server/examples/cuda-pod.yaml

apiVersion: v1
kind: Pod
metadata:
  name: gpu
spec:
  restartPolicy: Never
  containers:
    - name: gpu
      image: "nvidia/cuda:11.4.1-base-ubuntu20.04"
      command: [ "/bin/bash", "-c", "--" ]
      args: [ "while true; do sleep 30; done;" ]
      resources:
        limits:
          nvidia.com/gpu: 1