lm-sys / lm-sys/FastChat

Does fastchat model worker support expose some metrics?

Open
#2,258 1 comment 1 reaction 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

Such as real time tokens per second or similar metrics. We want to measure the performance based on these.

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 inspecting the FastChat model worker entry point and its existing request or generation reporting. Clarify which metrics are required, especially real-time tokens per second, how they should be exposed, and how consumers will measure performance; the work is done when those metrics are available during model serving.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, observability
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.