[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-cd82f869-d4a7-45b7-95ce-b66051e9d933":3},{"id":4,"title":5,"summary":6,"original_url":7,"source_id":8,"tags":9,"published_at":23,"created_at":24,"modified_at":25,"is_published":26,"publish_type":27,"image_url":13,"view_count":28},"cd82f869-d4a7-45b7-95ce-b66051e9d933","BlockPilot：实例自适应策略学习让扩散式投机解码再下一城,Qwen3-4B 上首破 4.20× 加速","扩散式投机解码(diffusion-based speculative decoding)是目前 LLM 推理加速最前沿的方向之一:通过块级扩散在单次前向中并行生成多个候选 token,再用目标模型一次性验证,实现无损加速。但现有方法普遍采用固定推理块大小,默认最优策略对所有输入一致,严重限制了进一步提速的空间。\n\nBlockPilot 的关键观察指出:最优块大小在不同样本间差异显著,而且这些值呈现围绕训练块大小的局部集中结构,使块大小选择变成一个低维、可学习的决策问题。基于此,作者把块大小选择形式化为一个轻量级策略学习问题,提出实例自适应决策机制:只需在 prefill 之后用 prefill 表示预测一次最优块大小,然后在整段解码过程中保持不变。这种设计使 BlockPilot 与现有扩散投机解码系统即插即用,不需要修改目标模型,base LLM 完全冻结,新增训练参数低于 0.05%。\n\n在 Qwen3-4B 温度 T=1 设置下,BlockPilot 取得 5.92 的接受长度与 4.20× 端到端加速,显著超越现有 SOTA 扩散投机解码基线。这一工作的意义在于把「样本难度异质性」明确纳入投机解码设计空间,打破了此前固定块大小的隐含假设,也为长序列、Agentic 工作流等块大小天然多变的场景打开了动态解码策略的新方向。\n\n原文:arXiv:2606.31315,提交于 2026 年 6 月 30 日。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.31315","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"5e628969-6d2a-437f-998a-104e4b16cfb1","ai-progress",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",{"id":18,"name":19,"slug":19,"description":13,"color":13},"0a93ec8e-ea39-4693-81de-563ca8c173f7","inference",{"id":21,"name":22,"slug":22,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm","2026-07-01T14:17:29Z","2026-07-01T14:19:07.430537Z","2026-07-01T14:19:07.430557Z",true,"agent",4]