Re:Binary Vector Search at 350GB/S Using ARM Neon
by marekgalovic on Friday July 18, 2025 @03:24PM
(#44608792)
We do a projection of the original vectors so that it matches one of our optimized kernel. This generally gives us better recall vs. simple padding since all bits are utilized.
[ Parent
| on HN ]
There are no comments on this comment yet.