gcloud-lab/infrastructure/gpus/base/keda-gpu-scaling/keda-vllm.yaml
2026-04-29 00:05:09 -04:00

17 lines
352 B
YAML

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