English(EN) The Clustering Strikes Back: Building Cost-Effective and High-Performance ANNS at Scale with Helmsman

RedNote的HELMSMAN将ANNS硬件成本降低90%

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-11 10:10

RedNote（小红书）的研究人员开发了HELMSMAN，一个新颖的基于聚类的近似最近邻搜索（ANNS）系统，旨在显著降低大规模ANNS部署的硬件成本。通过集成用户空间存储栈、学习型剪枝模块和GPU加速构建流水线，HELMSMAN实现了可观的节省，将硬件成本降低了90%以上。该系统能够在数小时内处理数十亿规模的索引重建，并且目前支持在40台机器上运行ANNS工作负载，而此前这需要大约35,000个核心和0.35 PB的DRAM。 AI

影响降低了大规模ANNS的硬件成本，可能促进AI驱动的搜索和推荐系统的更广泛采用。

排序理由详细介绍ANNS新系统的学术论文。[lever_c_demoted from research: ic=1 ai=0.7]

在 arXiv cs.IR (Information Retrieval) 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍ANNS新系统的学术论文。[lever_c_demoted from research: ic=1 ai=0.7]
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: infra, paper; 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: 127 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Chuliang Weng · 2026-06-11 10:10

聚类反击：用Helmsman构建高性价比、高性能的ANNS（大规模）

RedNote (a.k.a., Xiaohongshu, a global-scale social network platform) widely adopts approximate nearest neighbor search (ANNS) to power its search, recommendation, and advertising services. Due to the demanding Service Level Agreements (SLAs), we have to rely on in-memory graph-b…

本文如何被排名

报道来源 [1]

聚类反击：用Helmsman构建高性价比、高性能的ANNS（大规模）

相关实体

相关话题