lm-sys / lm-sys/FastChat

Speed up inferencing

Open
#2,347 1 comment 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

Hi,

I have been able to run the comolete pipeline but the inferencing speed is very slow. It is around 1-2 tokens per sec . Is there any way to increase the inferencing speed?
Maybe with multiple GPUs or anything like that?

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

The issue names no files, tests, or entry points. Reproduce the complete pipeline and measure the reported 1–2 tokens/sec baseline first, then identify the inference bottleneck and define done as a measured speed improvement with any multi-GPU behavior documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.