vllm/examples/online_serving/chart-helm/templates/job.yaml

{{- if and .Values.extraInit .Values.extraInit.modelDownload.enabled }}
apiVersion: batch/v1
kind: Job
metadata:
  name: "{{ .Release.Name }}-init-vllm"
  namespace: {{ .Release.Namespace }}
spec:
  ttlSecondsAfterFinished: 100
  template:
   metadata:
     name: init-vllm
   spec:
    containers:
    - name: job-download-model
      image: {{ .Values.extraInit.modelDownload.image.repository }}:{{ .Values.extraInit.modelDownload.image.tag }}
      imagePullPolicy: {{ .Values.extraInit.modelDownload.image.pullPolicy }}
      command: {{ .Values.extraInit.modelDownload.downloadJob.command | toJson }}
      args:
      {{- toYaml .Values.extraInit.modelDownload.downloadJob.args | nindent 8 }}
      env:
      {{- if .Values.extraInit.modelDownload.downloadJob.env }}
      {{- toYaml .Values.extraInit.modelDownload.downloadJob.env | nindent 8 }}
      {{- else }}
      {{- include "chart.extraInitEnv" . | nindent 8 }}
      {{- end }}
      volumeMounts:
        - name: {{ .Release.Name }}-storage
          mountPath: /data
      resources:
        requests:
          cpu: 200m
          memory: 1Gi
        limits:
          cpu: 500m
          memory: 2Gi
    restartPolicy: OnFailure
    volumes:
    - name: {{ .Release.Name }}-storage
      persistentVolumeClaim:
        claimName: "{{ .Release.Name }}-storage-claim"
{{- end }}