# GPU Accelerated Vector DBs

> Browse 6 items in GPU Accelerated Vector DBs.

## Items

- [NVIDIA cuVS](https://vectordb.ever.works/items/nvidia-cuvs) — 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.
- [cuVS](https://vectordb.ever.works/items/cuvs) — 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.
- [GPU-Accelerated Vector Indexing](https://vectordb.ever.works/items/gpu-accelerated-vector-indexing) — Open-source project demonstrating GPU-accelerated approximate nearest neighbor search using Inverted File (IVF) indexing on embeddings from a large Wikipedia dataset. It employs K-means clustering into 128 clusters and supports configurable CUDA kernels for coarse and fine search stages. Applicable for efficient vector querying in AI applications.
- [Hora](https://vectordb.ever.works/items/hora) — High-performance vector search library with product quantization.
- [PilotANN](https://vectordb.ever.works/items/pilotann) — 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.
- [RUMMY](https://vectordb.ever.works/items/rummy-gpu-vector-search) — GPU-accelerated vector query processing system using CUDA to handle datasets larger than GPU memory via reordered pipelining and cluster-based retrofitting. Supports batch queries with up to 135x speedup over traditional GPU methods and 23x vs CPU-only for large-scale similarity search and MIPS.

---

_Canonical page: https://vectordb.ever.works/categories/gpu-accelerated-vector-dbs_