apiVersion: apps/v1
kind: Deployment
metadata:
  name: ai-model
spec:
  replicas: 2
  template:
    spec:
      containers:
        - name: model
          image: registry.example.com/ai-model:v1
          ports:
            - containerPort: 8000
          resources:
            limits:
              nvidia.com/gpu: 1
---
apiVersion: v1
kind: Service
metadata:
  name: ai-model-service
spec:
  type: LoadBalancer
  ports:
    - port: 80
      targetPort: 8000
  selector:
    app: ai-model