diff --git a/charts/kserve/templates/inferenceservice.yaml b/charts/kserve/templates/inferenceservice.yaml index 535899b..7338113 100644 --- a/charts/kserve/templates/inferenceservice.yaml +++ b/charts/kserve/templates/inferenceservice.yaml @@ -21,4 +21,6 @@ spec: image: {{ .Values.inferenceService.model.image }} {{- end }} resources: - {{- toYaml .Values.inferenceService.resources | nindent 8 }} \ No newline at end of file + {{- toYaml .Values.inferenceService.resources | nindent 8 }} + minReplicas: {{ .Values.inferenceService.minReplicas }} + maxReplicas: {{ .Values.inferenceService.maxReplicas }} \ No newline at end of file diff --git a/charts/kserve/values.yaml b/charts/kserve/values.yaml index a2ae5e4..7988ef4 100644 --- a/charts/kserve/values.yaml +++ b/charts/kserve/values.yaml @@ -23,7 +23,10 @@ inferenceService: - --dtype=float16 storageUri: "pvc://model-volume/phi-1_5" image: kserve/huggingfaceserver:v0.15.0-gpu - + + minReplicas: 0 + maxReplicas: 3 + # 리소스 설정 resources: limits: