gpu-workload/t5/kubernetes/pod-monitoring.yaml

apiVersion: monitoring.googleapis.com/v1
kind: PodMonitoring
metadata:
  name: torchserve
  labels:
    app.kubernetes.io/name: torchserve
spec:
  selector:
    matchLabels:
      model: t5
  endpoints:
  - port: metrics
    path: /metrics
    timeout: 30s
    interval: 60s