Individualized non-uniform quantization for vector search — mentioned by jbellis

Tue, 11 Nov 2025 21:28:29 GMT

two great points here: (1) quantization is how you speed up vector indexes, and (2) how your build your graph matters much much less* These are the insights behind DiskANN, which has replaced HNSW in most production systems. past that, well, you should really go read the DiskANN paper instead of this article, product quantization is way way way way way more effective than simple int8 or binary quant. here's my writeup from a year and a half ago: https://dev.to/datastax/why-vector-compression-matters-64l and if you want to skip forward several years to the cutting edge, check out…

Paper and discussion history. A mention is not an endorsement.

Individualized non-uniform quantization for vector search · HackerPapers discussions

Individualized non-uniform quantization for vector search — mentioned by jbellis