gpu-workload/triton/hpa.yaml

apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: triton-inference-server-hpa
  labels:
    app: triton-inference-server-hpa
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: triton-inference-server
  minReplicas: 1
  maxReplicas: 3
  metrics:
    - type: External
      external:
        metric:
          name: kubernetes.io|container|accelerator|duty_cycle
        target:
          type: AverageValue
          averageValue: "80"