Preprint
Aug 2026
InSituANN: Revisiting IVF for PCIe-Efficient Billion-Scale Vector Search
Approximate nearest neighbor search (ANNS) over billion-scale vector datasets has become a foundational operator for modern retrieval systems, powering large-scale recommendation, semantic search, and LLM/RAG workloads. Although GPUs offer massive parallelism and high-bandwidth memory for batched vector search, their l...
Yue-Meng Xu, Zongxi Liu, Junyu Long et al.
· 0 citations