hyyuananran comments

Repositories
Issues
Comments

Results 2 comments of


                                            hyyuananran

[Bug]: Using VLLM072 server to start the MiniCPM-O-26 service, but receiving video and audio output model inference errors.

The input of audio will still generate errors：INFO: 172.16.50.151:0 -"POST /v1/chat/completions HTTP/1.1" 500 Internal Server Error

[Usage]: I would like to know how to transfer fps and max_pixels after starting a qwen2vl-7b service using vllm?

I passed the max_pixels parameter through mm_processor_kwargs, but encountered an error: api_server.py error argument --mm_processor_kwargs invalid loads value max_pixels:798 command： python -m vllm.entrypoints.openai.api_server --host 0.0.0.0 --port 8088 --model /app/qwen2vl-7b --tensor-parrallel...