Docker拉取命令

docker pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/seldonio/mlserver:1.7.1
docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/seldonio/mlserver:1.7.1  docker.io/seldonio/mlserver:1.7.1

Containerd拉取命令

ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/seldonio/mlserver:1.7.1
ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/seldonio/mlserver:1.7.1  docker.io/seldonio/mlserver:1.7.1

Shell快速替换命令

sed -i 's#seldonio/mlserver:1.7.1#swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/seldonio/mlserver:1.7.1#' deployment.yaml

Ansible快速分发-Docker

#ansible k8s -m shell -a 'docker pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/seldonio/mlserver:1.7.1 && docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/seldonio/mlserver:1.7.1  docker.io/seldonio/mlserver:1.7.1'

Ansible快速分发-Containerd

#ansible k8s -m shell -a 'ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/seldonio/mlserver:1.7.1 && ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/seldonio/mlserver:1.7.1  docker.io/seldonio/mlserver:1.7.1'

镜像构建历史

# 2025-06-06 20:31:52  0.00B 设置默认要执行的命令
CMD ["/bin/bash" "-c" ". $CONDA_PATH/etc/profile.d/conda.sh &&     source ./hack/activate-env.sh $MLSERVER_ENV_TARBALL &&     mlserver start $MLSERVER_MODELS_DIR"]
                        
# 2025-06-06 20:31:52  0.00B 指定运行容器时使用的用户
USER 1000
                        
# 2025-06-06 20:31:52  5.46KB 复制新文件或目录到容器中
COPY ./hack/build-env.sh ./hack/generate_dotenv.py ./hack/activate-env.sh ./hack/ # buildkit
                        
# 2025-06-06 20:31:52  1.89MB 复制新文件或目录到容器中
COPY ./licenses/license.txt /licenses/ # buildkit
                        
# 2025-06-06 20:31:52  1.89MB 复制新文件或目录到容器中
COPY ./licenses/license.txt . # buildkit
                        
# 2025-06-06 20:31:52  9.45GB 执行命令并创建新的镜像层
RUN |4 PYTHON_VERSION=3.10.12 CONDA_VERSION=23.11.0 MINIFORGE_VERSION=23.11.0-0 RUNTIMES=all /bin/bash -c . $CONDA_PATH/etc/profile.d/conda.sh &&     pip install --upgrade pip wheel setuptools &&     if [[ $RUNTIMES == "all" ]]; then         for _wheel in "./dist/mlserver_"*.whl; do             if [[ ! $_wheel == *"mllib"* ]]; then                 echo "--> Installing $_wheel...";                 pip install $_wheel --constraint ./dist/constraints.txt;             fi         done     else         for _runtime in $RUNTIMES; do             _wheelName=$(echo $_runtime | tr '-' '_');             _wheel="./dist/$_wheelName-"*.whl;             echo "--> Installing $_wheel...";             pip install $_wheel --constraint ./dist/constraints.txt;         done     fi &&     pip install $(ls "./dist/mlserver-"*.whl) --constraint ./dist/constraints.txt &&     rm -f /opt/conda/lib/python3.10/site-packages/spacy/tests/package/requirements.txt &&     rm -rf /root/.cache/pip # buildkit
                        
# 2025-06-06 20:28:38  431.76KB 复制新文件或目录到容器中
COPY /opt/mlserver/dist ./dist # buildkit
                        
# 2025-06-06 20:28:38  2.99KB 执行命令并创建新的镜像层
RUN |4 PYTHON_VERSION=3.10.12 CONDA_VERSION=23.11.0 MINIFORGE_VERSION=23.11.0-0 RUNTIMES=all /bin/bash -c useradd -u 1000 -s /bin/bash mlserver -d $MLSERVER_PATH &&     chown -R 1000:0 $MLSERVER_PATH &&     chmod -R 776 $MLSERVER_PATH # buildkit
                        
# 2025-06-06 20:28:38  0.00B 设置工作目录为/opt/mlserver
WORKDIR /opt/mlserver
                        
# 2025-06-06 20:28:38  0.00B 执行命令并创建新的镜像层
RUN |4 PYTHON_VERSION=3.10.12 CONDA_VERSION=23.11.0 MINIFORGE_VERSION=23.11.0-0 RUNTIMES=all /bin/bash -c mkdir $MLSERVER_PATH # buildkit
                        
# 2025-06-06 20:28:38  856.56MB 执行命令并创建新的镜像层
RUN |4 PYTHON_VERSION=3.10.12 CONDA_VERSION=23.11.0 MINIFORGE_VERSION=23.11.0-0 RUNTIMES=all /bin/bash -c microdnf install -y wget &&     wget "https://github.com/conda-forge/miniforge/releases/download/${MINIFORGE_VERSION}/Miniforge3-${MINIFORGE_VERSION}-Linux-x86_64.sh"         -O miniforge3.sh &&     bash "./miniforge3.sh" -b -p $CONDA_PATH &&     rm ./miniforge3.sh &&     echo $PATH &&     conda install --yes         conda=$CONDA_VERSION         python=$PYTHON_VERSION         ffmpeg &&     conda clean -tipy &&     microdnf remove -y wget &&     echo "conda activate base" >> "$CONDA_PATH/etc/profile.d/conda.sh" &&     ln -s "$CONDA_PATH/etc/profile.d/conda.sh" /etc/profile.d/conda.sh &&     echo ". $CONDA_PATH/etc/profile.d/conda.sh" >> ~/.bashrc # buildkit
                        
# 2025-06-06 20:27:40  334.04MB 执行命令并创建新的镜像层
RUN |4 PYTHON_VERSION=3.10.12 CONDA_VERSION=23.11.0 MINIFORGE_VERSION=23.11.0-0 RUNTIMES=all /bin/bash -c microdnf update -y &&     microdnf install -y         tar         gzip         libgomp         mesa-libGL         glib2-devel         shadow-utils         git # buildkit
                        
# 2025-06-06 20:27:40  0.00B 设置环境变量 MLSERVER_MODELS_DIR MLSERVER_ENV_TARBALL MLSERVER_PATH CONDA_PATH PATH LD_LIBRARY_PATH HF_HOME NUMBA_CACHE_DIR
ENV MLSERVER_MODELS_DIR=/mnt/models MLSERVER_ENV_TARBALL=/mnt/models/environment.tar.gz MLSERVER_PATH=/opt/mlserver CONDA_PATH=/opt/conda PATH=/opt/mlserver/.local/bin:/opt/conda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/opt/conda/lib/python3.10/site-packages/nvidia/cuda_runtime/lib: HF_HOME=/opt/mlserver/.cache NUMBA_CACHE_DIR=/opt/mlserver/.cache
                        
# 2025-06-06 20:27:40  0.00B 定义构建参数
ARG RUNTIMES=all
                        
# 2025-06-06 20:27:40  0.00B 定义构建参数
ARG MINIFORGE_VERSION=23.11.0-0
                        
# 2025-06-06 20:27:40  0.00B 定义构建参数
ARG CONDA_VERSION=23.11.0
                        
# 2025-06-06 20:27:40  0.00B 定义构建参数
ARG PYTHON_VERSION=3.10.12
                        
# 2025-06-06 20:27:40  0.00B 
SHELL [/bin/bash -c]
                        
# 2025-05-14 18:36:12  104.40MB 
/bin/sh -c #(nop) LABEL "build-date"="2025-05-14T10:35:47" "architecture"="x86_64" "vcs-type"="git" "vcs-ref"="f2f252e0ac953b9e80eaebfc08ec086edac81945" "release"="1747218906"
                        
# 2025-05-14 18:36:11  0.00B 
/bin/sh -c #(nop) COPY file:58cc94f5b3b2d60de2c77a6ed4b1797dcede502ccdb429a72e7a72d994235b3c in /usr/share/buildinfo/content-sets.json 
                        
# 2025-05-14 18:36:11  0.00B 
/bin/sh -c #(nop) CMD ["/bin/bash"]
                        
# 2025-05-14 18:36:11  0.00B 
/bin/sh -c #(nop) COPY file:b37d593713ee21ad52a4cd1424dc019a24f7966f85df0ac4b86d234302695328 in /etc/yum.repos.d/. 
                        
# 2025-05-14 18:36:11  0.00B 
/bin/sh -c #(nop) COPY dir:9782e2e1b0ca599e0a33d178720d08213ae97157f753b7e5bae27ac0755f7280 in / 
                        
# 2025-05-14 18:36:11  0.00B 
/bin/sh -c #(nop) ENV container oci
                        
# 2025-05-14 18:36:11  0.00B 
/bin/sh -c #(nop) LABEL io.openshift.tags="minimal rhel9"
                        
# 2025-05-14 18:36:11  0.00B 
/bin/sh -c #(nop) LABEL io.openshift.expose-services=""
                        
# 2025-05-14 18:36:11  0.00B 
/bin/sh -c #(nop) LABEL io.k8s.display-name="Red Hat Universal Base Image 9 Minimal"
                        
# 2025-05-14 18:36:11  0.00B 
/bin/sh -c #(nop) LABEL io.k8s.description="The Universal Base Image Minimal is a stripped down image that uses microdnf as a package manager. 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."
                        
# 2025-05-14 18:36:09  0.00B 
/bin/sh -c #(nop) LABEL description="The Universal Base Image Minimal is a stripped down image that uses microdnf as a package manager. 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."
                        
# 2025-05-14 18:36:06  0.00B 
/bin/sh -c #(nop) LABEL summary="Provides the latest release of the minimal Red Hat Universal Base Image 9."
                        
# 2025-05-14 18:36:05  0.00B 
/bin/sh -c #(nop) LABEL com.redhat.license_terms="https://www.redhat.com/en/about/red-hat-end-user-license-agreements#UBI"
                        
# 2025-05-14 18:36:05  0.00B 
/bin/sh -c #(nop) LABEL com.redhat.component="ubi9-minimal-container"       name="ubi9-minimal"       version="9.6"       distribution-scope="public"
                        
# 2025-05-14 18:36:05  0.00B 
/bin/sh -c #(nop) LABEL url="https://www.redhat.com"
                        
# 2025-05-14 18:36:05  0.00B 
/bin/sh -c #(nop) LABEL vendor="Red Hat, Inc."
                        
# 2025-05-14 18:36:04  0.00B 
/bin/sh -c #(nop) LABEL maintainer="Red Hat, Inc."
                        
                    

镜像信息

{
    "Id": "sha256:b601307570e541d09c4183318640c0660a22a7399f71b76fbcd8b146b42d736e",
    "RepoTags": [
        "seldonio/mlserver:1.7.1",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/seldonio/mlserver:1.7.1"
    ],
    "RepoDigests": [
        "seldonio/mlserver@sha256:80c10c963d5ef4f61abb84c72c5600a3da08e99acb8a8f4fc64c281df00dc218",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/seldonio/mlserver@sha256:80c10c963d5ef4f61abb84c72c5600a3da08e99acb8a8f4fc64c281df00dc218"
    ],
    "Parent": "",
    "Comment": "buildkit.dockerfile.v0",
    "Created": "2025-06-06T12:31:52.651951974Z",
    "Container": "",
    "ContainerConfig": null,
    "DockerVersion": "",
    "Author": "",
    "Config": {
        "Hostname": "",
        "Domainname": "",
        "User": "1000",
        "AttachStdin": false,
        "AttachStdout": false,
        "AttachStderr": false,
        "Tty": false,
        "OpenStdin": false,
        "StdinOnce": false,
        "Env": [
            "PATH=/opt/mlserver/.local/bin:/opt/conda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",
            "container=oci",
            "MLSERVER_MODELS_DIR=/mnt/models",
            "MLSERVER_ENV_TARBALL=/mnt/models/environment.tar.gz",
            "MLSERVER_PATH=/opt/mlserver",
            "CONDA_PATH=/opt/conda",
            "LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/opt/conda/lib/python3.10/site-packages/nvidia/cuda_runtime/lib:",
            "HF_HOME=/opt/mlserver/.cache",
            "NUMBA_CACHE_DIR=/opt/mlserver/.cache"
        ],
        "Cmd": [
            "/bin/bash",
            "-c",
            ". $CONDA_PATH/etc/profile.d/conda.sh \u0026\u0026     source ./hack/activate-env.sh $MLSERVER_ENV_TARBALL \u0026\u0026     mlserver start $MLSERVER_MODELS_DIR"
        ],
        "ArgsEscaped": true,
        "Image": "",
        "Volumes": null,
        "WorkingDir": "/opt/mlserver",
        "Entrypoint": null,
        "OnBuild": null,
        "Labels": {
            "architecture": "x86_64",
            "build-date": "2025-05-14T10:35:47",
            "com.redhat.component": "ubi9-minimal-container",
            "com.redhat.license_terms": "https://www.redhat.com/en/about/red-hat-end-user-license-agreements#UBI",
            "description": "MLServer aims to provide an easy way to start serving your machine learning models through a REST and gRPC interface, fully compliant with KFServing’s V2 Dataplane spec.",
            "distribution-scope": "public",
            "io.buildah.version": "1.39.0-dev",
            "io.k8s.description": "The Universal Base Image Minimal is a stripped down image that uses microdnf as a package manager. 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 Minimal",
            "io.openshift.expose-services": "",
            "io.openshift.tags": "minimal rhel9",
            "maintainer": "hello@seldon.io",
            "name": "mlserver",
            "release": "1.7.1",
            "summary": "An open source inference server for your machine learning models.",
            "url": "https://www.redhat.com",
            "vcs-ref": "f2f252e0ac953b9e80eaebfc08ec086edac81945",
            "vcs-type": "git",
            "vendor": "SeldonIO",
            "version": "1.7.1"
        },
        "Shell": [
            "/bin/bash",
            "-c"
        ]
    },
    "Architecture": "amd64",
    "Os": "linux",
    "Size": 10751778738,
    "GraphDriver": {
        "Data": {
            "LowerDir": "/var/lib/docker/overlay2/fc68fd120b3eb7a8e0419cccb119cc3d84f448c87d95b5e9d2be77511da87a50/diff:/var/lib/docker/overlay2/8cb5db3aa64503cfd823a0b76773b6b8563befa5696931059d3c9d6967c60ce3/diff:/var/lib/docker/overlay2/32f98a9acd706bf62a2468c9a015c2a2398e340acb3625f58b24de0ddbc0a03c/diff:/var/lib/docker/overlay2/baf2c8d9c60f3113ff648b5d9e83cbb8d3c04b9418e6d6506037b858d4164ee1/diff:/var/lib/docker/overlay2/bf7c0f6279e8bda626ce382ca08ec7c8ad3d483d6cb226833beed4f4db2e0696/diff:/var/lib/docker/overlay2/16652a8c222a1f54c9242c8dd82964388e94d1efcf5c64a190ee1f56b389281b/diff:/var/lib/docker/overlay2/56678fdc0fae7b311e2de2ed15912949469a51089486ef92e1cbc207bd70419c/diff:/var/lib/docker/overlay2/6a4b285408ac6da062113a38b4aea09c5c09cd3703c18c7a969c0b3d8733ebbc/diff:/var/lib/docker/overlay2/39b012578294e85f29248e82bacd0379ee38347230c130c9cbbc66da4aeff80a/diff:/var/lib/docker/overlay2/62f110f1cf927bb0c293f44486e13ec85cad72f518133a54ebc3e74ea649249c/diff",
            "MergedDir": "/var/lib/docker/overlay2/e04cb97ce34a8c01071e88cf4a6645670068393cf8e467ecbae049d895215d1d/merged",
            "UpperDir": "/var/lib/docker/overlay2/e04cb97ce34a8c01071e88cf4a6645670068393cf8e467ecbae049d895215d1d/diff",
            "WorkDir": "/var/lib/docker/overlay2/e04cb97ce34a8c01071e88cf4a6645670068393cf8e467ecbae049d895215d1d/work"
        },
        "Name": "overlay2"
    },
    "RootFS": {
        "Type": "layers",
        "Layers": [
            "sha256:4caa76cd913fca9631c8168851168a2b9235ba5f5c51ada4444bfefaf1df2a54",
            "sha256:2335e92b1e5acc87d773174d5526b32b059f424d4bfa3662b05a254eedea49f6",
            "sha256:8d16007266ebf04030f5e89ba80195777645414e21962ed5690a721370a72a40",
            "sha256:32afbc953b17a33c135ef56999c5ab9b5a08c29039fb3ea95f6a88bb7e1d68b6",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:fc90bd77acd452c86170d68b033462caad9c0f4e41431ae78670c9ff62ca2b89",
            "sha256:c15e3bd28056534c8b9ee47b9221eb367320eff9e7fd73ee9f77fdd7fe3a9332",
            "sha256:d2e4ba7f1ad959a7a85f34bdf900c84bf312ad3bfcce6f78191f5c16246d7631",
            "sha256:9e02d186c913cc28f877debc253d01aaceb1632242fb57099b4a4992355ab5fa",
            "sha256:5e4a6caf05d45f7045b033fd224f68cf9cdd32dae306a9dd1407cf73f3d670ab",
            "sha256:1affa84f0549730d3439dfd55302392274330a64f102cad1a0d7f587da78afe5"
        ]
    },
    "Metadata": {
        "LastTagTime": "2026-11-11T00:33:48.53650615+08:00"
    }
}