Hacker News
TurboQuant can reduce vector index size by 10x at 100M Row Scale
8 points by mxfeinberg ago
|
2 comments
0-_-0
|
next
[-]
32 bits vs 4 bits it looks like
mxfeinberg
|
root
|
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
|
previous
[-]
[dead]