lm-sys / lm-sys/FastChat

start openai_api_server.py。The streaming interface output using OpenAI requires a long wait of 23 seconds before it can be output. But the openai interface can return results within 3 seconds. How can I solve this problem

Open
#1,594 2 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

The streaming interface output using OpenAI requires a long wait of 23 seconds before it can be output. But the openai interface can return results within 3 seconds. How can I solve this problem

Reasoning using V100 32G GPU。

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 with openai_api_server.py and inspect the streaming interface path described in the issue. Compare its time to first output with the OpenAI interface under the reported V100 32G GPU setup; the issue is resolved when the unexplained 23-second delay is identified and reduced.

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
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.