apiVersion: apps/v1
kind: Deployment
metadata:
  name: ollama
  namespace: ollama
  labels:
    app: ollama
spec:
  replicas: 0
  strategy:
    type: Recreate
  selector:
    matchLabels:
      app: ollama
  template:
    metadata:
      labels:
        app: ollama
    spec:
      containers:
        - name: ollama
          image: ollama/ollama:latest
          ports:
            - containerPort: 11434
          env:
            - name: NVIDIA_VISIBLE_DEVICES
              value: all
          volumeMounts:
            - name: models
              mountPath: /root/.ollama
          resources:
            requests:
              memory: 2Gi
              cpu: 500m
            limits:
              memory: 8Gi
              cpu: "4"
      volumes:
        - name: models
          persistentVolumeClaim:
            claimName: ollama-models
---
apiVersion: v1
kind: Service
metadata:
  name: ollama
  namespace: ollama
spec:
  selector:
    app: ollama
  ports:
    - port: 11434
      targetPort: 11434
      nodePort: 31434
  type: NodePort