LMSYS Blog·· 2026-08-04精选AI 评分72
SpecForge v0.3.0 发布：统一解耦与共置投机解码栈，新增开放 SpecBundle 草稿模型
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 导读
SpecForge v0.3.0 将目标模型推理与草稿模型训练分离，支持 EAGLE3、EAGLE3.1、P-EAGLE、DFlash、Domino、DSpark 等多种投机解码算法，并统一在线、离线与解耦工作流。
推荐理由
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。
来源：LMSYS Blog · lmsys.org