DBScholar

Back to papers

GPU-Native Approximate Nearest Neighbor Search with IVF-RaBitQ: Fast Index Build and Search

Summary: GPU-native IVF-RaBitQ combines IVF clustering with low-bit RaBitQ quantization for fast, compact ANNS without raw-vector reranking. Fused GPU kernels deliver ~3× CAGRA QPS, 14.7× faster builds, and >4.5× IVF-PQ throughput at ~0.95 recall. (summarized by gpt-5.6-luna on Aug 28 2026)

Paper ID
hcf9fca992e45fef6
Venue
VLDB
Year
2026
Pagerank
4.9793485e-05
Overall Rank
10,873 | 26.90%
DOI
10.14778/3836663.3836701

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

BibTeX Citation

@article{shi_vldb26,
        title = {{GPU-Native Approximate Nearest Neighbor Search with IVF-RaBitQ: Fast Index Build and Search}},
        author = {Shi, Jifan and Gao, Jianyang and Xia, James and Fehér, Tamás Béla and Long, Cheng},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {11},
        pages = {3454--3467},
        doi = {10.14778/3836663.3836701},
        url = {https://doi.org/10.14778/3836663.3836701},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 10 of 10 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
74 Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph 2019 VLDB 0.00037091678
804 RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search 2024 SIGMOD 0.00013832333
2,060 Similarity search in the blink of an eye with compressed indices 2023 VLDB 9.0983169e-05
2,821 Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search 2025 SIGMOD 7.9711961e-05
3,385 SymphonyQG: Towards Symphonious Integration of Quantization and Graph for Approximate Nearest Neighbor Search 2025 SIGMOD 7.3548612e-05
6,720 The Journey to A Knowledgeable Assistant with Retrieval-Augmented Generation (RAG) 2024 SIGMOD 5.6982109e-05
6,831 Filtered Vector Search: State-of-the-art and Research Opportunities 2025 VLDB 5.6685191e-05
7,587 Scalable Graph Indexing using GPUs for Approximate Nearest Neighbor Search 2026 SIGMOD 5.4891389e-05
8,032 VecFlow: A High-Performance Vector Data Management System for Filtered-Search on GPUs 2026 SIGMOD 5.4035152e-05
8,885 GPU-Accelerated ANNS: Quantized for Speed, Built for Change 2026 VLDB 5.2559789e-05
Previous Page 1 / 1 Next

Semantically Similar Papers

# Overall Rank Paper Year Venue
1 2,060 Similarity search in the blink of an eye with compressed indices 2023 VLDB
2 10,425 CMANNS: GPU-Accelerated Graph Index Construction for ANNS via Compute-Memory Disaggregation 2026 SIGMOD
3 7,004 Accelerating Graph Indexing for ANNS on Modern CPUs 2025 SIGMOD
4 10,643 FlashANNS: GPU-Driven Asynchronous I/O Pipelining for Eliminating Storage-Compute Bottlenecks in Billion-Scale Similarity Search 2026 SIGMOD
5 2,821 Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search 2025 SIGMOD
6 10,697 SVFusion: A CPU-GPU Co-Processing Architecture for Large-Scale Real-Time Vector Search 2026 VLDB
7 804 RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search 2024 SIGMOD
8 10,574 High-Throughput, Cost-Effective Billion-Scale Vector Search with a Single GPU 2026 SIGMOD
9 7,587 Scalable Graph Indexing using GPUs for Approximate Nearest Neighbor Search 2026 SIGMOD
10 8,885 GPU-Accelerated ANNS: Quantized for Speed, Built for Change 2026 VLDB