lm-sys / lm-sys/FastChat

vllm_worker will be hung after chating a while

Open
#3,003 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
39.5k
Forks
4.8k
PR merge metrics
No merged PRs in 30d

Description

After vllm_worker for fastchat is started and chat for a while, the message responded by fastchat will be hung and then the screen showed "NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE".

image

The log of vllm_worker shows request is aborted.
Don't know why.
Does anyone knows the root cause of this issue or how to resolve it?

The web server log:
image

The vllm worker log:
image

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the hang after sustained chatting with the vllm_worker for FastChat, then inspect the web server and vllm worker logs around the aborted request. Done would mean identifying the cause of the aborted request and preventing the worker from hanging or returning the high-traffic network error.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
api, backend
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.