投机解码让本地大模型推理提速数倍，草稿模型接受率是关键指标，无需额外硬件成本即可优化生成速度。
Article URL: https://vettedconsumer.com/speculative-decoding-explained-the-free-speed-toggle-your-local-llm-is-probably-not-using/ Comments URL: https…
提出DeLS-Spec方法，解耦长短上下文实现并行投机解码，大幅提升大模型推理效率。
arXiv:2607.07409v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by drafting multiple tokens and verifying them in paral…
面向CPU受限场景的自适应投机解码框架，多策略编排让LLM推理更高效。
arXiv:2607.03876v1 Announce Type: new Abstract: With the rise of small quantized GGUF-based language models and their increasing use for on-device inf…
深度揭秘DeepSeek最新研究：投机解码如何大幅加速LLM推理，论文全文在此。
Article URL: https://github.com/deepseek-ai/DeepSpec/blob/main/DSpark_paper.pdf Comments URL: https://news.ycombinator.com/item?id=48696585 Points: 52…
JetSpec用并行树解码实现最高9.64倍无损LLM推理加速，吞吐可达1000TPS，值得关注。
Article URL: https://haoailab.com/blogs/parallel-tree-decoding/ Comments URL: https://news.ycombinator.com/item?id=48680042 Points: 4 # Comments: 1
投机解码新突破：提出LK损失函数直接优化接受率，加速大模型推理生成
arXiv:2602.23881v2 Announce Type: replace Abstract: Speculative decoding accelerates autoregressive large language model (LLM) inference by using a li…
自适应投机解码新方法AdaSD，大幅提升大模型推理效率，值得关注的最新论文成果
arXiv:2512.11280v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, bu…
针对大模型推理中投机解码的验证瓶颈，提出层次化投机解码方法，显著提升推理速度。
arXiv:2510.01336v2 Announce Type: replace-cross Abstract: Speculative decoding accelerates LLM inference by using a smaller draft model to speculate t…
投机解码将小模型驻留DRAM，突破手机LLM推理的内存瓶颈，实现高效闪存大模型推理
arXiv:2605.16786v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly needed for interactive mobile applications, but high-qua…
强化学习驱动自适应投机训练，统一训练与推理流程，消除部署延迟，加速大模型服务。
arXiv:2602.06932v4 Announce Type: replace Abstract: Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentan…