When Parallel Drafter Meets Parallel Speculative Decoding

2026-09-23

AI Summary

本文提出DPara框架，通过并行化骨干网络与验证过程重叠，解决了现有方法在猜测错误时需回退到串行起草的问题，实现在多个基准测试中显著加速解码。

Abstract

DSpark-style parallel drafters have made speculative decoding highly effective, yet their draft phase remains serialized on the critical path of every round. Parallel speculative decoding (PSD) overlaps drafting with verification, yet existing methods must guess the accepted prefix and bonus token in advance: a wrong guess reverts the whole batch to serial drafting. We present DPara, a PSD framework that reuses effective parallel drafters yet guarantees backbone--verification overlap in every round, thereby eliminating this probabilistic fallback altogether. While the target verifies, DPara's diffusion backbone precomputes draft representations for every acceptance boundary with the bonus left unspecified; a lightweight autoregressive head then combines the revealed verification outcome with the matching precomputed representation to emit the next round's draft tokens almost instantly---fully parallelizing the dominant backbone forward with verification and leaving only the negligible head cost serial. Experiments on Qwen3-8B and Qwen3-14B across seven math, coding, and chat benchmarks show that DPara achieves average speedups of $3.21\times$ and $3.52\times$ over autoregressive decoding, surpassing the strongest serial and parallel speculative decoding baselines alike.

Problem

• Parallel Speculative Decoding
• Serialized Drafting
• Speculative Decoding

Innovation

• Parallel Speculative Decoding
• Backbone-Verification Overlap
• Precomputed Representations
• Lightweight Autoregressive Head