ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd linux/amd64

ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd - 国内下载镜像源 浏览次数:49
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。

源镜像 ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd
国内镜像 swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd
镜像ID sha256:282d1bb50af40bb3068c0141db19f86d17f764fdeb54cc690824087efacf1d1c
镜像TAG server-cuda--b1-a59f8fd
大小 2.55GB
镜像源 ghcr.io
CMD
启动入口 /llama-server
工作目录
OS/平台 linux/amd64
浏览量 49 次
贡献者 tz*******l@gmail.com
镜像创建 2024-07-10T00:11:45.233488856Z
同步时间 2024-11-03 15:35
更新时间 2024-11-22 03:12
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>=11.7 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 NV_CUDA_CUDART_VERSION=11.7.99-1 NV_CUDA_COMPAT_PACKAGE=cuda-compat-11-7 CUDA_VERSION=11.7.1 LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64 NVIDIA_VISIBLE_DEVICES=all NVIDIA_DRIVER_CAPABILITIES=compute,utility NV_CUDA_LIB_VERSION=11.7.1-1 NV_NVTX_VERSION=11.7.91-1 NV_LIBNPP_VERSION=11.7.4.75-1 NV_LIBNPP_PACKAGE=libnpp-11-7=11.7.4.75-1 NV_LIBCUSPARSE_VERSION=11.7.4.91-1 NV_LIBCUBLAS_PACKAGE_NAME=libcublas-11-7 NV_LIBCUBLAS_VERSION=11.10.3.66-1 NV_LIBCUBLAS_PACKAGE=libcublas-11-7=11.10.3.66-1 NV_LIBNCCL_PACKAGE_NAME=libnccl2 NV_LIBNCCL_PACKAGE_VERSION=2.13.4-1 NCCL_VERSION=2.13.4-1 NV_LIBNCCL_PACKAGE=libnccl2=2.13.4-1+cuda11.7 NVIDIA_PRODUCT_NAME=CUDA
镜像标签
NVIDIA CORPORATION <cudatools@nvidia.com>: maintainer ubuntu: org.opencontainers.image.ref.name 22.04: org.opencontainers.image.version
镜像安全扫描 查看Trivy扫描报告

系统OS: ubuntu 22.04 扫描引擎: Trivy 扫描时间: 2024-11-03 15:35

低危漏洞:76 中危漏洞:64 高危漏洞:0 严重漏洞:0

Docker拉取命令 无权限下载?点我修复

docker pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd
docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd  ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd

Containerd拉取命令

ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd
ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd  ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd

Shell快速替换命令

sed -i 's#ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd#swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd#' 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--b1-a59f8fd && docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd  ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd'

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--b1-a59f8fd && ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd  ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd'

镜像历史

大小 创建时间 层信息
0.00B 2024-07-10 08:11:45 ENTRYPOINT ["/llama-server"]
0.00B 2024-07-10 08:11:45 HEALTHCHECK &{["CMD" "curl" "-f" "http://localhost:8080/health"] "0s" "0s" "0s" "0s" '\x00'}
458.00MB 2024-07-10 08:11:45 COPY /app/llama-server /llama-server # buildkit
59.78MB 2024-07-10 08:11:43 RUN /bin/sh -c apt-get update && apt-get install -y libcurl4-openssl-dev libgomp1 curl # buildkit
0.00B 2023-11-10 15:09:03 ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
0.00B 2023-11-10 15:09:03 ENV NVIDIA_PRODUCT_NAME=CUDA
2.53KB 2023-11-10 15:09:03 COPY nvidia_entrypoint.sh /opt/nvidia/ # buildkit
3.06KB 2023-11-10 15:09:02 COPY entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit
260.16KB 2023-11-10 15:09:02 RUN |1 TARGETARCH=amd64 /bin/sh -c apt-mark hold ${NV_LIBCUBLAS_PACKAGE_NAME} ${NV_LIBNCCL_PACKAGE_NAME} # buildkit
1.82GB 2023-11-10 15:09:02 RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-libraries-11-7=${NV_CUDA_LIB_VERSION} ${NV_LIBNPP_PACKAGE} cuda-nvtx-11-7=${NV_NVTX_VERSION} libcusparse-11-7=${NV_LIBCUSPARSE_VERSION} ${NV_LIBCUBLAS_PACKAGE} ${NV_LIBNCCL_PACKAGE} && rm -rf /var/lib/apt/lists/* # buildkit
0.00B 2023-11-10 15:09:02 LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
0.00B 2023-11-10 15:09:02 ARG TARGETARCH
0.00B 2023-11-10 15:09:02 ENV NV_LIBNCCL_PACKAGE=libnccl2=2.13.4-1+cuda11.7
0.00B 2023-11-10 15:09:02 ENV NCCL_VERSION=2.13.4-1
0.00B 2023-11-10 15:09:02 ENV NV_LIBNCCL_PACKAGE_VERSION=2.13.4-1
0.00B 2023-11-10 15:09:02 ENV NV_LIBNCCL_PACKAGE_NAME=libnccl2
0.00B 2023-11-10 15:09:02 ENV NV_LIBCUBLAS_PACKAGE=libcublas-11-7=11.10.3.66-1
0.00B 2023-11-10 15:09:02 ENV NV_LIBCUBLAS_VERSION=11.10.3.66-1
0.00B 2023-11-10 15:09:02 ENV NV_LIBCUBLAS_PACKAGE_NAME=libcublas-11-7
0.00B 2023-11-10 15:09:02 ENV NV_LIBCUSPARSE_VERSION=11.7.4.91-1
0.00B 2023-11-10 15:09:02 ENV NV_LIBNPP_PACKAGE=libnpp-11-7=11.7.4.75-1
0.00B 2023-11-10 15:09:02 ENV NV_LIBNPP_VERSION=11.7.4.75-1
0.00B 2023-11-10 15:09:02 ENV NV_NVTX_VERSION=11.7.91-1
0.00B 2023-11-10 15:09:02 ENV NV_CUDA_LIB_VERSION=11.7.1-1
0.00B 2023-11-10 15:04:25 ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
0.00B 2023-11-10 15:04:25 ENV NVIDIA_VISIBLE_DEVICES=all
17.29KB 2023-11-10 15:04:25 COPY NGC-DL-CONTAINER-LICENSE / # buildkit
0.00B 2023-11-10 15:04:25 ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64
0.00B 2023-11-10 15:04:25 ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
46.00B 2023-11-10 15:04:25 RUN |1 TARGETARCH=amd64 /bin/sh -c echo "/usr/local/nvidia/lib" >> /etc/ld.so.conf.d/nvidia.conf && echo "/usr/local/nvidia/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit
119.67MB 2023-11-10 15:04:25 RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-cudart-11-7=${NV_CUDA_CUDART_VERSION} ${NV_CUDA_COMPAT_PACKAGE} && rm -rf /var/lib/apt/lists/* # buildkit
0.00B 2023-11-10 15:04:11 ENV CUDA_VERSION=11.7.1
10.56MB 2023-11-10 15:04:11 RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends gnupg2 curl ca-certificates && curl -fsSLO https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/${NVARCH}/cuda-keyring_1.0-1_all.deb && dpkg -i cuda-keyring_1.0-1_all.deb && apt-get purge --autoremove -y curl && rm -rf /var/lib/apt/lists/* # buildkit
0.00B 2023-11-10 15:04:11 LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
0.00B 2023-11-10 15:04:11 ARG TARGETARCH
0.00B 2023-11-10 15:04:11 ENV NV_CUDA_COMPAT_PACKAGE=cuda-compat-11-7
0.00B 2023-11-10 15:04:11 ENV NV_CUDA_CUDART_VERSION=11.7.99-1
0.00B 2023-11-10 15:04:11 ENV NVIDIA_REQUIRE_CUDA=cuda>=11.7 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
0.00B 2023-11-10 15:04:11 ENV NVARCH=x86_64
0.00B 2023-10-05 15:33:32 /bin/sh -c #(nop) CMD ["/bin/bash"]
77.82MB 2023-10-05 15:33:32 /bin/sh -c #(nop) ADD file:63d5ab3ef0aab308c0e71cb67292c5467f60deafa9b0418cbb220affcd078444 in /
0.00B 2023-10-05 15:33:30 /bin/sh -c #(nop) LABEL org.opencontainers.image.version=22.04
0.00B 2023-10-05 15:33:30 /bin/sh -c #(nop) LABEL org.opencontainers.image.ref.name=ubuntu
0.00B 2023-10-05 15:33:30 /bin/sh -c #(nop) ARG LAUNCHPAD_BUILD_ARCH
0.00B 2023-10-05 15:33:30 /bin/sh -c #(nop) ARG RELEASE

镜像信息

{
    "Id": "sha256:282d1bb50af40bb3068c0141db19f86d17f764fdeb54cc690824087efacf1d1c",
    "RepoTags": [
        "ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd"
    ],
    "RepoDigests": [
        "ghcr.io/ggerganov/llama.cpp@sha256:1c890914e9b90a5fa2ccc9f9c33ee29a8ccb8a5d6d8c712bd587f98f4eb62a0d",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/ggerganov/llama.cpp@sha256:6167df6fe96cbd6f0cae28be42e64e70346a93704b4e75a830dcd8071da8ab65"
    ],
    "Parent": "",
    "Comment": "buildkit.dockerfile.v0",
    "Created": "2024-07-10T00:11:45.233488856Z",
    "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=11.7 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",
            "NV_CUDA_CUDART_VERSION=11.7.99-1",
            "NV_CUDA_COMPAT_PACKAGE=cuda-compat-11-7",
            "CUDA_VERSION=11.7.1",
            "LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64",
            "NVIDIA_VISIBLE_DEVICES=all",
            "NVIDIA_DRIVER_CAPABILITIES=compute,utility",
            "NV_CUDA_LIB_VERSION=11.7.1-1",
            "NV_NVTX_VERSION=11.7.91-1",
            "NV_LIBNPP_VERSION=11.7.4.75-1",
            "NV_LIBNPP_PACKAGE=libnpp-11-7=11.7.4.75-1",
            "NV_LIBCUSPARSE_VERSION=11.7.4.91-1",
            "NV_LIBCUBLAS_PACKAGE_NAME=libcublas-11-7",
            "NV_LIBCUBLAS_VERSION=11.10.3.66-1",
            "NV_LIBCUBLAS_PACKAGE=libcublas-11-7=11.10.3.66-1",
            "NV_LIBNCCL_PACKAGE_NAME=libnccl2",
            "NV_LIBNCCL_PACKAGE_VERSION=2.13.4-1",
            "NCCL_VERSION=2.13.4-1",
            "NV_LIBNCCL_PACKAGE=libnccl2=2.13.4-1+cuda11.7",
            "NVIDIA_PRODUCT_NAME=CUDA"
        ],
        "Cmd": null,
        "Healthcheck": {
            "Test": [
                "CMD",
                "curl",
                "-f",
                "http://localhost:8080/health"
            ]
        },
        "Image": "",
        "Volumes": null,
        "WorkingDir": "",
        "Entrypoint": [
            "/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": 2547532107,
    "GraphDriver": {
        "Data": {
            "LowerDir": "/var/lib/docker/overlay2/cf15ef161b7bedbb7b84077f9537239fe5c8de3cbb3e3ad644df064b0d9e3f53/diff:/var/lib/docker/overlay2/76be164f8328b37b304dd422eccf7e677a66d729b9c43a8e30d9e70da86b30da/diff:/var/lib/docker/overlay2/d914bad66dabdda108f5cd8357518b6ec2e5e54790a5a3205992a92859ff324b/diff:/var/lib/docker/overlay2/d09a614349bc7001ac24cf694b869649f50c9186acaa3b6267d46c798abaa53c/diff:/var/lib/docker/overlay2/77905561f5e181d60add8c386322a1781d3301d3cd3fe59043e114dd5be5fe48/diff:/var/lib/docker/overlay2/064f838f639490f15050cc39e7c94d0f9245a420f271c93377b6f7e7fe5882b3/diff:/var/lib/docker/overlay2/eb148c289f22be4c2e1e77b7348058adc45fbeb40b292ff321e6c80a4b2f1678/diff:/var/lib/docker/overlay2/9fa9ee7eafcffe1fb9da77d618175df81576d0fee4e782517251aa9484bff434/diff:/var/lib/docker/overlay2/4bf250e36b12061986bde7332522ba399caae0dd4e41f5f09d30a1434afa3f4c/diff:/var/lib/docker/overlay2/f2905627b4505cda033dd62b5a5dc1676edda5a6e1bda7cd6e6e2048fcf5aee0/diff",
            "MergedDir": "/var/lib/docker/overlay2/240a6c76e86bbef72011a35eae861c67068404ac7828bb86808ea9d419ef821e/merged",
            "UpperDir": "/var/lib/docker/overlay2/240a6c76e86bbef72011a35eae861c67068404ac7828bb86808ea9d419ef821e/diff",
            "WorkDir": "/var/lib/docker/overlay2/240a6c76e86bbef72011a35eae861c67068404ac7828bb86808ea9d419ef821e/work"
        },
        "Name": "overlay2"
    },
    "RootFS": {
        "Type": "layers",
        "Layers": [
            "sha256:256d88da41857db513b95b50ba9a9b28491b58c954e25477d5dad8abb465430b",
            "sha256:4ad41657a86c8516483228108d82a96ac1775fc9854fc3678d8c0d7da25739b8",
            "sha256:67efcadf4aa7886c0d71a16de756a006aad4fcc5d29ffab31748fc775195be06",
            "sha256:ce834a1fbcb846045b8e44772c20fe0b993c32e73715996d5353e594a9d2c5c3",
            "sha256:95e88160a0fcdbddc8277a0764eb3effe83301ed42102de4b7673b42b3387acb",
            "sha256:4b69e1255531691f1b5f1ecfff65847ffac917c8e5a0747648a872cfaadab270",
            "sha256:2d59be1c8099b8cebd945a5923ec6e4fe676df8eac50280a8e5c16a87e69c667",
            "sha256:eb9fe4c91d76328db5dcea49b192a276545fd774342785855123d6b7ac5f739f",
            "sha256:c4d94af61487ca48de110c9a4b962779e28754a80c1fcb62e9b679e88836b29a",
            "sha256:9163d5e2f85e485464d6fa403d5465bbe8977d10f999fbb667966e6315da505c",
            "sha256:9b20e8b9450424f7cae4d88c4af1a3a272348f80a01006268953db3cbfffe813"
        ]
    },
    "Metadata": {
        "LastTagTime": "2024-11-03T15:35:11.156981515+08:00"
    }
}

更多版本

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

linux/amd64 ghcr.io2.73GB2024-09-12 11:55
128

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

linux/amd64 ghcr.io2.32GB2024-11-03 15:07
37

ghcr.io/ggerganov/llama.cpp:server-cuda--b1-a59f8fd

linux/amd64 ghcr.io2.55GB2024-11-03 15:35
48

ghcr.io/ggerganov/llama.cpp:light

linux/amd64 ghcr.io175.71MB2024-11-05 16:15
25

ghcr.io/ggerganov/llama.cpp:full

linux/amd64 ghcr.io3.52GB2024-11-08 14:49
23