ]
    },
    "Metadata": {
        "LastTagTime": "2025-02-10T16:53:53.188812374+08:00"
    }
}

更多版本

ghcr.io/ggerganov/llama.cpp:server-cuda

linux/amd64 ghcr.io2.73GB2024-09-12 11:55

3281

ghcr.io/ggerganov/llama.cpp:server-cuda--b1-7d1a378

linux/amd64 ghcr.io2.32GB2024-11-03 15:07