---
kind: Service
apiVersion: v1
metadata:
  name: your_service_name
  labels:
    app: your_service_name
spec:
  ports:
  - name: preds
    port: 8080
    targetPort: ts 
  - name: mdl
    port: 8081
    targetPort: ts-management
  type: LoadBalancer
  selector:
    app: your_service_name
---
kind: Deployment
apiVersion: apps/v1
metadata:
  name: your_service_name
  labels:
    app: your_service_name
spec:
  replicas: 1
  selector:
    matchLabels:
      app: your_service_name
  template:
    metadata:
      labels:
        app: your_service_name
    spec:
      containers:
      - name: your_service_name
        image: "pytorch/torchserve:latest-gpu"
        ports:
        - name: ts
          containerPort: 8080
        - name: ts-management
          containerPort: 8081
        imagePullPolicy: IfNotPresent
        resources:
          limits:
            cpu: 4
            memory: 4Gi
            nvidia.com/gpu: 1
          requests:
            cpu: "1"
            memory: 1Gi