from Hacker News

Show HN: A GPU-accelerated binary vector index

by andes314 on 2/17/25, 12:45 AM with 7 comments

This is a vector index I built that supports insertion and k-nearest neighbors (k-NN) querying, optimized for GPUs. It operates entirely in CUDA and can process queries on half a billion vectors in under 200 milliseconds. The codebase is structured as a standalone library with an HTTP API for remote access. It’s intended for high-performance search tasks—think similarity search, AI model retrieval, or reinforcement learning replay buffers. The codebase is located at https://github.com/rodlaf/BinaryGPUIndex.

  • by kookamamie on 2/18/25, 11:40 PM

    Does it beat hnswlib? Also, it would be nice to see code examples (C++) without the API.

  • by rytill on 2/19/25, 10:23 AM

    When and how would one use binary vectors for encoding in ML? Do you have to make your model work natively with binary vectors or is there a translation step between float and binary vectors to make it compatible?

  • by martinloretz on 2/18/25, 10:48 PM

    Great work. Can you elaborate on how the radix selection works and how to get that working with float's and inner product distance? I just quickly checked the code, I'm not familiar with radix selection, but really interested in making extremely fast GPU indices.