An error occurred when starting vLLM sampling:
(dev) hrq@gemini-k8s-node01-wxyd:~/project/UPFT$ python inference/vllm_inference.py
INFO 05-28 17:07:07 [__init__.py:239] Automatically detected platform cuda.
Traceback (most recent call last):
File "/home/hrq/project/UPFT/inference/vllm_inference.py", line 21, in <module>
from utils.utils import *
ModuleNotFoundError: No module named 'utils.utils'; 'utils' is not a package