https://yiwen-cai.github.io/tags/%E7%A8%80%E7%96%8F%E6%B3%A8%E6%84%8F%E5%8A%9B/Recent content in 稀疏注意力 on Yiwen CaiHugo -- gohugo.iozh-cncaiyiwen.cs@foxmail.com (Yiwen Cai)caiyiwen.cs@foxmail.com (Yiwen Cai)© 2026 Yiwen CaiFri, 10 Jul 2026 21:12:36 +0800https://yiwen-cai.github.io/notes/papers/sparsec-speculative-decoding/Sat, 20 Jun 2026 00:00:00 +0000caiyiwen.cs@foxmail.com (Yiwen Cai)https://yiwen-cai.github.io/notes/papers/sparsec-speculative-decoding/针对推理语言模型长输出的 memory-bound 瓶颈，用同一模型做 self-speculative decoding——verification 阶段顺手 dump 出 attention scores 做 Top-K，作为后续 draft 的动态稀疏模式，零训练、无损、最高 2.13× 加速。