NVIDIA and AWS Make GPU Vector Indexing the Default in OpenSearch Serverless via cuVS — Up to 10x Faster at a Quarter of the Cost

NVIDIA Blog·medium signal

NVIDIA and AWS announced (June 23) that the NVIDIA cuVS library now powers GPU-accelerated vector indexing as the default in Amazon OpenSearch Serverless, claiming up to 10x faster index builds at roughly a quarter the cost versus CPU-only, making billion-scale vector databases buildable in under an hour. The same announcement debuts EC2 G7 instances on NVIDIA RTX PRO 4500 Blackwell Server Edition GPUs, part of a plan to deploy over 1M GPUs in 2026. For RAG and agent builders, this directly attacks the cost and latency of the retrieval layer at production scale.