InternLM / lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
https://lmdeploy.readthedocs.io/en/latest/
Apache License 2.0
3.13k stars 280 forks source link

Refine AsyncEngine exception handler #1789

Closed AllentDan closed 1 week ago

AllentDan commented 2 weeks ago

1788

The pytorch backend still hangs. @grimoire is going to fix it.

lvhan028 commented 2 weeks ago

After #1782 is merged, may rebase main to fix the UT