Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation 文章

ArXiv CS.CL2026-06-05NEWSen作者: Shuaiyi Li, Zhisong Zhang, Yan Wang, Lei Zhu, Dongyang Ma, Chenlong Deng, Yang Deng, Wai Lam
查看原文 →
关系图谱

Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation · 相关技术

相关技术

Retrieval-augmented generationKV CacheBlock attention