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

apiVersion: apps/v1
kind: Deployment
metadata:
  name: "{{ .Release.Name }}-deployment-vllm"
  namespace: {{ .Release.Namespace }}
  labels:
  {{- include "chart.labels" . | nindent 4 }}
spec:
  replicas: {{ .Values.replicaCount }}
  {{- include "chart.strategy" . | nindent 2 }}
  selector:                                                                                                                                  
    matchLabels:
      environment: "test"
      release: "test"
  progressDeadlineSeconds: 1200
  template:
    metadata:
      labels:
        environment: "test"
        release: "test"
    spec:
      containers:
        - name: "vllm"
          image: "{{ required "Required value 'image.repository' must be defined !" .Values.image.repository }}:{{ required "Required value 'image.tag' must be defined !" .Values.image.tag }}"
          {{- if .Values.image.command }}
          command :
            {{- with .Values.image.command }}
            {{- toYaml . | nindent 10 }}
            {{- end }}
          {{- end }}
          securityContext:
            {{- if .Values.image.securityContext }}
              {{- with .Values.image.securityContext }}
              {{- toYaml . | nindent 12 }}
              {{- end }}
            {{- else }}
            runAsNonRoot: false
              {{- include "chart.user" . | indent 12 }}
            {{- end }}
          imagePullPolicy: IfNotPresent
          {{- if .Values.image.env }}
          env :
            {{- with .Values.image.env }}
            {{- toYaml . | nindent 10 }}
            {{- end }}
          {{- else }}
          env: []
          {{- end }}
          {{- if or .Values.externalConfigs .Values.configs .Values.secrets }}
          envFrom:
            {{- if .Values.configs }}
            - configMapRef:
                name: "{{ .Release.Name }}-configs"
            {{- end }}
            {{- if .Values.secrets}}
            - secretRef:
                name: "{{ .Release.Name }}-secrets"
            {{- end }}
            {{- include "chart.externalConfigs" . | nindent 12 }}
          {{- end }}          
          ports:
            - name: {{ include "chart.container-port-name" . }}
              containerPort: {{ include "chart.container-port" . }}
            {{- include "chart.extraPorts" . | nindent 12 }}
          {{- include "chart.probes" . | indent 10 }}
          resources: {{- include "chart.resources" . | nindent 12 }}
          volumeMounts:
          - name: {{ .Release.Name }}-storage
            mountPath: /data

        {{- with .Values.extraContainers }}
        {{ toYaml . | nindent 8 }}
        {{- end }}

      {{-   if .Values.extraInit  }}
      initContainers:
      - name: wait-download-model
        image: {{ include "chart.extraInitImage" . }}
        command: 
          - /bin/bash
        args:
          - -eucx
          - while aws --endpoint-url $S3_ENDPOINT_URL s3 sync --dryrun s3://$S3_BUCKET_NAME/$S3_PATH /data | grep -q download; do sleep 10; done
        env: {{- include "chart.extraInitEnv" . | nindent 10 }}
        resources:
          requests:
            cpu: 200m
            memory: 1Gi
          limits:
            cpu: 500m
            memory: 2Gi
        volumeMounts:
        - name: {{ .Release.Name }}-storage
          mountPath: /data
      {{- end }}
      volumes:
        - name: {{ .Release.Name }}-storage
          persistentVolumeClaim:
            claimName: {{ .Release.Name }}-storage-claim     

      {{- with .Values.nodeSelector }}
      nodeSelector:
        {{- toYaml . | nindent 8 }}
      {{- end }}
      {{- with .Values.tolerations }}
      tolerations:
        {{- toYaml . | nindent 8 }}
      {{- end }}
      {{- if and (gt (int (index .Values.resources.requests "nvidia.com/gpu")) 0) (gt (int (index .Values.resources.limits "nvidia.com/gpu")) 0) }}
      runtimeClassName: nvidia
      affinity:
        nodeAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            nodeSelectorTerms:
              - matchExpressions:
                - key: nvidia.com/gpu.product
                  operator: In
                  {{- with .Values.gpuModels }}
                  values:
                    {{- toYaml . | nindent 20 }}
                  {{- end }}
      {{- end }}