DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
打开互动全文版（逐段中英对照 + 图/公式 + 论文问答）→推测解码通过将草稿生成与目标验证解耦来加速大语言模型推理。虽然最近的并行草稿器能在单次前向传播中高效生成长令牌序列，但由于缺乏令牌间依赖关系，其接受率会迅速下降。此外，不加区分地验证这些扩展块会浪费关键批处理容量在高拒绝风险的令牌上，严重降低高并发服务系统的吞吐量。我们提出了 DSpark，一个统一高吞吐并行生成与自适应、负载感知验证的推测解码框架。为保持草稿质量，DSpark 采用半自回归架构——将并行主干与轻量级顺序模块耦合——引入块内依赖建模并缓解后缀衰减。为优化系统效率，DSpark 采用置信度调度验证，基于估计的前缀存活概率和引擎特定的吞吐量配置文件，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 在接受的令牌长度上显著优于最先进的自回归和并行草稿器。当部署在 DeepSeek-V4 服务系统中并面对实时用户流量时，DSpark 成功缓解了验证浪费。与已建立的生产基线（MTP-1）相比，DSpark 在匹配吞吐量水平下将每用户生成速度提升了 60%-85%。更重要的是，通过防止在严格交互性约束下吞吐量严重下降，它实现了以前无法达到的性能层级，改变了服务系统的帕累托前沿。为促进社区进步，我们开源了 DSpark 检查点以及 DeepSpec，一个用于推测解码的算法驱动训练仓库。
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%–85% 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. To facilitate community progress, we open-source the DSpark checkpoints alongside DeepSpec, an algorithm-driven training repository for speculative decoding.