sgl-project/sglang

[Feature] Enable EPLB in Draft Models

Open

#7,893 建立於 2025年7月9日

在 GitHub 查看
 (6 留言) (0 反應) (1 負責人)Python (6,216 fork)auto 404
good first issue

倉庫指標

Star
 (28,442 star)
PR 合併指標
 (平均合併 2天 1小時) (30 天內合併 1,000 個 PR)

描述

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

貢獻者指南