kserve/docs/samples/llmisvc/managed-dra/llm-inference-service-managed-dra-minimal.yaml

apiVersion: serving.kserve.io/v1alpha2
kind: LLMInferenceService
metadata:
  name: qwen2-7b-instruct-dra-minimal
  # Minimal Managed DRA: request one device of the given DeviceClass.
  annotations:
    serving.kserve.io/exp-dra-device-class: gpu.nvidia.com
spec:
  model:
    uri: hf://Qwen/Qwen2.5-7B-Instruct
    name: Qwen/Qwen2.5-7B-Instruct
  replicas: 1
  router:
    scheduler: { }
    route: { }
    gateway: { }
  template:
    containers:
      - name: main
        resources:
          limits:
            cpu: '4'
            memory: 32Gi
          requests:
            cpu: '2'
            memory: 16Gi
        livenessProbe:
          httpGet:
            path: /health
            port: 8000
            scheme: HTTPS
          initialDelaySeconds: 120
          periodSeconds: 30
          timeoutSeconds: 30
          failureThreshold: 5