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

> 标题为英语

> 全文为英语

**Published:** 2026年9月22日
**Author:** Chuxu Song, Jiuqi Wei, Zhencan Peng
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/rbs-attention-radius-bounded-sparse-prefill-for-long-context-large-langu

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 relevant token among many…

> 内容来自原始来源： **arXiv — cs.AI**
> [在 arXiv — cs.AI 阅读全文](https://arxiv.org/abs/2609.20971)

**标签：** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*