This commit is contained in:
wbsong111
2025-10-23 16:39:45 +09:00
2 changed files with 7 additions and 2 deletions
@@ -21,4 +21,6 @@ spec:
image: {{ .Values.inferenceService.model.image }}
{{- end }}
resources:
{{- toYaml .Values.inferenceService.resources | nindent 8 }}
{{- toYaml .Values.inferenceService.resources | nindent 8 }}
minReplicas: {{ .Values.inferenceService.minReplicas }}
maxReplicas: {{ .Values.inferenceService.maxReplicas }}
+4 -1
View File
@@ -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: