diff --git a/charts/kserve/CUSTOM-README.md b/charts/kserve/CUSTOM-README.md index 3e2c52c..8eb553e 100644 --- a/charts/kserve/CUSTOM-README.md +++ b/charts/kserve/CUSTOM-README.md @@ -29,6 +29,7 @@ | `inferenceService.model.args[1]` | 사용할 모델 이름 | `--model_name=phi-1.5` | | `inferenceService.model.args[2]` | 데이터 타입 설정 | `--dtype=float16` | | `inferenceService.model.storageUri` | 모델 파일 저장 위치 | `pvc://model-volume/phi-1_5` | +| `inferenceService.model.image` | 모델 서빙 이미지 | `kserve/huggingfaceserver:v0.15.0-gpu` | ### 3) 리소스 설정 diff --git a/charts/kserve/custom-values.yaml b/charts/kserve/custom-values.yaml index 1e48cd4..b11caf8 100644 --- a/charts/kserve/custom-values.yaml +++ b/charts/kserve/custom-values.yaml @@ -8,6 +8,7 @@ inferenceService: - --model_name=phi-1_5 - --dtype=float16 storageUri: "pvc://model-volume/phi-1_5" + image: kserve/huggingfaceserver:v0.15.0-gpu resources: limits: diff --git a/charts/kserve/templates/inferenceservice.yaml b/charts/kserve/templates/inferenceservice.yaml index b9fd17a..535899b 100644 --- a/charts/kserve/templates/inferenceservice.yaml +++ b/charts/kserve/templates/inferenceservice.yaml @@ -17,5 +17,8 @@ spec: {{- toYaml . | nindent 8 }} {{- end }} storageUri: {{ .Values.inferenceService.model.storageUri }} + {{- if .Values.inferenceService.model.image }} + image: {{ .Values.inferenceService.model.image }} + {{- end }} resources: {{- toYaml .Values.inferenceService.resources | nindent 8 }} \ No newline at end of file diff --git a/charts/kserve/values.yaml b/charts/kserve/values.yaml index 49af5c2..a2ae5e4 100644 --- a/charts/kserve/values.yaml +++ b/charts/kserve/values.yaml @@ -22,6 +22,7 @@ inferenceService: - --model_name=phi-1.5 - --dtype=float16 storageUri: "pvc://model-volume/phi-1_5" + image: kserve/huggingfaceserver:v0.15.0-gpu # 리소스 설정 resources: