apiVersion: node.k8s.io/v1
kind: RuntimeClass
metadata:
  name: nvidia
handler: nvidia
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: nvidia-device-plugin-daemonset
  namespace: kube-system
spec:
  selector:
    matchLabels:
      name: nvidia-device-plugin-ds
  updateStrategy:
    type: RollingUpdate
  template:
    metadata:
      labels:
        name: nvidia-device-plugin-ds
    spec:
      runtimeClassName: nvidia # Explicitly request the runtime
      tolerations:
      - key: nvidia.com/gpu
        operator: Exists
        effect: NoSchedule
      # Mark this pod as a critical add-on; when enabled, the critical add-on
      # scheduler reserves resources for critical add-on pods so that they can
      # be rescheduled after a failure.
      # See https://kubernetes.io/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/
      priorityClassName: "system-node-critical"
      containers:
      - image: nvcr.io/nvidia/k8s-device-plugin:v0.15.0-rc.2
        name: nvidia-device-plugin-ctr
        env:
          - name: FAIL_ON_INIT_ERROR
            value: "false"
        securityContext:
          allowPrivilegeEscalation: false
          capabilities:
            drop: ["ALL"]
        volumeMounts:
        - name: device-plugin
          mountPath: /var/lib/kubelet/device-plugins
      volumes:
      - name: device-plugin
        hostPath:
          path: /var/lib/kubelet/device-plugins