vllm: [Performance]: Qwen2.5VL preprocessing extremely slow with large image, leading low gpu usage

Proposal to improve performance

No response

Report of performance regression

No response

Misc discussion on performance

No response

Your current environment (if you think it is necessary)

The output of `python collect_env.py`

Before submitting a new issue…

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

About this issue

  • Original URL
  • State: closed
  • Created 2 years ago
  • Comments: 15 (5 by maintainers)

Most upvoted comments

I encountered this issue before as well. I resolved it by upgrading vllm from 0.83 to 0.84.

I encountered this issue before as well. I resolved it by upgrading vllm from 0.83 to 0.84.

Thanks! let me have a try

@tenacioustommy May I ask whether you have already resolved this issue? yes I have solved it