apiVersion: "serving.kserve.io/v1beta1"
kind: "InferenceService"
metadata:
  name: "qwen-llm"
  namespace: kserve
spec:
  predictor:
    model:
      modelFormat:
        name: huggingface
      args:
        - --model_name=qwen
      storageUri: "hf://Qwen/Qwen2.5-0.5B-Instruct"
      resources:
        limits:
          cpu: "2"
          memory: 6Gi
          nvidia.com/gpu: "1"
        requests:
          cpu: "1"
          memory: 4Gi
          nvidia.com/gpu: "1"