unkinben
5372914803
Deploys LiteLLM proxy with CNPG PostgreSQL (3-instance HA), PgBouncer pooler, and Redis cache. Introduces a dedicated aitooling AppProject and ApplicationSet to keep AI tooling services separate from platform infra. Reviewed-on: #94
42 lines
852 B
YAML
42 lines
852 B
YAML
---
|
|
apiVersion: autoscaling/v2
|
|
kind: HorizontalPodAutoscaler
|
|
metadata:
|
|
name: litellm-hpa
|
|
namespace: litellm
|
|
spec:
|
|
scaleTargetRef:
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
name: litellm
|
|
minReplicas: 2
|
|
maxReplicas: 10
|
|
metrics:
|
|
- type: Resource
|
|
resource:
|
|
name: cpu
|
|
target:
|
|
type: Utilization
|
|
averageUtilization: 60
|
|
behavior:
|
|
scaleUp:
|
|
stabilizationWindowSeconds: 0
|
|
selectPolicy: Max
|
|
policies:
|
|
- type: Percent
|
|
value: 100
|
|
periodSeconds: 30
|
|
- type: Pods
|
|
value: 4
|
|
periodSeconds: 30
|
|
scaleDown:
|
|
stabilizationWindowSeconds: 300
|
|
selectPolicy: Min
|
|
policies:
|
|
- type: Percent
|
|
value: 10
|
|
periodSeconds: 60
|
|
- type: Pods
|
|
value: 2
|
|
periodSeconds: 60
|