20260706:新增一些文章
This commit is contained in:
30
concepts/MTP.md
Normal file
30
concepts/MTP.md
Normal file
@@ -0,0 +1,30 @@
|
||||
---
|
||||
title: "MTP (Multi-Token Prediction)"
|
||||
created: 2026-06-28
|
||||
updated: 2026-06-28
|
||||
type: concept
|
||||
tags: [speculative-decoding, autoregressive-drafting, deepseek, production]
|
||||
sources: [DSpark]
|
||||
---
|
||||
# Multi-Token Prediction (MTP)
|
||||
|
||||
MTP(Multi-Token Prediction)是 DeepSeek 系列模型(DeepSeek-V2, V3, V4)内置的[[autoregressive-drafting|自回归草稿(Autoregressive Drafting)]]机制,作为生产环境中的投机解码草稿器。
|
||||
|
||||
## 变体
|
||||
|
||||
- **MTP-1**:单 token 草稿模式,DSpark 论文中的生产基线。历史上被维持是因为静态多 token 草稿器(MTP-3/5)在高并发下会因过度验证开销严格降低总吞吐量
|
||||
- **MTP-3/5**:多 token 草稿模式
|
||||
|
||||
## 在 DSpark 部署中的角色
|
||||
|
||||
DSpark 在 DeepSeek-V4 发布两周后取代了 MTP-1 成为生产系统。DSpark-5(最大草稿长度 $\gamma=5$)相比 MTP-1:
|
||||
- V4-Flash:在匹配吞吐量下,每用户生成速度提升 60%-85%
|
||||
- V4-Pro:提升 57%-78%
|
||||
|
||||
关键突破:DSpark 通过[[confidence-scheduled-verification|置信度调度验证(Confidence-Scheduled Verification)]]安全解锁了大草稿块的性能潜力,解决了 MTP-3/5 因固定长度验证导致的吞吐量退化问题。
|
||||
|
||||
## 参考
|
||||
|
||||
- [[DSpark]]
|
||||
- [[autoregressive-drafting|自回归草稿(Autoregressive Drafting)]]
|
||||
- [[Eagle3]]
|
||||
Reference in New Issue
Block a user