NVIDIA cuVS is an open-source library for GPU-accelerated vector search and data clustering that enables faster vector searches and index builds.
It supports scalable data analysis, enhances semantic search efficiency, and helps developers accelerate existing systems or compose new ones from the ground up.
Integrated with key libraries and databases, cuVS manages complex code updates as new NVIDIA architectures and NVIDIA® CUDA® versions are released, ensuring peak performance and seamless scalability.
NVIDIA NIM™ provides containers to self-host GPU-accelerated inferencing microservices for pretrained and customized AI models across clouds, data centers, RTX™ AI PCs and workstations. NIM microservices expose industry-standard APIs for simple integration into AI applications, development frameworks, and workflows. Built on pre-optimized inference engines from NVIDIA and the community, including NVIDIA® TensorRT™ and TensorRT-LLM, NIM microservices optimize response latency and throughput for each combination of foundation model and GPU.
Blogs
- Exploring GPU-accelerated Vector Search in Elasticsearch with NVIDIA
- NVIDIA NIM with Elasticsearch vector database
Learn more
- NVIDIA GTC 2025 session: Bring Massive-Scale Vector Search to the GPU with Apache Lucene.