example.yaml

apiVersion: v1
kind: Namespace
metadata:
  labels:
    kubernetes.io/metadata.name: gpu-test-workloads
    pod-security.kubernetes.io/enforce: privileged
  name: gpu-test-workloads
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: cuda-sample-vector-add
  namespace: gpu-test-workloads
  labels:
    app: cuda-sample-vector-add
spec:
  replicas: 1
  selector:
    matchLabels:
      app: cuda-sample-vector-add
  template:
    metadata:
      labels:
        app: cuda-sample-vector-add
    spec:
      containers:
        - name: cuda-sample-vector-add
          image: nvcr.io/nvidia/k8s/cuda-sample:vectoradd-cuda11.7.1-ubuntu20.04
          command:
            - /bin/bash
            - '-c'
            - '--'
          args:
            - while true; do /cuda-samples/vectorAdd; done
          resources:
            limits:
              nvidia.com/gpu: 1 # declare how many physical GPUs the pod needs
              nvidia.com/gpumem: 3000 # Each vGPU contains 3000M device memory （Optional,Integer）
          terminationMessagePath: /dev/termination-log
          terminationMessagePolicy: File
          imagePullPolicy: IfNotPresent
      restartPolicy: Always
      terminationGracePeriodSeconds: 30
      dnsPolicy: ClusterFirst
      hostPID: true
      securityContext: {}
      schedulerName: default-scheduler
      tolerations:
        - key: nvidia.com/gpu
          operator: Exists
          effect: NoSchedule
      priorityClassName: system-cluster-critical
  strategy:
    type: RollingUpdate
    rollingUpdate:
      maxUnavailable: 25%
      maxSurge: 25%
  revisionHistoryLimit: 10
  progressDeadlineSeconds: 600