sgl-project/sglang

[Feature] Enable EPLB in Draft Models

Open

#7,893 opened on 2025年7月9日

GitHub で見る
 (6 comments) (0 reactions) (1 assignee)Python (6,216 forks)auto 404
good first issue

Repository metrics

Stars
 (28,442 stars)
PR merge metrics
 (平均マージ 2d 1h) (30d で 1,000 merged PRs)

説明

Checklist

Motivation

Currently, EPLB is not supported in draft models, which constrains the parallelism size. For example, with EPLB, we can set the EP size as 72/144 for the DeepSeek model as it has 288 experts in total. However, these parallelism settings cannot be adopted when MTP is enabled as the draft model as has 256 experts.

Related resources

No response

コントリビューターガイド