lm-sys/FastChat

[Feature Request] Add a ctranslate2 model worker

Open

#2,133 opened on 2023年8月1日

GitHub で見る
 (2 comments) (1 reaction) (1 assignee)Python (38,959 stars) (4,736 forks)batch import
enhancementgood first issue

説明

According to some recent analysis on twitter, CTranslate2 can serve LLMs a little faster than vLLM and (maybe?) with a small quality increase. At least for Llama 2.

This could either be a a model worker that's added directly to fastchat OR a doc with extensive documentation on how to write a custom model worker (with mostly working \ implementation code) that anyone can use in their own project. The second option might be best so that people can expand FastChat with custom model workers without having to change the base project too much.

If this is appealing I can get to it at some point.

コントリビューターガイド

技術スタック
python
領域
backendmachine learning
Issue 種別
feature
難度新しい貢献者にとっての実装難度です。1 は非常に小さな変更、5 は専門的な作業です。
3
推定時間経験ある貢献者が調査、実装、テスト、pull request 準備にかけるおおよその時間範囲です。
3-5 days
活動状況Issue が今どれだけ取り組みやすいかを示します。新しい、活発、古い、ブロック中、またはメンテナー入力待ちなどです。
blocked
明確さ期待される変更、受け入れ条件、次の手順がどれだけ明確かを示します。
clear
前提条件
PythonFastChat codebaseLLM serving conceptsCTranslate2 library
初心者向け度初回貢献者にどれだけ取り組みやすいかを 1-100 で推定したスコアです。
25
調査方針
Start by examining existing model workers in FastChat, such as those for vLLM, to understand the pattern and integration points. Look at files like 'fastchat/serve/model worker.py' and any associated configurations. Review the conversation in this issue for any additional requirements or direction from maintainers. Investigate the CTranslate2 Python library's documentation and example code to plan the integration. Since the issue has an assignee, check if they have any open branches or related commits.