按年被提到
20262026 · 2 次2026
大模型与语言模型›量化、解码与分词·arXiv:2607.05147 · cs.AI

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

Xin Cheng, Xingkai Yu, Chenze Shao, Jiashi Li, Yunfan Xiong, Yi Qian, Jiaqi Zhu, Shirong Ma, Xiaokang Zhang, Jiasheng Ye, Qinyu Chen, Chengqi Deng 等 33 人 · 2026
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2026-07-13 · 最近 2026-08-14
2不同的人
2活跃月份
2讨论串
4被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论kamranjon · 2026-07

“Some of the most exciting engineering work is happening in the DS4 repo - and I'm watching it almost like a sports game. When the DSpark paper came out[1] the next day we had folks attempting to implement, working together, validating their failures. Eventually their work being synthesized into a PR[1] that admits performance is not ideal. Something anti…”

Control the Ideas, Not the Code原评论 ↗
评论petu · 2026-08

“Deepseek's DSpark does dynamically adjust speculated token count per user/completion. https://arxiv.org/abs/2607.05147 But they do so to maximise total throughput, I don't think there's reason to do that for batch=1.”

Qwen 3.8 27B is out: open weights, best local dense model yet原评论 ↗