DLoop：循环式投机解码

View PDF HTML (experimental)

Abstract:Speculative decoding accelerates autoregressive generation in large language models. In each drafting stage, a lightweight draft model proposes tokens that the target model subsequently verifies. With increasingly capable draft models, we find that the target model frequently accepts all tokens produced in a drafting stage. A verification nevertheless follows each drafting stage, resulting in unnecessary target-model forward passes even when drafting could have continued. Adaptive draft length methods decide during decoding how many draft tokens precede a verification, but they raise the speedup only for autoregressive draft models. For a parallel draft model, drafting further requires target-model hidden states for draft tokens that have not been verified. We propose DLoop, a looped form of speculative decoding that adaptively performs multiple drafting stages before verification. DLoop continues drafting while the draft model remains confident and verifies all accumulated draft tokens together. Loop-aware training keeps the draft model reliable in the additional drafting stages by exposing it to its own hidden states for unverified draft tokens. By spending additional draft-model forward passes, DLoop reduces the number of target-model forward passes required for verification. Across diverse speculative decoding methods including EAGLE-3, DFlash, Domino, DSpark, and multi-token prediction modules, DLoop improves the wall-clock speedup by 5 to 41 percent while preserving lossless decoding. Code will be available at this https URL.

Comments:	22 pages
Subjects:	Computation and Language (cs.CL)
Cite as:	arXiv:2610.07659 [cs.CL]
	(or arXiv:2610.07659v2 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2610.07659 arXiv-issued DOI via DataCite

Submission history

From: Geonmo Gu [view email]
[v1] Tue, 6 Oct 2026 02:55:25 UTC (280 KB)
[v2] Wed, 21 Oct 2026 03:47:16 UTC (280 KB)