Files
vllm/examples/deployment/chart-helm/templates/hpa.yaml
wang.yuqiGitHubgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
1d694e78c9 [Examples][last/6] Resettle examples. (#41084)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-05-07 19:42:12 -07:00

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 }}