Files
vllm-project--vllm/examples/deployment/chart-helm/templates/hpa.yaml
T
wehub-resource-sync 7ce4c8e27e
pre-commit / pre-run-check (push) Has been cancelled
pre-commit / pre-commit (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:55:37 +08:00

31 lines
929 B
YAML

{{- if .Values.autoscaling.enabled }}
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
name: "{{ .Release.Name }}-hpa"
namespace: {{ .Release.Namespace }}
spec:
scaleTargetRef:
apiVersion: apps/v1
kind: Deployment
name: vllm
minReplicas: {{ .Values.autoscaling.minReplicas }}
maxReplicas: {{ .Values.autoscaling.maxReplicas }}
metrics:
{{- if .Values.autoscaling.targetCPUUtilizationPercentage }}
- type: Resource
resource:
name: cpu
target:
type: Utilization
averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
{{- end }}
{{- if .Values.autoscaling.targetMemoryUtilizationPercentage }}
- type: Resource
resource:
name: memory
target:
type: Utilization
averageUtilization: {{ .Values.autoscaling.targetMemoryUtilizationPercentage }}
{{- end }}
{{- end }}