DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

📄 arXiv: 2607.05147v1 📥 PDF

作者: Xin Cheng, Xingkai Yu, Chenze Shao, Jiashi Li, Yunfan Xiong, Yi Qian, Jiaqi Zhu, Shirong Ma, Xiaokang Zhang, Jiasheng Ye, Qinyu Chen, Chengqi Deng, Jiping Yu, Damai Dai, Zhengyan Zhang, Yixuan Wei, Yixuan Tan, Wenkai Yang, Runxin Xu, Yu Wu, Zhean Xu, Xuanyu Wang, Muyang Chen, Rui Tian, Xiao Bi, Zhewen Hao, Shaoyuan Chen, Huanqi Cao, Wentao Zhang, Anyi Xu, Huishuai Zhang, Dongyan Zhao, Wenfeng Liang

分类: cs.AI, cs.CL

发布日期: 2026-07-06

💡 一句话要点

提出DSpark以解决大语言模型推理效率问题

🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)

关键词: 推测解码 大语言模型 半自回归 动态验证 高吞吐量

📋 核心要点

  1. 现有的推测解码方法在生成长序列时，因缺乏标记间依赖，导致接受率迅速下降，影响推理效率。
  2. DSpark通过半自回归架构结合并行生成与轻量验证，增强了草稿质量并优化了系统效率。
  3. 在多领域基准测试中，DSpark显著提高了接受长度，并在实际应用中加速了用户生成速度60%至85%。

📝 摘要（中文）

论文提出了一种名为DSpark的推测解码框架，通过将草稿生成与目标验证解耦，显著提升了大语言模型的推理效率。现有的并行草稿生成方法在生成长序列时，因缺乏跨标记依赖而导致接受率迅速下降。DSpark采用半自回归架构，结合并行主干与轻量级序列模块，引入块内依赖建模，优化了验证过程，动态调整验证长度，显著提高了接受的序列长度和系统吞吐量。实验结果表明，DSpark在多领域基准测试中表现优异，并在实际用户流量下有效减少了验证浪费。

🔬 方法详解

问题定义：论文要解决的是大语言模型推理中的效率问题，现有方法在生成长序列时因缺乏标记间依赖而导致接受率下降，影响系统吞吐量。

核心思路：DSpark的核心思路是结合半自回归架构与并行生成，增强草稿生成的质量，同时通过动态调整验证长度来优化系统效率。

技术框架：DSpark的整体架构包括一个并行生成主干和一个轻量级的序列模块，前者负责快速生成草稿，后者则进行验证和调整。

关键创新：DSpark的主要创新在于引入了块内依赖建模和基于置信度的动态验证调度，这与现有方法的静态验证方式形成了本质区别。

关键设计：在设计中，DSpark采用了置信度调度机制，根据每个请求的前缀生存概率和引擎特定的吞吐量特征动态调整验证长度，确保高效利用系统资源。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

在多领域的离线基准测试中，DSpark显著提高了接受长度，相较于最先进的自回归和并行生成方法，提升幅度明显。在DeepSeek-V4服务系统中，DSpark在实际用户流量下将每用户生成速度提升了60%至85%，有效减少了验证浪费。

🎯 应用场景

DSpark的研究成果在大语言模型的推理加速、实时交互系统以及高并发服务场景中具有广泛的应用潜力。其优化的验证机制和高效的生成策略能够显著提升用户体验，适用于智能客服、在线教育和内容生成等领域。

📄 摘要（原文）

Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification. While recent parallel drafters efficiently propose long token sequences in a single forward pass, they suffer from rapid acceptance decay due to a lack of inter-token dependencies. Furthermore, indiscriminately verifying these extended blocks wastes critical batch capacity on tokens with high rejection risks, severely degrading throughput in high-concurrency serving systems. We introduce DSpark, a speculative decoding framework that unifies high-throughput parallel generation with adaptive, load-aware verification. To maintain draft quality, DSpark utilizes a semi-autoregressive architecture, coupling a parallel backbone with a lightweight sequential module, to introduce intra-block dependency modeling and mitigate suffix decay. To optimize system efficiency, DSpark employs confidence-scheduled verification, dynamically tailoring the verification length for each request based on estimated prefix survival probabilities and engine-specific throughput profiles. On offline benchmarks across diverse domains, DSpark substantially improves the accepted length over state-of-the-art autoregressive and parallel drafters. When deployed within the DeepSeek-V4 serving system under live user traffic, DSpark successfully mitigates verification waste. Compared to the established production baseline (MTP-1), DSpark accelerates per-user generation speeds by 60 to 85 percent at matched throughput levels. More importantly, by preventing severe throughput degradation under strict interactivity constraints, it enables performance tiers that were previously unattainable, shifting the Pareto frontier of our serving system.