DSpark：基于置信度调度的推测性解码与半自回归生成

摘要

推测解码通过将草稿生成与目标验证解耦，加速了大语言模型（LLM）的推理过程。尽管近期提出的并行草稿生成器能够在单次前向传播中高效生成较长的Token序列，但由于缺乏Token间的依赖关系，它们会遭遇快速接受率衰减的问题。此外，不加区分地验证这些扩展块，会将宝贵的批处理容量浪费在高拒绝风险的Token上，从而严重降低高并发服务系统的吞吐量。本文提出DSpark——一种将高吞吐并行生成与自适应、负载感知的验证统一起来的推测解码框架。为了保持草稿质量，DSpark采用半自回归架构，将并行主干网络与轻量级顺序模块相结合，引入块内依赖建模以缓解后缀衰减问题。为了优化系统效率，DSpark采用置信度调度验证，根据估计的前缀存活概率和引擎特定的吞吐量特征，动态调整每个请求的验证长度。在跨多个领域的离线基准测试中，DSpark相较于最先进的回归式和并行式草稿生成器，显著提升了接受长度。在DeepSeek-V4服务系统中部署后，面对真实用户流量，DSpark成功缓解了验证浪费问题。与现有生产基线（MTP-1）相比，在相同吞吐量水平下，DSpark将每个用户的生成速度提升了60%至85%。更重要的是，通过防止在严格的交互性约束下出现的严重吞吐量下降，DSpark实现了此前无法达到的性能等级，推动了服务系统的帕累托前沿边界。

English

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.