Hacker News new | ask | show | jobs
TurboQuant can reduce vector index size by 10x at 100M Row Scale (github.com)
8 points by mxfeinberg 28 days ago
1 comments
0-_-0 27 days ago
32 bits vs 4 bits it looks like
link
mxfeinberg 27 days ago
Yup, and unlike the original turboquant paper, my implementation is pinned to using a 4 bit code book so I could use SIMD kernels for performance.
link