hipVS documentation#
2026-11-02
1 min read time
hipVS is a GPU-accelerated vector search library for AMD GPUs, enabling high-performance approximate and exact nearest-neighbor (ANN) search and clustering workloads. It is part of the AMD Data Science toolkit, an open-source software collection for high-performance data science applications. Forked from the RAPIDS® cuVS project and aligned with RAPIDS 26.06, hipVS brings state-of-the-art vector similarity capabilities to the ROCm/HIP software stack and AMD platforms. It is designed to minimize porting friction for users familiar with cuVS by maintaining consistent directory structure, file organization, and API naming. For more information, see What is hipVS?
The hipVS code is open and hosted at AMD-Ecosystem/hipVS.
To contribute to the documentation refer to Contributing to AMD Data Science.
You can find licensing information on the Licensing page.