sgl-project/sglang

[Feature] Enable Two-Batch Overlap in Draft Models

Open

#7,892 opened on 2025年7月9日

GitHub で見る
 (5 comments) (0 reactions) (0 assignees)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, when eagle is in use, the running batch size is constrained by the draft_extend phase because low-latency dispatch constrains the number of dispatched tokens but two-batch overlap (TBO) is not supported in the draft_extend phase. Enabling TBO can double the running batch size.

Related resources

No response

コントリビューターガイド