ghcr.io/ggml-org/llama.cpp:server-cuda-b6795 - 镜像下载

ghcr.io/ggml-org/llama.cpp:server-cuda-b6795

linux/amd64 ghcr.io 蓝聪贡献

这是一个包含llama.cpp项目的Docker容器镜像。llama.cpp是一个开源项目，允许在CPU和GPU上运行大型语言模型 (LLMs)，例如 LLaMA。

481

浏览次数

2.69GB

镜像大小

源镜像

ghcr.io/ggml-org/llama.cpp:server-cuda-b6795

国内镜像

swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp:server-cuda-b6795

镜像ID

sha256:abcb724a20dbde46fa7b948b3536dd9dec9f6e66cc15ad7def9f5ad9c66e3515

镜像 TAG

server-cuda-b6795

镜像大小

2.69GB

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

2025-10-19T05:03:50.449081763Z

同步时间

2025-10-30 17:31

浏览量

481 次

贡献者

蓝聪

⚙️ 环境变量 23

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>=12.4 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 brand=tesla,driver>=535,driver<536 brand=unknown,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=geforce,driver>=535,driver<536 brand=geforcertx,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=titan,driver>=535,driver<536 brand=titanrtx,driver>=535,driver<536	`2`
`NV_CUDA_CUDART_VERSION=12.4.99-1`	`3`
`NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-4`	`4`
`CUDA_VERSION=12.4.0`	`5`
`LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64`	`6`
`NVIDIA_VISIBLE_DEVICES=all`	`7`
`NVIDIA_DRIVER_CAPABILITIES=compute,utility`	`8`
`NV_CUDA_LIB_VERSION=12.4.0-1`	`9`
`NV_NVTX_VERSION=12.4.99-1`	`10`
`NV_LIBNPP_VERSION=12.2.5.2-1`	`11`
`NV_LIBNPP_PACKAGE=libnpp-12-4=12.2.5.2-1`	`12`
`NV_LIBCUSPARSE_VERSION=12.3.0.142-1`	`13`
`NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-4`	`14`
`NV_LIBCUBLAS_VERSION=12.4.2.65-1`	`15`
`NV_LIBCUBLAS_PACKAGE=libcublas-12-4=12.4.2.65-1`	`16`
`NV_LIBNCCL_PACKAGE_NAME=libnccl2`	`17`
`NV_LIBNCCL_PACKAGE_VERSION=2.20.5-1`	`18`
`NCCL_VERSION=2.20.5-1`	`19`
`NV_LIBNCCL_PACKAGE=libnccl2=2.20.5-1+cuda12.4`	`20`
`NVIDIA_PRODUCT_NAME=CUDA`	`21`
`LLAMA_ARG_HOST=0.0.0.0`	`22`

🏷️ 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`

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/ggml-org/llama.cpp:server-cuda-b6795
docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp:server-cuda-b6795  ghcr.io/ggml-org/llama.cpp:server-cuda-b6795

Containerd拉取命令

ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp:server-cuda-b6795
ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp:server-cuda-b6795  ghcr.io/ggml-org/llama.cpp:server-cuda-b6795

Shell快速替换命令

sed -i 's#ghcr.io/ggml-org/llama.cpp:server-cuda-b6795#swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp:server-cuda-b6795#' 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/ggml-org/llama.cpp:server-cuda-b6795 && docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp:server-cuda-b6795  ghcr.io/ggml-org/llama.cpp:server-cuda-b6795'

Ansible快速分发-Containerd

#ansible k8s -m shell -a 'ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp:server-cuda-b6795 && ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp:server-cuda-b6795  ghcr.io/ggml-org/llama.cpp:server-cuda-b6795'

镜像构建历史


# 2025-10-19 13:03:50  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/app/llama-server"]
                        
# 2025-10-19 13:03:50  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'}
                        
# 2025-10-19 13:03:50  0.00B 设置工作目录为/app
WORKDIR /app
                        
# 2025-10-19 13:03:50  4.33MB 复制新文件或目录到容器中
COPY /app/full/llama-server /app # buildkit
                        
# 2025-10-19 13:03:50  0.00B 设置环境变量 LLAMA_ARG_HOST
ENV LLAMA_ARG_HOST=0.0.0.0
                        
# 2025-10-19 12:58:38  401.48MB 复制新文件或目录到容器中
COPY /app/lib/ /app # buildkit
                        
# 2025-10-09 12:53:36  6.84MB 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
                        
# 2024-04-05 07:40:07  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
                        
# 2024-04-05 07:40:07  0.00B 设置环境变量 NVIDIA_PRODUCT_NAME
ENV NVIDIA_PRODUCT_NAME=CUDA
                        
# 2024-04-05 07:40:07  2.53KB 复制新文件或目录到容器中
COPY nvidia_entrypoint.sh /opt/nvidia/ # buildkit
                        
# 2024-04-05 07:40:07  3.06KB 复制新文件或目录到容器中
COPY entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit
                        
# 2024-04-05 07:40:07  262.98KB 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
                        
# 2024-04-05 07:40:07  2.03GB 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-12-4=${NV_CUDA_LIB_VERSION}     ${NV_LIBNPP_PACKAGE}     cuda-nvtx-12-4=${NV_NVTX_VERSION}     libcusparse-12-4=${NV_LIBCUSPARSE_VERSION}     ${NV_LIBCUBLAS_PACKAGE}     ${NV_LIBNCCL_PACKAGE}     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2024-04-05 07:40:07  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2024-04-05 07:40:07  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2024-04-05 07:40:07  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE
ENV NV_LIBNCCL_PACKAGE=libnccl2=2.20.5-1+cuda12.4
                        
# 2024-04-05 07:40:07  0.00B 设置环境变量 NCCL_VERSION
ENV NCCL_VERSION=2.20.5-1
                        
# 2024-04-05 07:40:07  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_VERSION
ENV NV_LIBNCCL_PACKAGE_VERSION=2.20.5-1
                        
# 2024-04-05 07:40:07  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_NAME
ENV NV_LIBNCCL_PACKAGE_NAME=libnccl2
                        
# 2024-04-05 07:40:07  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE
ENV NV_LIBCUBLAS_PACKAGE=libcublas-12-4=12.4.2.65-1
                        
# 2024-04-05 07:40:07  0.00B 设置环境变量 NV_LIBCUBLAS_VERSION
ENV NV_LIBCUBLAS_VERSION=12.4.2.65-1
                        
# 2024-04-05 07:40:07  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE_NAME
ENV NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-4
                        
# 2024-04-05 07:40:07  0.00B 设置环境变量 NV_LIBCUSPARSE_VERSION
ENV NV_LIBCUSPARSE_VERSION=12.3.0.142-1
                        
# 2024-04-05 07:40:07  0.00B 设置环境变量 NV_LIBNPP_PACKAGE
ENV NV_LIBNPP_PACKAGE=libnpp-12-4=12.2.5.2-1
                        
# 2024-04-05 07:40:07  0.00B 设置环境变量 NV_LIBNPP_VERSION
ENV NV_LIBNPP_VERSION=12.2.5.2-1
                        
# 2024-04-05 07:40:07  0.00B 设置环境变量 NV_NVTX_VERSION
ENV NV_NVTX_VERSION=12.4.99-1
                        
# 2024-04-05 07:40:07  0.00B 设置环境变量 NV_CUDA_LIB_VERSION
ENV NV_CUDA_LIB_VERSION=12.4.0-1
                        
# 2024-04-05 07:36:23  0.00B 设置环境变量 NVIDIA_DRIVER_CAPABILITIES
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
                        
# 2024-04-05 07:36:23  0.00B 设置环境变量 NVIDIA_VISIBLE_DEVICES
ENV NVIDIA_VISIBLE_DEVICES=all
                        
# 2024-04-05 07:36:23  17.29KB 复制新文件或目录到容器中
COPY NGC-DL-CONTAINER-LICENSE / # buildkit
                        
# 2024-04-05 07:36:23  0.00B 设置环境变量 LD_LIBRARY_PATH
ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64
                        
# 2024-04-05 07:36:23  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
                        
# 2024-04-05 07:36:23  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
                        
# 2024-04-05 07:36:23  155.92MB 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-12-4=${NV_CUDA_CUDART_VERSION}     ${NV_CUDA_COMPAT_PACKAGE}     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2024-04-05 07:36:11  0.00B 设置环境变量 CUDA_VERSION
ENV CUDA_VERSION=12.4.0
                        
# 2024-04-05 07:36:11  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_1.1-1_all.deb &&     dpkg -i cuda-keyring_1.1-1_all.deb &&     apt-get purge --autoremove -y curl     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2024-04-05 07:36:11  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2024-04-05 07:36:11  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2024-04-05 07:36:11  0.00B 设置环境变量 NV_CUDA_COMPAT_PACKAGE
ENV NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-4
                        
# 2024-04-05 07:36:11  0.00B 设置环境变量 NV_CUDA_CUDART_VERSION
ENV NV_CUDA_CUDART_VERSION=12.4.99-1
                        
# 2024-04-05 07:36:11  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
ENV NVIDIA_REQUIRE_CUDA=cuda>=12.4 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 brand=tesla,driver>=535,driver<536 brand=unknown,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=geforce,driver>=535,driver<536 brand=geforcertx,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=titan,driver>=535,driver<536 brand=titanrtx,driver>=535,driver<536
                        
# 2024-04-05 07:36:11  0.00B 设置环境变量 NVARCH
ENV NVARCH=x86_64
                        
# 2024-02-28 02:52:59  0.00B 
/bin/sh -c #(nop)  CMD ["/bin/bash"]
                        
# 2024-02-28 02:52:58  77.86MB 
/bin/sh -c #(nop) ADD file:21c2e8d95909bec6f4acdaf4aed55b44ee13603681f93b152e423e3e6a4a207b in / 
                        
# 2024-02-28 02:52:57  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.version=22.04
                        
# 2024-02-28 02:52:57  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.ref.name=ubuntu
                        
# 2024-02-28 02:52:57  0.00B 
/bin/sh -c #(nop)  ARG LAUNCHPAD_BUILD_ARCH
                        
# 2024-02-28 02:52:57  0.00B 
/bin/sh -c #(nop)  ARG RELEASE

镜像信息

{
    "Id": "sha256:abcb724a20dbde46fa7b948b3536dd9dec9f6e66cc15ad7def9f5ad9c66e3515",
    "RepoTags": [
        "ghcr.io/ggml-org/llama.cpp:server-cuda-b6795",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp:server-cuda-b6795"
    ],
    "RepoDigests": [
        "ghcr.io/ggml-org/llama.cpp@sha256:1930754897c347c708ca7ca5306fe154e71eb4268d97926e3315f27a0be487fb",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp@sha256:229c4a7d25f84e156d4749ff9a1426dfd3c50593d53370d76e95753eb747da99"
    ],
    "Parent": "",
    "Comment": "buildkit.dockerfile.v0",
    "Created": "2025-10-19T05:03:50.449081763Z",
    "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=12.4 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 brand=tesla,driver\u003e=535,driver\u003c536 brand=unknown,driver\u003e=535,driver\u003c536 brand=nvidia,driver\u003e=535,driver\u003c536 brand=nvidiartx,driver\u003e=535,driver\u003c536 brand=geforce,driver\u003e=535,driver\u003c536 brand=geforcertx,driver\u003e=535,driver\u003c536 brand=quadro,driver\u003e=535,driver\u003c536 brand=quadrortx,driver\u003e=535,driver\u003c536 brand=titan,driver\u003e=535,driver\u003c536 brand=titanrtx,driver\u003e=535,driver\u003c536",
            "NV_CUDA_CUDART_VERSION=12.4.99-1",
            "NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-4",
            "CUDA_VERSION=12.4.0",
            "LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64",
            "NVIDIA_VISIBLE_DEVICES=all",
            "NVIDIA_DRIVER_CAPABILITIES=compute,utility",
            "NV_CUDA_LIB_VERSION=12.4.0-1",
            "NV_NVTX_VERSION=12.4.99-1",
            "NV_LIBNPP_VERSION=12.2.5.2-1",
            "NV_LIBNPP_PACKAGE=libnpp-12-4=12.2.5.2-1",
            "NV_LIBCUSPARSE_VERSION=12.3.0.142-1",
            "NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-4",
            "NV_LIBCUBLAS_VERSION=12.4.2.65-1",
            "NV_LIBCUBLAS_PACKAGE=libcublas-12-4=12.4.2.65-1",
            "NV_LIBNCCL_PACKAGE_NAME=libnccl2",
            "NV_LIBNCCL_PACKAGE_VERSION=2.20.5-1",
            "NCCL_VERSION=2.20.5-1",
            "NV_LIBNCCL_PACKAGE=libnccl2=2.20.5-1+cuda12.4",
            "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": 2687832993,
    "GraphDriver": {
        "Data": {
            "LowerDir": "/var/lib/docker/overlay2/dd093edb82c0c80dbd03f86edfd7337219baad2eb502d4a73df4695c4be6e920/diff:/var/lib/docker/overlay2/8a86526da7e670f40a89fb5165fccd06ca2cc28e95c1f174c72b1fe7922399a2/diff:/var/lib/docker/overlay2/098409ad74af5c4d9555497b837f30ffadf2586c562610dc928812ff3aa144b5/diff:/var/lib/docker/overlay2/7f7a77f91efd89c5c046f51f2dc6dc4e6e94b5348923ff3ef71ebe6c474e3684/diff:/var/lib/docker/overlay2/959059feba7e00f07930dc3bb3a617ec6b068a0e20313fb891d3e24c3af8e6e7/diff:/var/lib/docker/overlay2/32e5bba4855a86f2572ed3c50bb9c76b6c7c04a0258355f770de30e4574fa9fa/diff:/var/lib/docker/overlay2/5c57424f6feedfc26b2fbba9c74ba1e0ecf1f817048e23c7ddb9df74fa9e0467/diff:/var/lib/docker/overlay2/461ca7fd6e39d861b2311f1e1433d554d7027501f7e27f291d664f440cb033f9/diff:/var/lib/docker/overlay2/627a195d1725748e224ba0c8d299e8d5a862ad6133982c6458052c6b839f5e4a/diff:/var/lib/docker/overlay2/297b258cb3a6b3147e80550dbc6c3bd5998554552abd02cb3248496dde840bb9/diff:/var/lib/docker/overlay2/53590fc1976ffdc026d2b1570b36addf9b59e2c2a5e053cb70ec6daa7177f59c/diff:/var/lib/docker/overlay2/36afb5f3b33b3915eca7fc7803ea8c9687feff5bf1dafe376b931e39494e6100/diff",
            "MergedDir": "/var/lib/docker/overlay2/c7ea7f5c0cfac80487ebaecc141fb5db5c75b839221c0a71787200930ed54dd2/merged",
            "UpperDir": "/var/lib/docker/overlay2/c7ea7f5c0cfac80487ebaecc141fb5db5c75b839221c0a71787200930ed54dd2/diff",
            "WorkDir": "/var/lib/docker/overlay2/c7ea7f5c0cfac80487ebaecc141fb5db5c75b839221c0a71787200930ed54dd2/work"
        },
        "Name": "overlay2"
    },
    "RootFS": {
        "Type": "layers",
        "Layers": [
            "sha256:5498e8c22f6996f25ef193ee58617d5b37e2a96decf22e72de13c3b34e147591",
            "sha256:4cd4079525948900a02a5734090afd1f3e046fc940dc882c55efcaee0a252dd0",
            "sha256:022bf74291b27404b223ba9ee16a7f3fb067253df9c65e23dfb3339800b28dfa",
            "sha256:eeb5315df33c9e700b3b8b8a3cdd1cf11e13c9dd44bfd946e340573478303349",
            "sha256:e942261d196e5e686398e2326c033119112f910191143b0497f13f78c377fa03",
            "sha256:421c5b38d6e056b3eee631bc65e1d2b24cee88b8f858457ec2ed1604b68cdbbb",
            "sha256:520e0f301880ab5ca0650a44703c86d75428b6ece6c3190b8ecd850e55372f60",
            "sha256:700fe921ad1f9a93e69a6a4faec3406f3f51e0f4ab4e9b732a9141261d941a4f",
            "sha256:b0dfaf1ca5c560107272f1e55220f7cef07d30d44ebac56c4cf8c45308538b91",
            "sha256:7679982bf4df27d4a1a1da6ae54f07c50cac56eaa40c0720de5b7025037c41d2",
            "sha256:59276ecc9259652265b416471c3570f7c8ea3bf98202981005d1e98ded759b81",
            "sha256:56ad0ba6af9e2233570445eb4c88b9d1fe2ad6cdab043c338d04297b782ecbc8",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef"
        ]
    },
    "Metadata": {
        "LastTagTime": "2025-10-30T17:30:43.279100848+08:00"
    }
}

更多版本

ghcr.io/ggml-org/llama.cpp:full

linux/amd64 ghcr.io1.96GB2025-03-17 14:48

1957

ghcr.io/ggml-org/llama.cpp:full-cuda

linux/amd64 ghcr.io5.05GB2025-03-18 10:58

3006

ghcr.io/ggml-org/llama.cpp:server

linux/amd64 ghcr.io96.62MB2025-05-02 00:26

4183

ghcr.io/ggml-org/llama.cpp:server-cuda

linux/amd64 ghcr.io2.57GB2025-06-14 16:26