ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728 linux/amd64

ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728 - 国内下载镜像源 浏览次数:11

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。

源镜像 ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728
国内镜像 swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728
镜像ID sha256:d8e2f34babfac555a269297c7e9683b17f261d6d6e3bfe7dceed9c3c1ef29a1d
镜像TAG server-cuda13-b7728
大小 2.53GB
镜像源 ghcr.io
CMD
启动入口 /app/llama-server
工作目录 /app
OS/平台 linux/amd64
浏览量 11 次
贡献者
镜像创建 2026-01-14T05:36:27.969945248Z
同步时间 2026-01-16 13:50
更新时间 2026-01-16 16:08
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>=13.1 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>=570,driver<571 brand=grid,driver>=570,driver<571 brand=tesla,driver>=570,driver<571 brand=nvidia,driver>=570,driver<571 brand=quadro,driver>=570,driver<571 brand=quadrortx,driver>=570,driver<571 brand=nvidiartx,driver>=570,driver<571 brand=vapps,driver>=570,driver<571 brand=vpc,driver>=570,driver<571 brand=vcs,driver>=570,driver<571 brand=vws,driver>=570,driver<571 brand=cloudgaming,driver>=570,driver<571 brand=unknown,driver>=575,driver<576 brand=grid,driver>=575,driver<576 brand=tesla,driver>=575,driver<576 brand=nvidia,driver>=575,driver<576 brand=quadro,driver>=575,driver<576 brand=quadrortx,driver>=575,driver<576 brand=nvidiartx,driver>=575,driver<576 brand=vapps,driver>=575,driver<576 brand=vpc,driver>=575,driver<576 brand=vcs,driver>=575,driver<576 brand=vws,driver>=575,driver<576 brand=cloudgaming,driver>=575,driver<576 brand=unknown,driver>=580,driver<581 brand=grid,driver>=580,driver<581 brand=tesla,driver>=580,driver<581 brand=nvidia,driver>=580,driver<581 brand=quadro,driver>=580,driver<581 brand=quadrortx,driver>=580,driver<581 brand=nvidiartx,driver>=580,driver<581 brand=vapps,driver>=580,driver<581 brand=vpc,driver>=580,driver<581 brand=vcs,driver>=580,driver<581 brand=vws,driver>=580,driver<581 brand=cloudgaming,driver>=580,driver<581 NV_CUDA_CUDART_VERSION=13.1.80-1 CUDA_VERSION=13.1.0 LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64 NVIDIA_VISIBLE_DEVICES=all NVIDIA_DRIVER_CAPABILITIES=compute,utility NV_CUDA_LIB_VERSION=13.1.0-1 NV_NVTX_VERSION=13.1.68-1 NV_LIBNPP_VERSION=13.0.2.21-1 NV_LIBNPP_PACKAGE=libnpp-13-1=13.0.2.21-1 NV_LIBCUSPARSE_VERSION=12.7.2.19-1 NV_LIBCUBLAS_PACKAGE_NAME=libcublas-13-1 NV_LIBCUBLAS_VERSION=13.2.0.9-1 NV_LIBCUBLAS_PACKAGE=libcublas-13-1=13.2.0.9-1 NVIDIA_PRODUCT_NAME=CUDA LLAMA_ARG_HOST=0.0.0.0
镜像标签
NVIDIA CORPORATION <cudatools@nvidia.com>: maintainer ubuntu: org.opencontainers.image.ref.name 24.04: org.opencontainers.image.version
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/ggml-org/llama.cpp:server-cuda13-b7728
docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728  ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728

Containerd拉取命令 

ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728
ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728  ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728

Shell快速替换命令 

sed -i 's#ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728#swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728#' 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-cuda13-b7728 && docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728  ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728'

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-cuda13-b7728 && ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728  ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728'

镜像构建历史 


# 2026-01-14 13:36:27  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/app/llama-server"]
                        
# 2026-01-14 13:36:27  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'}
                        
# 2026-01-14 13:36:27  0.00B 设置工作目录为/app
WORKDIR /app
                        
# 2026-01-14 13:36:27  6.98MB 复制新文件或目录到容器中
COPY /app/full/llama-server /app # buildkit
                        
# 2026-01-14 13:36:27  0.00B 设置环境变量 LLAMA_ARG_HOST
ENV LLAMA_ARG_HOST=0.0.0.0
                        
# 2026-01-14 13:33:25  148.91MB 复制新文件或目录到容器中
COPY /app/lib/ /app # buildkit
                        
# 2025-12-31 12:29:06  6.06MB 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
                        
# 2025-12-12 03:40:57  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
                        
# 2025-12-12 03:40:57  0.00B 设置环境变量 NVIDIA_PRODUCT_NAME
ENV NVIDIA_PRODUCT_NAME=CUDA
                        
# 2025-12-12 03:40:57  2.53KB 复制新文件或目录到容器中
COPY nvidia_entrypoint.sh /opt/nvidia/ # buildkit
                        
# 2025-12-12 03:40:57  3.06KB 复制新文件或目录到容器中
COPY entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit
                        
# 2025-12-12 03:40:57  238.69KB 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} # buildkit
                        
# 2025-12-12 03:40:56  1.85GB 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-13-1=${NV_CUDA_LIB_VERSION}     ${NV_LIBNPP_PACKAGE}     cuda-nvtx-13-1=${NV_NVTX_VERSION}     libcusparse-13-1=${NV_LIBCUSPARSE_VERSION}     ${NV_LIBCUBLAS_PACKAGE}     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2025-12-12 03:40:56  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2025-12-12 03:40:56  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2025-12-12 03:40:56  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE
ENV NV_LIBCUBLAS_PACKAGE=libcublas-13-1=13.2.0.9-1
                        
# 2025-12-12 03:40:56  0.00B 设置环境变量 NV_LIBCUBLAS_VERSION
ENV NV_LIBCUBLAS_VERSION=13.2.0.9-1
                        
# 2025-12-12 03:40:56  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE_NAME
ENV NV_LIBCUBLAS_PACKAGE_NAME=libcublas-13-1
                        
# 2025-12-12 03:40:56  0.00B 设置环境变量 NV_LIBCUSPARSE_VERSION
ENV NV_LIBCUSPARSE_VERSION=12.7.2.19-1
                        
# 2025-12-12 03:40:56  0.00B 设置环境变量 NV_LIBNPP_PACKAGE
ENV NV_LIBNPP_PACKAGE=libnpp-13-1=13.0.2.21-1
                        
# 2025-12-12 03:40:56  0.00B 设置环境变量 NV_LIBNPP_VERSION
ENV NV_LIBNPP_VERSION=13.0.2.21-1
                        
# 2025-12-12 03:40:56  0.00B 设置环境变量 NV_NVTX_VERSION
ENV NV_NVTX_VERSION=13.1.68-1
                        
# 2025-12-12 03:40:56  0.00B 设置环境变量 NV_CUDA_LIB_VERSION
ENV NV_CUDA_LIB_VERSION=13.1.0-1
                        
# 2025-12-12 03:26:32  0.00B 设置环境变量 NVIDIA_DRIVER_CAPABILITIES
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
                        
# 2025-12-12 03:26:32  0.00B 设置环境变量 NVIDIA_VISIBLE_DEVICES
ENV NVIDIA_VISIBLE_DEVICES=all
                        
# 2025-12-12 03:26:32  17.29KB 复制新文件或目录到容器中
COPY NGC-DL-CONTAINER-LICENSE / # buildkit
                        
# 2025-12-12 03:26:32  0.00B 设置环境变量 LD_LIBRARY_PATH
ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
                        
# 2025-12-12 03:26:32  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
                        
# 2025-12-12 03:26:32  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
                        
# 2025-12-12 03:26:32  430.61MB 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-13-1=${NV_CUDA_CUDART_VERSION}     cuda-compat-13-1     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2025-12-12 03:26:10  0.00B 设置环境变量 CUDA_VERSION
ENV CUDA_VERSION=13.1.0
                        
# 2025-12-12 03:26:10  10.26MB 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/ubuntu2404/${NVARCH}/3bf863cc.pub | apt-key add - &&     echo "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${NVARCH} /" > /etc/apt/sources.list.d/cuda.list &&     apt-get purge --autoremove -y curl     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2025-12-12 03:26:10  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2025-12-12 03:26:10  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2025-12-12 03:26:10  0.00B 设置环境变量 NV_CUDA_CUDART_VERSION
ENV NV_CUDA_CUDART_VERSION=13.1.80-1
                        
# 2025-12-12 03:26:10  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>=13.1 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>=570,driver<571 brand=grid,driver>=570,driver<571 brand=tesla,driver>=570,driver<571 brand=nvidia,driver>=570,driver<571 brand=quadro,driver>=570,driver<571 brand=quadrortx,driver>=570,driver<571 brand=nvidiartx,driver>=570,driver<571 brand=vapps,driver>=570,driver<571 brand=vpc,driver>=570,driver<571 brand=vcs,driver>=570,driver<571 brand=vws,driver>=570,driver<571 brand=cloudgaming,driver>=570,driver<571 brand=unknown,driver>=575,driver<576 brand=grid,driver>=575,driver<576 brand=tesla,driver>=575,driver<576 brand=nvidia,driver>=575,driver<576 brand=quadro,driver>=575,driver<576 brand=quadrortx,driver>=575,driver<576 brand=nvidiartx,driver>=575,driver<576 brand=vapps,driver>=575,driver<576 brand=vpc,driver>=575,driver<576 brand=vcs,driver>=575,driver<576 brand=vws,driver>=575,driver<576 brand=cloudgaming,driver>=575,driver<576 brand=unknown,driver>=580,driver<581 brand=grid,driver>=580,driver<581 brand=tesla,driver>=580,driver<581 brand=nvidia,driver>=580,driver<581 brand=quadro,driver>=580,driver<581 brand=quadrortx,driver>=580,driver<581 brand=nvidiartx,driver>=580,driver<581 brand=vapps,driver>=580,driver<581 brand=vpc,driver>=580,driver<581 brand=vcs,driver>=580,driver<581 brand=vws,driver>=580,driver<581 brand=cloudgaming,driver>=580,driver<581
                        
# 2025-12-12 03:26:10  0.00B 设置环境变量 NVARCH
ENV NVARCH=x86_64
                        
# 2025-10-17 03:23:03  0.00B 
/bin/sh -c #(nop)  CMD ["/bin/bash"]
                        
# 2025-10-17 03:23:03  78.12MB 
/bin/sh -c #(nop) ADD file:ddf1aa62235de6657123492b19d27d937c25668011b5ebf923a3f019200f8540 in / 
                        
# 2025-10-17 03:23:01  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.version=24.04
                        
# 2025-10-17 03:23:01  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.ref.name=ubuntu
                        
# 2025-10-17 03:23:01  0.00B 
/bin/sh -c #(nop)  ARG LAUNCHPAD_BUILD_ARCH
                        
# 2025-10-17 03:23:01  0.00B 
/bin/sh -c #(nop)  ARG RELEASE

镜像信息 

{
    "Id": "sha256:d8e2f34babfac555a269297c7e9683b17f261d6d6e3bfe7dceed9c3c1ef29a1d",
    "RepoTags": [
        "ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728"
    ],
    "RepoDigests": [
        "ghcr.io/ggml-org/llama.cpp@sha256:3578742d04d00c4e881aec99b905f55f00798668b5c80181d8d0e84e1a63e8b7",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggml-org/llama.cpp@sha256:213603ef47ee6e42b694c862482d9ce0e19204594ed0f4fe1aaefb05017cdc56"
    ],
    "Parent": "",
    "Comment": "buildkit.dockerfile.v0",
    "Created": "2026-01-14T05:36:27.969945248Z",
    "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=13.1 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=570,driver\u003c571 brand=grid,driver\u003e=570,driver\u003c571 brand=tesla,driver\u003e=570,driver\u003c571 brand=nvidia,driver\u003e=570,driver\u003c571 brand=quadro,driver\u003e=570,driver\u003c571 brand=quadrortx,driver\u003e=570,driver\u003c571 brand=nvidiartx,driver\u003e=570,driver\u003c571 brand=vapps,driver\u003e=570,driver\u003c571 brand=vpc,driver\u003e=570,driver\u003c571 brand=vcs,driver\u003e=570,driver\u003c571 brand=vws,driver\u003e=570,driver\u003c571 brand=cloudgaming,driver\u003e=570,driver\u003c571 brand=unknown,driver\u003e=575,driver\u003c576 brand=grid,driver\u003e=575,driver\u003c576 brand=tesla,driver\u003e=575,driver\u003c576 brand=nvidia,driver\u003e=575,driver\u003c576 brand=quadro,driver\u003e=575,driver\u003c576 brand=quadrortx,driver\u003e=575,driver\u003c576 brand=nvidiartx,driver\u003e=575,driver\u003c576 brand=vapps,driver\u003e=575,driver\u003c576 brand=vpc,driver\u003e=575,driver\u003c576 brand=vcs,driver\u003e=575,driver\u003c576 brand=vws,driver\u003e=575,driver\u003c576 brand=cloudgaming,driver\u003e=575,driver\u003c576 brand=unknown,driver\u003e=580,driver\u003c581 brand=grid,driver\u003e=580,driver\u003c581 brand=tesla,driver\u003e=580,driver\u003c581 brand=nvidia,driver\u003e=580,driver\u003c581 brand=quadro,driver\u003e=580,driver\u003c581 brand=quadrortx,driver\u003e=580,driver\u003c581 brand=nvidiartx,driver\u003e=580,driver\u003c581 brand=vapps,driver\u003e=580,driver\u003c581 brand=vpc,driver\u003e=580,driver\u003c581 brand=vcs,driver\u003e=580,driver\u003c581 brand=vws,driver\u003e=580,driver\u003c581 brand=cloudgaming,driver\u003e=580,driver\u003c581",
            "NV_CUDA_CUDART_VERSION=13.1.80-1",
            "CUDA_VERSION=13.1.0",
            "LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64",
            "NVIDIA_VISIBLE_DEVICES=all",
            "NVIDIA_DRIVER_CAPABILITIES=compute,utility",
            "NV_CUDA_LIB_VERSION=13.1.0-1",
            "NV_NVTX_VERSION=13.1.68-1",
            "NV_LIBNPP_VERSION=13.0.2.21-1",
            "NV_LIBNPP_PACKAGE=libnpp-13-1=13.0.2.21-1",
            "NV_LIBCUSPARSE_VERSION=12.7.2.19-1",
            "NV_LIBCUBLAS_PACKAGE_NAME=libcublas-13-1",
            "NV_LIBCUBLAS_VERSION=13.2.0.9-1",
            "NV_LIBCUBLAS_PACKAGE=libcublas-13-1=13.2.0.9-1",
            "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": "24.04"
        }
    },
    "Architecture": "amd64",
    "Os": "linux",
    "Size": 2526348203,
    "GraphDriver": {
        "Data": {
            "LowerDir": "/var/lib/docker/overlay2/1b57b644bf8bfad6a2c9c3c5b0d87290b5e7ea840bf48afabead5e6b65cd3be9/diff:/var/lib/docker/overlay2/6319cc7e0d85c2d9b867d51463ac92c4f06a75e03edd81ad7a300b2f1194281e/diff:/var/lib/docker/overlay2/5fe1973cef372dad091c1d141376cc61fb87f89a3b79702c7e7d284f61372445/diff:/var/lib/docker/overlay2/ec9feab620524217266388b8b116553bb9241160317d4303122e7c22d9d20c9f/diff:/var/lib/docker/overlay2/bdc9424d8f61830efb2a04ded5d8df07ade56b755ac6de737211cb6d1cea4911/diff:/var/lib/docker/overlay2/7f82053a4fec41d85a99bdeb27555774e621ca607bac44476f98100c77829cb3/diff:/var/lib/docker/overlay2/2745a8605e3b8c27133f62a6f7e9092d183136787335613ab926e517be977376/diff:/var/lib/docker/overlay2/837f10200e3d2a0008d72b9ec60bbb938f345ad996e23e0cf8a0279d7a554d39/diff:/var/lib/docker/overlay2/20c11971493ad907fa4ae57798a0ecdc367fa1a41c7c0d2a55d574e4fa4ebdb2/diff:/var/lib/docker/overlay2/df061d7ae8fb0f73e754af7754205d4b28fe6ab877da8bb1f46a59d5993e02ec/diff:/var/lib/docker/overlay2/7e77196b2a07c29c9c45290c4015de6739b69513ca09118a0c12c199ae03a2bc/diff:/var/lib/docker/overlay2/eb70712178461cb65c5a956187c966c31d60ac41eacf62af98ead2c9415d1d0a/diff",
            "MergedDir": "/var/lib/docker/overlay2/594dbb4a30d2b7c153d33899e8920e256f5a312a7afaef21ff7beb938005f354/merged",
            "UpperDir": "/var/lib/docker/overlay2/594dbb4a30d2b7c153d33899e8920e256f5a312a7afaef21ff7beb938005f354/diff",
            "WorkDir": "/var/lib/docker/overlay2/594dbb4a30d2b7c153d33899e8920e256f5a312a7afaef21ff7beb938005f354/work"
        },
        "Name": "overlay2"
    },
    "RootFS": {
        "Type": "layers",
        "Layers": [
            "sha256:e8bce0aabd687e9ee90e0bada33884f40b277196f72aac9934357472863a80ae",
            "sha256:36d90060b95409b7b193fde60fed0f87c6a7dec974898f6099e7213d6578adfa",
            "sha256:a6d89077dfddaea9358e85b65df742d0f6dd654bf89ba3bff784a9775a5f44df",
            "sha256:ed3b33bb139880e9c999206a60a13dcffdf52cbebc6560e8a1c5cd256e238d8f",
            "sha256:3391c095abd37954db07511960d6126fd97123a171e7fb567cfe9546883fb2ca",
            "sha256:0adb15f2fc6d717ecfed6a5fc9a17a599080a01407b01fe178e431c2af1c785f",
            "sha256:5baae8eebdaf1b432774660b8ee656b18d588110be07f6a9ee84891cff316e74",
            "sha256:6bdba62a484e7e708595f5e8cd984342f2fe310f1466f0d76059386551cf2368",
            "sha256:f35e9394347628083ddefaaeee44dbc2d21bbd3fc721502f1b0f185f8fc11a2a",
            "sha256:504610e0b7722bbc7c28cabd195dbd0ef92ed55834bd995b54ae96b34e86458d",
            "sha256:7aeac2270d2128706e0e5195893bd2bc3242d35cd8975b8eccf490d9116746e4",
            "sha256:7008c2d4d3b2cf858e9972f38f37fbe29f86602601af8a46ac54365d3fcd04ef",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef"
        ]
    },
    "Metadata": {
        "LastTagTime": "2026-01-16T13:50:13.144745481+08:00"
    }
}

更多版本

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

linux/amd64 ghcr.io1.96GB2025-03-17 14:48
1105

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

linux/amd64 ghcr.io5.05GB2025-03-18 10:58
1247

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

linux/amd64 ghcr.io96.62MB2025-05-02 00:26
1381

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

linux/amd64 ghcr.io2.57GB2025-06-14 16:26
1571

ghcr.io/ggml-org/llama.cpp:server-cuda-b6006

linux/amd64 ghcr.io2.58GB2025-07-28 15:06
474

ghcr.io/ggml-org/llama.cpp:server-musa-b6189

linux/amd64 ghcr.io4.44GB2025-08-18 19:58
244

ghcr.io/ggml-org/llama.cpp:server-musa-b6375

linux/amd64 ghcr.io4.45GB2025-09-04 16:53
240

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

linux/amd64 ghcr.io480.55MB2025-09-04 17:34
318

ghcr.io/ggml-org/llama.cpp:server-cuda-b6485

linux/amd64 ghcr.io2.63GB2025-09-16 16:27
335

ghcr.io/ggml-org/llama.cpp:server-musa-b6571

linux/amd64 ghcr.io4.45GB2025-09-28 14:58
138

ghcr.io/ggml-org/llama.cpp:server-cuda-b6725

linux/amd64 ghcr.io2.64GB2025-10-10 16:46
230

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

linux/amd64 docker.io5.01GB2025-10-13 17:40
162

docker.io/ghcr.io/ggml-org/llama.cpp:full-cuda-b6746

linux/amd64 docker.io5.01GB2025-10-13 17:42
206

ghcr.io/ggml-org/llama.cpp:full-cuda-b6746

linux/amd64 ghcr.io5.01GB2025-10-13 18:03
270

ghcr.io/ggml-org/llama.cpp:full-b6746

linux/amd64 ghcr.io2.06GB2025-10-14 17:12
193

ghcr.io/ggml-org/llama.cpp:full-cuda-b6823

linux/amd64 ghcr.io5.05GB2025-10-23 14:36
179

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

linux/amd64 ghcr.io2.69GB2025-10-30 17:31
256

ghcr.io/ggml-org/llama.cpp:server-musa-b6970

linux/amd64 ghcr.io4.47GB2025-11-07 14:50
131

ghcr.io/ggml-org/llama.cpp:full-cuda-b7083

linux/amd64 ghcr.io5.02GB2025-11-18 14:14
222

ghcr.io/ggml-org/llama.cpp:full-b7139

linux/amd64 ghcr.io2.01GB2025-11-24 14:53
252

ghcr.io/ggml-org/llama.cpp:server-b7139

linux/amd64 ghcr.io101.25MB2025-11-24 15:22
160

ghcr.io/ggml-org/llama.cpp:full-cuda12-b7681

linux/amd64 ghcr.io5.16GB2026-01-10 03:32
40

ghcr.io/ggml-org/llama.cpp:server-cuda13-b7728

linux/amd64 ghcr.io2.53GB2026-01-16 13:50
10