sgl-project/sglang

[Feature] Enable Two-Batch Overlap in Draft Models

Open

#7,892 opened on Jul 9, 2025

View on GitHub
 (5 comments) (0 reactions) (0 assignees)Python (6,216 forks)auto 404
good first issue

Repository metrics

Stars
 (28,442 stars)
PR merge metrics
 (Avg merge 2d 1h) (1,000 merged PRs in 30d)

Description

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

Contributor guide

Research direction
Investigate the draft extend phase and implement two batch overlap to increase running batch size.
Tech stack
python
Domain
backend
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
Python
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
50