helm_chart/HyperPodHelmChart/charts/neuron-device-plugin/templates/k8s-neuron-device-plugin.yaml

# https://kubernetes.io/docs/concepts/extend-kubernetes/compute-storage-net/device-plugins/
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: neuron-device-plugin-daemonset
  namespace: {{ .Values.namespace }}
spec:
  selector:
    matchLabels:
      name:  neuron-device-plugin-ds
  updateStrategy:
    type: RollingUpdate
  template:
    metadata:
      # Uncomment the annotation below if k8s version is 1.13 or lower
      # annotations:
      #  scheduler.alpha.kubernetes.io/critical-pod: ""
      labels:
        name: neuron-device-plugin-ds
    spec:
      serviceAccount: neuron-device-plugin
      tolerations:
      - key: CriticalAddonsOnly
        operator: Exists
      - key: aws.amazon.com/neuron
        operator: Exists
        effect: NoSchedule
      - key: sagemaker.amazonaws.com/node-health-status
        operator: Equal
        value: Unschedulable
        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"
      affinity:
        nodeAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            nodeSelectorTerms:
              - matchExpressions:
                  - key: "node.kubernetes.io/instance-type"
                    operator: In
                    values:
                      - inf1.xlarge
                      - inf1.2xlarge
                      - inf1.6xlarge
                      - inf1.24xlarge
                      - inf2.xlarge
                      - inf2.8xlarge
                      - inf2.24xlarge
                      - inf2.48xlarge
                      - trn1.2xlarge
                      - trn1.32xlarge
                      - trn1n.32xlarge
                      - ml.inf2.xlarge
                      - ml.inf2.8xlarge
                      - ml.inf2.24xlarge
                      - ml.inf2.48xlarge
                      - ml.trn1.2xlarge
                      - ml.trn1.32xlarge
                      - ml.trn1n.32xlarge
                      - ml.trn2.48xlarge
      containers:
        # Find all neuron-device-plugin images at https://gallery.ecr.aws/neuron/neuron-device-plugin
      - image: public.ecr.aws/neuron/neuron-device-plugin:2.19.16.0
        imagePullPolicy: Always
        name: neuron-device-plugin
        env:
        - name: KUBECONFIG
          value: /etc/kubernetes/kubelet.conf
        - name: NODE_NAME
          valueFrom:
            fieldRef:
              fieldPath: spec.nodeName
        securityContext:
          allowPrivilegeEscalation: false
          capabilities:
            drop: ["ALL"]
        volumeMounts:
          - name: device-plugin
            mountPath: /var/lib/kubelet/device-plugins
          - name: infa-map
            mountPath: /run
      volumes:
        - name: device-plugin
          hostPath:
            path: /var/lib/kubelet/device-plugins
        - name: infa-map
          hostPath:
            path: /run