将500亿向量索引分布到上千台机器，实现26ms低延迟高效搜索。
DISTRIBUTEDANN: Efficient Scaling of a Single DISKANN Graph Across Thousands of Computers
- 用分布式键值存储与内存ANN索引构建跨千机系统
- 支持超10万QPS，中位查询延迟仅26ms，效率提升6倍
- 已替代Bing搜索的旧架构，适合大规模向量服务场景
我们提出DISTRIBUTEDANN，一种分布式向量搜索服务，可在超过一千台机器上运行单一500亿向量图索引，实现26ms中位查询延迟，每秒处理超过10万次查询。其效率比现有分片与路由策略高出6倍。该系统基于两个成熟组件：分布式键值存储和内存内近似最近邻（ANN）索引。DISTRIBUTEDANN已取代传统扩展架构，用于支撑Bing搜索服务，并分享了迁移过程中的实践经验。
原文摘要 · Abstract (English)
We present DISTRIBUTEDANN, a distributed vector search service that makes it possible to search over a single 50 billion vector graph index spread across over a thousand machines that offers 26ms median query latency and processes over 100,000 queries per second. This is 6x more efficient than existing partitioning and routing strategies that route the vector query to a subset of partitions in a scale out vector search system. DISTRIBUTEDANN is built using two well-understood components: a distributed key-value store and an in-memory ANN index. DISTRIBUTEDANN has replaced conventional scale-out architectures for serving the Bing search engine, and we share our experience from making this transition.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。