Products & Apps

SpecForge v0.3.0 released with unified decoupled and colocated speculative decoding stack, open SpecBundle draft models

Original title:Blog SpecForge v0.3.0: a Unified Disaggregated and Colocated Speculative Decoding Stack, and New Open SpecBundle Draft Models When we first released SpecForge, a training job owned both the frozen target model and the draft model being optimized. This made EAGLE3 draft-model training practical and directly compatible with SG... The SpecForge Team

AI summary

SpecForge v0.3.0 separates target model inference from draft model training, supports speculative decoding algorithms including EAGLE3, EAGLE3.1, P-EAGLE, DFlash, Domino and DSpark, and unifies online, offline and decoupled workflows.

Key Takeaways

  • SpecForge v0.
  • 0 separates target model inference from draft model training,supports speculative decoding…
  • 1,P-EAGLE,DFlash,Domino and DSpark,and unifies online,offline and decoupled workflows.

Quick Facts

Published
Updated
Source
LMSYS Blog
Category
Products & Apps
AI score
72
Read the original Read the full article at the original source
Why it matters

将目标模型推理与草稿模型训练分离,让两种工作负载可独立扩缩,改变了投机解码训练中资源配比必须硬编码的旧模式,资源规划可按模型和序列长度灵活调整。

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: SpecForge v0.3.0 released with unified decoupled and colocated speculative decoding stack, open SpecBundle draft models. August 4, 2026. https://new.nat6.net/en/news/cmseyfjcz1au8ro2enx0b7os6/

View all →