James

Is this feature not supported yet? I tested it using the vLLM image v0.7.2 and encountered several bugs: ``` 2025-02-07T08:33:07.776941692Z ERROR 02-07 00:33:07 engine.py:389] File "/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/engine.py", line 380, in run_mp_engine...

Hi everyone, I’m encountering the following error when trying to run the image vllm/vllm-openai:v0.6.6.post1 on a node equipped with 8x H100 SMX GPUs: ``` ValueError: Error in model execution (input...

Please support!!!! Thanks for Team!