lm-sys / lm-sys/FastChat

Worker do not stop even if the api request was cancelled

Open
#2,163 4 comments 2 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

Worker do not stop even if the api request was cancelled

I'm using LangChain + OpenAI API simulated by FastChat, running lmsys_vicuna-13b-v1.5-16k model.

step 1, send a request to api server;
step 2, the worker started to work. But in case user want to cancel this request;
The worker will not stop the job.

Need solve this problem as the old job still consuming huge resources and new job could not be processed.

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 tracing how API request cancellation reaches the worker lifecycle and identify where the running job continues after the client disconnects. Verify that cancellation stops the existing worker, releases its resources, and allows a subsequent request to be processed.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, 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.