RBS-Attention: Radius-Bounded Sparse Prefill for Long-Context Large Language Models

事件

arXiv:2609.20971v1 Announce Type: new Abstract: Long-context large language model inference is increasingly limited by prefill, where dense self-attention processes the entire prompt before generation begins. Sparse block selection can reduce this cost, but a block centroid may hide a highly relevan

来源

本条目由采集管线自动抓取并发布，完整内容见下方来源链接。

*采集源：arXiv cs.AI*