Remix.run Logo
TurboQuant can reduce vector index size by 10x at 100M Row Scale(github.com)
8 points by mxfeinberg 12 hours ago | 3 comments
0-_-0 4 hours ago | parent | next [-]

32 bits vs 4 bits it looks like

mxfeinberg an hour ago | parent [-]

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.

Slovian 12 hours ago | parent | prev [-]

[dead]