Are there any examples of ray vllm for offline local model calls?

RLlib Configure Algorithm, Training, Evaluation, Scaling
1

The environment I am in now cannot connect to the network and can only be debugged locally. I have now downloaded the model to my local machine.

apiVersion: ray.io/v1
kind: RayService
metadata:
  name: llama-3-8b
spec:
  serveConfigV2: |
    applications:
    - name: llm
      route_prefix: /
      import_path:  ray-operator.config.samples.vllm.serve:model
      deployments:
      - name: VLLMDeployment
        num_replicas: 1
        ray_actor_options:
          num_cpus: 8
          # NOTE: num_gpus is set automatically based on TENSOR_PARALLELISM
      runtime_env:
        working_dir: "https://github.com/ray-project/kuberay/archive/master.zip"
        pip: ["vllm==0.6.1.post2"]
        env_vars:
          MODEL_ID: "meta-llama/Meta-Llama-3-8B-Instruct"
          TENSOR_PARALLELISM: "2"
          PIPELINE_PARALLELISM: "1"

I tried changing MODEL_ID to the local path, but I still cannot use curl.

https://docs.ray.io/en/latest/cluster/kubernetes/examples/vllm-rayservice.html#create-a-kubernetes-secret-containing-your-hugging-face-access-token

2 
status:
  activeServiceStatus:
    dashboardStatus: {}
    rayClusterStatus:
      availableWorkerReplicas: 1
      desiredWorkerReplicas: 1
      endpoints:
        client: "10001"
        dashboard: "8265"
        dashboard-agent: "52365"
        gcs-server: "6379"
        metrics: "8080"
        serve: "8000"
      head:
        podIP: 192.168.206.50
        serviceIP: 10.109.80.209
      lastUpdateTime: "2025-02-13T06:32:48Z"
      maxWorkerReplicas: 24
      observedGeneration: 1
      state: ready
  observedGeneration: 1
  pendingServiceStatus:
    applicationStatuses:
      deepseek:
        healthLastUpdateTime: "2025-02-13T06:32:48Z"
        lastUpdateTime: "2025-02-13T06:47:34Z"
        message: |
          Deploying app 'deepseek' failed with exception:
          Traceback (most recent call last):
            File "/home/ray/anaconda3/lib/python3.10/site-packages/ray/serve/_private/application_state.py", line 1152, in build_serve_application
              import_attr(import_path), args
            File "/home/ray/anaconda3/lib/python3.10/site-packages/ray/_private/utils.py", line 1191, in import_attr
              module = importlib.import_module(module_name)
            File "/home/ray/anaconda3/lib/python3.10/importlib/__init__.py", line 126, in import_module
              return _bootstrap._gcd_import(name[level:], package, level)
            File "<frozen importlib._bootstrap>", line 1050, in _gcd_import
            File "<frozen importlib._bootstrap>", line 1027, in _find_and_load
            File "<frozen importlib._bootstrap>", line 992, in _find_and_load_unlocked
            File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
            File "<frozen importlib._bootstrap>", line 1050, in _gcd_import
            File "<frozen importlib._bootstrap>", line 1027, in _find_and_load
            File "<frozen importlib._bootstrap>", line 992, in _find_and_load_unlocked
            File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
            File "<frozen importlib._bootstrap>", line 1050, in _gcd_import
            File "<frozen importlib._bootstrap>", line 1027, in _find_and_load
            File "<frozen importlib._bootstrap>", line 992, in _find_and_load_unlocked
            File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
            File "<frozen importlib._bootstrap>", line 1050, in _gcd_import
            File "<frozen importlib._bootstrap>", line 1027, in _find_and_load
            File "<frozen importlib._bootstrap>", line 992, in _find_and_load_unlocked
            File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
            File "<frozen importlib._bootstrap>", line 1050, in _gcd_import
            File "<frozen importlib._bootstrap>", line 1027, in _find_and_load
            File "<frozen importlib._bootstrap>", line 1004, in _find_and_load_unlocked
          ModuleNotFoundError: No module named 'ray-operator'
        status: DEPLOY_FAILED
    dashboardStatus:
      healthLastUpdateTime: "2025-02-13T06:47:34Z"
      isHealthy: true
      lastUpdateTime: "2025-02-13T06:47:34Z"
    rayClusterName: deepseek-r1-671b-raycluster-8jhvk
    rayClusterStatus:
      head: {}
  serviceStatus: WaitForServeDeploymentReady

Is there anyone who can help? Thank you very much. Wish you happy every day.
How to configure import_path and working_dir? I have put everything locally. How should I modify them?