sgl-project/sglang

[Feature] Enable Two-Batch Overlap in Draft Models

Open

#7,892 创建于 2025年7月9日

在 GitHub 查看
 (5 评论) (0 反应) (0 负责人)Python (6,216 fork)auto 404
good first issue

仓库指标

Star
 (28,442 star)
PR 合并指标
 (平均合并 2天 1小时) (30 天内合并 1,000 个 PR)

描述

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

贡献者指南