agora/contoso_motors/charts/ovms/templates/modelserver.yaml

apiVersion: intel.com/v1alpha1
kind: ModelServer
metadata:
  name: ovms
  namespace: {{ .Release.Namespace }}
  labels:
    app.kubernetes.io/name: "ovms"
    app.kubernetes.io/managed-by: {{ .Release.Service }}
    app.kubernetes.io/instance: {{ .Release.Name | quote }}
    app.kubernetes.io/version: {{ .Chart.AppVersion }}
    helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version | replace "+" "_" }}
  annotations:
    "helm.sh/hook": pre-install
    "helm.sh/hook-weight": "10"
spec:
  image_name: openvino/model_server:latest
  deployment_parameters:
    replicas: {{ .Values.replicaCount }}
    openshift_service_mesh: false
    resources:
      limits:
        cpu: "1"
        memory: "8192Mi"
      requests:
        cpu: "1"
        memory: "8192Mi"
  models_settings:
    single_model_mode: false
    config_configmap_name: "ovms-config"
    config_path: ""
    model_name: ""
    model_path: ""
    nireq: 0
    plugin_config: '{"CPU_THROUGHPUT_STREAMS":"1"}'
    batch_size: ""
    shape: ""
    model_version_policy: "{\"latest\": {\"num_versions\":1 }}"
    layout: ""
    target_device: "CPU"
    is_stateful: false
    idle_sequence_cleanup: false
    low_latency_transformation: true
    max_sequence_number: 0
  server_settings:
    file_system_poll_wait_seconds: 0
    sequence_cleaner_poll_wait_minutes: 0
    log_level: "INFO"
  service_parameters:
    grpc_port: 8080
    rest_port: 8081
    service_type: LoadBalancer
  models_repository:
    storage_type: "cluster"
    models_volume_claim : "ovms-pvc"