19 lines
543 B
YAML
19 lines
543 B
YAML
apiVersion: http.keda.sh/v1alpha1
|
|
kind: HTTPScaledObject
|
|
metadata:
|
|
name: openclaw-brain-a100-scaling
|
|
namespace: customer1
|
|
spec:
|
|
scaleTargetRef:
|
|
name: openclaw-brain-vllm
|
|
kind: Deployment
|
|
minReplicaCount: 0
|
|
maxReplicaCount: 1
|
|
cooldownPeriod: 900 # 15 minutes idle before scale-down
|
|
pollingInterval: 30
|
|
triggers:
|
|
- type: http
|
|
metadata:
|
|
path: "/v1/"
|
|
host: "openclaw-brain-service.customer1.svc.cluster.local"
|
|
requestCount: "1" # Scale up on 1+ request (wake script handles cold start)
|