TF Serving on k8s with GPUs example

spec:
  replicas: 1
  template:
    metadata:
      labels:
        app: inception-server
    spec:
      containers:
      - name: inception-container
        image: gcr.io/vishnuk-cloud/tf-serving-gpu
        resources:
          limits:
            nvidia.com/gpu: 1
        command:
          - /usr/local/bin/tensorflow_model_server
        args:
          - --port=9000
          - --model_name=inception
          - --model_base_path=gs://kubeflow-models/inception
        ports:
        - containerPort: 9000
---
apiVersion: v1
kind: Service
metadata:
  labels:
    run: inception-service
  name: inception-service
spec:
  ports:
  - port: 9000
    targetPort: 9000
  selector:
    app: inception-server
  type: LoadBalancer