第 3 章 安装 Node Feature Discovery Operator 和 NVIDIA GPU Operator

流程

1. 禁用默认的 OperatorHub 源。运行以下命令:

   $ oc patch OperatorHub cluster --type json \
       -p '[{"op": "add", "path": "/spec/disableAllDefaultSources", "value": true}]'

2. 为 Node Feature Discovery Operator 和 NVIDIA GPU Operator 应用 Namespace、OperatorGroup 和 Subscription CR。

   1. 创建 Namespace CR：

      oc apply -f - <<EOF
      apiVersion: v1
      kind: Namespace
      metadata:
        name: nvidia-gpu-operator
      ---
      apiVersion: v1
      kind: Namespace
      metadata:
        name: openshift-nfd
        labels:
          name: openshift-nfd
          openshift.io/cluster-monitoring: "true"
      EOF

   2. 创建 OperatorGroup CR：

      oc apply -f - <<EOF
      apiVersion: operators.coreos.com/v1
      kind: OperatorGroup
      metadata:
        name: gpu-operator-certified
        namespace: nvidia-gpu-operator
      spec:
       targetNamespaces:
       - nvidia-gpu-operator
      ---
      apiVersion: operators.coreos.com/v1
      kind: OperatorGroup
      metadata:
        generateName: openshift-nfd-
        name: openshift-nfd
        namespace: openshift-nfd
      spec:
        targetNamespaces:
        - openshift-nfd
      EOF

   3. 创建 Subscription CR：

      oc apply -f - <<EOF
      apiVersion: operators.coreos.com/v1alpha1
      kind: Subscription
      metadata:
        name: gpu-operator-certified
        namespace: nvidia-gpu-operator
      spec:
        channel: "stable"
        installPlanApproval: Manual
        name: gpu-operator-certified
        source: certified-operators
        sourceNamespace: openshift-marketplace
      ---
      apiVersion: operators.coreos.com/v1alpha1
      kind: Subscription
      metadata:
        name: nfd
        namespace: openshift-nfd
      spec:
        channel: "stable"
        installPlanApproval: Automatic
        name: nfd
        source: redhat-operators
        sourceNamespace: openshift-marketplace
      EOF

3. 为 Hugging Face 令牌创建 Secret 自定义资源(CR)。

   1. 使用您在 Hugging Face 中设置的令牌，设置 HF_TOKEN 变量。

      $ HF_TOKEN=<your_huggingface_token>

   2. 将集群命名空间设置为与部署 Red Hat AI Inference Server 镜像的位置匹配，例如：

      $ NAMESPACE=rhaiis-namespace

   3. 在集群中创建 Secret CR：

      $ oc create secret generic hf-secret --from-literal=HF_TOKEN=$HF_TOKEN -n $NAMESPACE