DigestAI news desk

AI news, digested. Every story with its sources, every hour.

Research

RBS-Attention provides radius-bounded sparse prefill for long-context LLMs

A new arXiv paper introduces RBS-Attention, a training‑free sparse‑prefill technique that uses a centroid base branch and a rescue branch to select attention blocks. The method independently thresholds each branch and merges their masks, preserving regular block‑sparse FlashAttention execution while mitigating the mean‑dilution failure mode.

1 source primary source

Key points

  • RBS-Attention achieves 20.65× standalone prefill‑attention speedup on H100 GPUs.
  • End‑to‑end time‑to‑first‑token speedup is 5.97× at 128K context on Qwen3-30B-A3B-Instruct-2507-FP8.
  • Overall RULER accuracy drops to 88.65 versus 89.52 for dense attention.

On H100 GPUs, RBS-Attention delivers a 20.65× speedup over dense prefill‑attention, an 11.92× boost compared with vLLM prefill‑attention, and a 5.97× end‑to‑end time‑to‑first‑token improvement at a 128K context on Qwen3-30B-A3B-Instruct-2507-FP8. When applied to the dense Qwen3-32B model, overall RULER accuracy is 88.65 versus 89.52 for dense attention. Additional evaluations on LongBench‑v2, InfiniteBench, and Video‑MME confirm quality retention, and ablations explore block size, threshold, and memory behavior.

Read the original atarXiv cs.AI · by Chuxu Song, Jiuqi Wei, Zhencan Peng primary sourceOpen source ↗
Topics · follow one to build your own front page
Qwen3-30B-A3B-Instruct-2507-FP8Qwen3-32B

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us.

Comments

via GitHub Discussions

More in Research

All →

Related stories