English(EN) Stream-CQSA: Exact Out-of-Memory Recovery for Attention

新框架为LLM注意力实现精确内存溢出恢复

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-03 04:00

研究人员开发了Stream-CQSA，一个旨在克服长上下文大型语言模型中内存溢出（OOM）限制的新颖框架。该方法利用CQS分解将注意力调用递归地划分为更小、可管理的子序列任务。通过独立执行这些任务然后重新组合结果，即使原始调用会超出设备内存，Stream-CQSA也能恢复完整的注意力输出。虽然与FlashAttention-2等优化内核相比，它会产生运行时开销，但它成功地防止了OOM故障，从而能够处理更长的序列。 AI

影响通过克服内存限制，能够处理LLM中的更长上下文，可能提高复杂任务的性能。

排序理由详细介绍LLM注意力新技术的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 22 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍LLM注意力新技术的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Yiming Bian, Joshua M. Akey · 2026-09-03 04:00

Stream-CQSA：注意力机制的精确内存溢出恢复

arXiv:2604.20819v2 Announce Type: replace Abstract: Long-context large language models are limited not only by attention cost but also by out-of-memory (OOM) failures. A selected attention call may not fit in available device memory even when the kernel is optimized. Exact and ap…

本文如何被排名

报道来源 [1]

Stream-CQSA：注意力机制的精确内存溢出恢复

相关实体

相关话题