apiVersion: keda.sh/v1alpha1
kind: ScaledObject
metadata:
  name: rtx6000-scaling
  namespace: customer1
spec:
  scaleTargetRef:
    name: rtx6000-brain-vllm
    kind: Deployment
    apiVersion: apps/v1
  hosts:
    - rtx6000-brain-service.customer1.svc.cluster.local
  replicas:
    min: 0
    max: 1
  targetPendingRequests: 1
  scaledownPeriod: 900\n  pollingInterval: 10\n  cooldownPeriod: 30