# ChainFlow: 用于推测解码的少步潜在流匹配

> 全文为英语

**Published:** 2026年11月9日
**Author:** Selim Aktas, Yusuf Erdem Erdem, Ahmed Zeer, Himmet Toprak Kesgin, Muzaffer Kaan Yuce, Mehmet Fatih Amasyali
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/chainflow-few-step-latent-flow-matching-for-speculative-decoding

arXiv:2611.08669v1 公告类型: 新 摘要: 推测解码已成为加速LLM推理的标准方法: 轻量级起草器提出令牌, 目标模型在一次并行传递中验证。现有起草器面临限制其加速比的权衡:…

arXiv:2611.08669v1 Announce Type: new Abstract: Speculative decoding has become a standard way to accelerate LLM inference: a lightweight drafter proposes tokens that the target verifies in one parallel pass. Existing drafters face trade-offs that limits their speedups: autoregressive drafters generate tokens one at a time, so drafting cost grows with draft length, while diffusion drafters generate tokens in parallel but predict each position independently, ignoring inter-token dependencies. We introduce ChainFlow, a new speculative decoding paradigm and the first flow-matching drafter conditioned on the target's hidden states. ChainFlow treats drafting as a short transport over hidden states, needing one or two flow steps instead of the many denoising steps of generation from noise. A variational autoencoder compresses these states so drafting cost barely grows with target size, lightweight feedback heads restore inter-token dependencies, and tree drafting raises acceptance. On Qwen3.5 models, at matched drafter size and training data, ChainFlow outperforms EAGLE-3 and DFlash in vLLM by 39% and 11%, respectively. These gains further widen as drafters are adapted to new languages sequentially. Our ablations cover drafter design and concurrent serving, and we open-source our code and drafter models.

---

*内容来自原始来源： [arXiv — cs.AI](https://arxiv.org/abs/2611.08669). 查看原文.*

**标签：** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*