RUMMY

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.

NVIDIA cuVS is a GPU-accelerated approximate nearest neighbor search library utilizing CUDA for high-performance CAGRA, HNSW, IVF-PQ indexes on billion-scale datasets. Supports batch queries for high-throughput operations, ideal for large-scale similarity search and real-time recommendations. Delivers up to 12x faster index building and 8x lower query latency compared to CPU-only implementations like Milvus.

NVIDIA RAPIDS cuVS is a GPU-accelerated library for vector search and clustering with CUDA-optimized HNSW, IVF, CAGRA, and PQ implementations. Supports batch queries for high QPS, suited for large-scale similarity search in GenAI apps. Achieves up to 12x faster indexing and lower latency vs CPU-only alternatives like FAISS CPU.

ASPLOS 2024 paper introducing Juno, a system that accelerates high-dimensional approximate nearest neighbor search using sparsity-aware algorithms and GPU ray-tracing (RT) core mapping for hardware-level computation acceleration.

A 2025 research paper presenting a GPU-driven asynchronous I/O framework for billion-scale approximate nearest neighbor search. The system addresses the fundamental bottleneck of data movement between storage and compute in large-scale vector search.