gcloud-lab/apps/base/customer1/openclaw/keda-vllm.yaml

apiVersion: http.keda.sh/v1alpha1
kind: HTTPScaledObject
metadata:
  name: openclaw-brain-a100-scaling
  namespace: customer1
spec:
  # The hostname(s) the interceptor should match and route
  hosts:
    - openclaw-brain-service.customer1.svc.cluster.local   # or your external domain if using Ingress
    # - "*.customer1.svc.cluster.local"   # optional wildcard

  # What to scale
  scaleTargetRef:
    name: openclaw-brain-vllm          # your Deployment name
    kind: Deployment
    apiVersion: apps/v1

  # The Service the interceptor will forward traffic to
  service:
    name: openclaw-brain-service       # adjust if your Service name is different
    port: 8000                           # or 8080 / whatever port your container listens on

  # Replica settings (enables scale-to-zero)
  replicas:
    min: 0
    max: 1

  # Scaling behavior – choose ONE of the two options below:

  # Option 1: Scale based on concurrent/pending requests (simplest, good for cold-start wake-up)
  targetPendingRequests: 1             # wake up on any incoming request