BANG

NVIDIA CAGRA is a GPU-accelerated graph-based library for approximate nearest neighbor searches, optimized for high-performance vector search leveraging modern GPU parallelism. It is suitable for scenarios requiring rapid, large-scale vector retrieval.

Cagra provides highly parallel graph construction and approximate nearest neighbor search for GPUs, supporting large-scale vector database operations and efficient similarity search.

This paper introduces the HNSW algorithm, which is widely adopted in vector databases and search engines for its efficient and robust performance on high-dimensional data. HNSW is foundational in powering modern vector search systems.

An influential paper analyzing and improving approximate nearest neighbor search methods for high-dimensional data, highly relevant for developing and understanding vector databases.

Memory-bounded GPU-accelerated framework for graph-based ANN vector search using CUDA and LibTorch, optimized for large-scale workloads beyond GPU memory. Features batch processing for high efficiency; outperforms CPU-only ANN in speed for similarity search in vector databases.

An efficient CPU/GPU cooperative processing architecture for billion-scale approximate nearest neighbor search. FusionANNS achieves up to 13.1× higher QPS compared to SPANN and can handle billion-vector datasets with over 12,000 QPS while maintaining 15ms latency using only one entry-level GPU.