NameError: name 'vllm_ChatCompletionRequest' is not defined

[mitrasarthak20]

VLLM package is not getting installed incase docker_build with ipex-llm .

Using User Model: llama-2-7b-chat-hf
[WARNING 2025-05-01 18:01:55,989] router_app.py: 83 VLLM package is not installed
Traceback (most recent call last):
File "/opt/conda/bin/llm_on_ray-serve", line 5, in
from llm_on_ray.inference.serve import main
File "/root/llm-on-ray/llm_on_ray/inference/serve.py", line 21, in
from llm_on_ray.inference.api_server_openai import openai_serve_run
File "/root/llm-on-ray/llm_on_ray/inference/api_server_openai.py", line 38, in
from llm_on_ray.inference.api_openai_backend.router_app import Router, router_app
File "/root/llm-on-ray/llm_on_ray/inference/api_openai_backend/router_app.py", line 256, in
class Router:
File "/root/llm-on-ray/llm_on_ray/inference/api_openai_backend/router_app.py", line 366, in Router
body: Union[ChatCompletionRequest, vllm_ChatCompletionRequest],
NameError: name 'vllm_ChatCompletionRequest' is not defined