kserve/charts/kserve-llmisvc-resources/values.yaml

kserve:
  version: v0.19.0
  createSharedResources: true
  inferenceServiceConfig:
    enabled: ''
  certManager:
    enabled: ''
  storagecontainer:
    enabled: ''
  agent:
    image: kserve/agent
    tag: ''
  router:
    image: kserve/router
    tag: ''
    imagePullPolicy: IfNotPresent
    imagePullSecrets: []
  service:
    serviceClusterIPNone: false
  storage:
    image: kserve/storage-initializer
    tag: ''
    resources:
      requests:
        memory: 100Mi
        cpu: 100m
      limits:
        memory: 1Gi
        cpu: '1'
    containerSecurityContext:
      allowPrivilegeEscalation: false
      privileged: false
      runAsNonRoot: true
      capabilities:
        drop:
          - ALL
    enableModelcar: true
    uidModelcar: 1010
    cpuModelcar: 10m
    memoryModelcar: 15Mi
    caBundleConfigMapName: ''
    caBundleVolumeMountPath: /etc/ssl/custom-certs
    storageSpecSecretName: storage-config
    storageSecretNameAnnotation: serving.kserve.io/secretName
    s3:
      accessKeyIdName: AWS_ACCESS_KEY_ID
      secretAccessKeyName: AWS_SECRET_ACCESS_KEY
      endpoint: ''
      useHttps: ''
      region: ''
      verifySSL: ''
      useVirtualBucket: ''
      useAnonymousCredential: ''
      CABundleConfigMap: ''
      CABundle: ''
  metricsaggregator:
    enableMetricAggregation: 'false'
    enablePrometheusScraping: 'false'
  servingruntime:
    art:
      image: kserve/art-explainer
      defaultVersion: ''
  localmodel:
    enabled: false
    controller:
      image: kserve/kserve-localmodel-controller
      tag: ''
    jobNamespace: kserve-localmodel-jobs
    jobTTLSecondsAfterFinished: 3600
    defaultJobImage: kserve/storage-initializer
    defaultJobTag: ''
    securityContext:
      fsGroup: 1000
    disableVolumeManagement: false
    agent:
      nodeSelector: {}
      affinity: {}
      tolerations: []
      hostPath: /mnt/models
      image: kserve/kserve-localmodelnode-agent
      tag: ''
      reconcilationFrequencyInSecs: 60
      securityContext:
        runAsUser: 1000
        runAsNonRoot: true
  security:
    autoMountServiceAccountToken: true
  inferenceservice:
    resources:
      limits:
        cpu: '1'
        memory: 2Gi
      requests:
        cpu: '1'
        memory: 2Gi
  opentelemetryCollector:
    scrapeInterval: 5s
    metricReceiverEndpoint: keda-otel-scaler.keda.svc:4317
    metricScalerEndpoint: keda-otel-scaler.keda.svc:4318
    resource:
      cpuLimit: '1'
      memoryLimit: 2Gi
      cpuRequest: 200m
      memoryRequest: 512Mi
  autoscaler:
    scaleUpStabilizationWindowSeconds: '0'
    scaleDownStabilizationWindowSeconds: '300'
  llmisvc:
    createGIECRDs: true
    controller:
      image: kserve/llmisvc-controller
      tag: ''
      imagePullPolicy: Always
      imagePullSecrets: []
      labels: {}
      podLabels: {}
      annotations: {}
      podAnnotations: {}
      serviceAnnotations: {}
      securityContext:
        runAsNonRoot: true
        seccompProfile:
          type: RuntimeDefault
      containerSecurityContext:
        allowPrivilegeEscalation: false
        capabilities:
          drop:
            - ALL
        privileged: false
        readOnlyRootFilesystem: true
        runAsNonRoot: true
        runAsUser: 1000
        seccompProfile:
          type: RuntimeDefault
      metricsBindAddress: 127.0.0.1
      metricsBindPort: '8443'
      nodeSelector: {}
      tolerations: []
      topologySpreadConstraints: []
      affinity: {}
      resources:
        limits:
          cpu: 100m
          memory: 300Mi
        requests:
          cpu: 100m
          memory: 300Mi
      replicas: 1
      strategy:
        type: RollingUpdate
        rollingUpdate:
          maxSurge: 1
          maxUnavailable: 0
      livenessProbe:
        enabled: true
        initialDelaySeconds: 30
        periodSeconds: 10
        timeoutSeconds: 5
        failureThreshold: 5
        httpGet:
          path: /healthz
          port: 8081
      readinessProbe:
        enabled: true
        initialDelaySeconds: 30
        periodSeconds: 5
        timeoutSeconds: 5
        failureThreshold: 5
        httpGet:
          path: /readyz
          port: 8081
      service:
        type: ClusterIP
        port: 8443
        targetPort: metrics
      serviceAccount:
        name: ''
      env: []
      extraVolumes: []
      extraVolumeMounts: []
      extraArgs: []
      terminationGracePeriodSeconds: 10
  controller:
    deploymentMode: Knative
    gateway:
      domain: example.com
      additionalIngressDomains: []
      domainTemplate: '{{ .Name }}-{{ .Namespace }}.{{ .IngressDomain }}'
      pathTemplate: ''
      urlScheme: http
      disableIstioVirtualHost: false
      disableIngressCreation: false
      disableHTTPRouteTimeout: false
      localGateway:
        gateway: knative-serving/knative-local-gateway
        gatewayService: knative-local-gateway.istio-system.svc.cluster.local
        knativeGatewayService: ''
      ingressGateway:
        enableGatewayApi: false
        kserveGateway: kserve/kserve-ingress-gateway
        createGateway: false
        gateway: knative-serving/knative-ingress-gateway
        className: istio
commonLabels: {}
commonAnnotations: {}