apiVersion: apps/v1 kind: Deployment metadata: name: ollama-deployment namespace: ollama-ns spec: replicas: 1 selector: matchLabels: app: ollama template: metadata: labels: app: ollama spec: runtimeClassName: nvidia containers: - name: ollama image: ollama/ollama ports: - containerPort: 11434 resources: limits: nvidia.com/gpu: 2 volumeMounts: - name: ollama-volume mountPath: /root/.ollama volumes: - name: ollama-volume persistentVolumeClaim: claimName: ollama-pvc