kserve/docs/samples/llmisvc/multi-gpu-vendor/llm-inference-service-qwen2-7b-nvidia-with-scheduler.yaml

apiVersion: serving.kserve.io/v1alpha1
kind: LLMInferenceService
metadata:
  name: qwen2-7b-instruct-nvidia
spec:
  model:
    uri: hf://Qwen/Qwen2.5-7B-Instruct
    name: Qwen/Qwen2.5-7B-Instruct
  replicas: 3
  router:
    scheduler: { }
    route: { }
    gateway: { }
  template:
    containers:
      - name: main
        resources:
          limits:
            cpu: '4'
            memory: 32Gi
            nvidia.com/gpu: "1"
          requests:
            cpu: '2'
            memory: 16Gi
            nvidia.com/gpu: "1"