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

arXiv: https://arxiv.org/abs/2602.23999 · HTML: https://mlsanity.com/paper/2602.23999/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Feb 2026.

## Built on by (most cited first, 4 of 4)

- [Revisiting RaBitQ and TurboQuant: A Symmetric Comparison of Methods, Theory, and Experiments](https://mlsanity.com/paper/2604.19528/) (2026)
- [IVF-TQ: Calibration-Free Streaming Vector Search via a Codebook-Free Residual Layer](https://mlsanity.com/paper/2605.17415/) (2026)
- [Stop Indexing at Full Precision: Revisiting Clustering for Vector Embeddings](https://mlsanity.com/paper/2608.14648/) (2026)
- [RSLM: Training-Free Vector Quantization for Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2608.30384/) (2026)

## Abstract (arXiv)

Approximate nearest neighbor search (ANNS) on GPUs is gaining increasing popularity for modern retrieval and recommendation workloads that operate over massive high-dimensional vectors. Graph-based indexes deliver high recall and throughput but incur heavy build-time and storage costs. In contrast, cluster-based methods build and scale efficiently yet often need many probes for high recall, straining memory bandwidth and compute. Aiming to simultaneously achieve fast index build, high-throughput search, high recall, and low storage requirement for GPUs, we present IVF-RaBitQ (GPU), a GPU-native ANNS solution that integrates the cluster-based method IVF with RaBitQ quantization into an efficient GPU index build/search pipeline. Specifically, for index build, we develop a scalable GPU-native RaBitQ quantization method that enables fast and accurate low-bit encoding at scale. For search, we develop GPU-native distance computation schemes for RaBitQ codes and a fused search kernel to achieve high throughput with high recall. With IVF-RaBitQ implemented and integrated into the NVIDIA cuVS Library, experiments on cuVS Bench across multiple datasets show that IVF-RaBitQ offers a strong performance frontier in recall, throughput, index build time, and storage footprint. For Recall approximately equal 0.95, IVF-RaBitQ achieves 3.0x higher QPS than the state-of-the-art graph-based method CAGRA, while also constructing indices 14.7x faster on average. Compared to the cluster-based method IVF-PQ, IVF-RaBitQ delivers on average over 4.5x higher throughput while avoiding accessing the raw vectors for reranking.