arXiv cs.CL· Roy Eisenstadt, Harel Lidar, Tal Gonen, Omer Luxembourg, Itamar Zimerman, Lior Wolf, Eli David, Ilan Naiman·· 6 天前AI 评分24
DCOCO：为推测解码的并行草稿恢复上下文依赖
Contextual Correction of Parallel Draftsfor Speculative Decoding
AI 导读
DCOCO（DFlash Contextual Corrector）是一种轻量机制，在保留并行草稿的同时恢复草稿块内被丢失的 token 依赖，通过并行评估相邻位置多个候选 token 的上下文兼容性来完成选择。在四个验证器骨干和十个基准上，DCOCO 在所有配置中取得最高平均吞吐，较原始解码最高加速 6.6x；在 4-32 并发请求下比最强竞争方法高 6-23%。
正文 · 原文
Abstract:Speculative decoding accelerates large language model inference by using a lightweight drafter to propose multiple tokens that are subsequently verified in parallel by the target model. Recent diffusion-based drafters make this paradigm particularly attractive: deep attention-based neural backbones provide strong predictions, while drafting multiple future positions in parallel avoids the sequential cost of autoregressive generation. This parallelism, however, comes at a cost. Tokens within a draft block are predicted without access to the realized identities of preceding draft tokens, removing intra-block dependencies that would naturally be available under autoregressive generation. We introduce DCOCO (DFlash Contextual Corrector), a lightweight mechanism that restores these dependencies while preserving parallel drafting. Rather than committing to each position's top prediction, DCOCO retains multiple candidate tokens and evaluates their contextual compatibility across adjacent draft positions in parallel, enabling contextually informed token selection at low additional cost. Across four verifier backbones and ten benchmarks, DCOCO achieves the highest average throughput in every evaluated configuration, spanning greedy and stochastic decoding with and without extended reasoning, with speedups of up to 6.6x over vanilla decoding. Its advantage persists under concurrent serving: DCOCO outperforms the strongest competing method by 6-23% across 4-32 concurrent requests, while other sequential correctors fall below uncorrected DFlash at these loads. These results demonstrate that recovering intra-block dependencies through parallel contextual scoring delivers consistent acceleration across decoding regimes and serving loads.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.12570 [cs.CL] |
| (or arXiv:2610.12570v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12570 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Roy Eisenstadt [view email]
[v1]
Thu, 8 Oct 2026 18:01:03 UTC (236 KB)
来源：arXiv cs.CL · arxiv.org