docker run -d --name tf-serving \
  -p 8500:8500 -p 8501:8501 \
  -v /data/models:/models \
  -e MODEL_NAME=my_model \
  docker.io/tensorflow/serving:latest

docker run -d --name tf-serving \
  --gpus all --restart unless-stopped \
  -p 8500:8500 -p 8501:8501 \
  -v /data/models:/models \
  -e MODEL_NAME=my_model \
  docker.io/tensorflow/serving:2.15.0

apiVersion: apps/v1
kind: Deployment
metadata:
  name: tf-serving
spec:
  replicas: 2
  selector:
    matchLabels:
      app: tf-serving
  template:
    metadata:
      labels:
        app: tf-serving
    spec:
      containers:
        - name: serving
          image: docker.io/tensorflow/serving:2.15.0
          ports:
            - containerPort: 8500
            - containerPort: 8501
          env:
            - name: MODEL_NAME
              value: my_model
          volumeMounts:
            - name: models
              mountPath: /models
      volumes:
        - name: models
          persistentVolumeClaim:
            claimName: tf-models
---
apiVersion: v1
kind: Service
metadata:
  name: tf-serving
spec:
  selector:
    app: tf-serving
  ports:
    - port: 8500
      targetPort: 8500
    - port: 8501
      targetPort: 8501