UBASE: An AI Search Engine for Trillion-Scale Vector Data Management at ByteDance

2026-08-31

AI Summary

UBASE通过量化感知向量核和混合存储引擎解决大规模向量数据管理中的内存瓶颈问题，提高吞吐量并降低成本。

Abstract

Since 2016, UBASE has been the foundation of ByteDance's search infrastructure, scaling to more than 7,000 clusters and 300 PB of indexed data. Driven by the demands of AI workloads, UBASE has evolved from a text search engine into a unified AI search system supporting vector retrieval, lexical matching, and predicate filtering. Its largest deployment indexes nearly one trillion high-dimensional vectors. This scale exposes two central bottlenecks in AI-era retrieval: memory-intensive graph-index construction under sustained ingestion, and the prohibitive cost of keeping vector indexes entirely in memory. UBASE addresses these bottlenecks with two techniques. First, it introduces a quantization-aware vector kernel based on SymRaBitQ, a new symmetric quantization scheme with tight theoretical guarantees that allows index construction to run directly in the quantized space accurately and efficiently without retaining a copy of full-precision vectors. Second, it provides a hybrid storage engine that supports memory-resident, hybrid, and SSD-resident deployments, with fine-grained record-level caching to trade memory for latency under operational control. On large-scale benchmarks, UBASE improves throughput by up to 3x, reduces indexing memory by 80%, and lowers operating cost by 86% compared with prior systems, while supporting trillion-vector scale, write-heavy or latency-sensitive workloads in production.

Problem

• vector data management
• graph-index construction
• memory-intensive
• vector indexes

Innovation

• SymRaBitQ
• quantization-aware vector kernel
• hybrid storage engine
• trillion-scale vector data