home
Mohamed Arbi Nsibi
tag

#Quantization

4 posts

TurboQuant: The Compression Shannon Would Approve

Millions of vectors, a fraction of the memory, and almost zero accuracy lost, here's the math behind it.

Qdrant 1.18: Faster, Smarter, and Easier Vector Search

Dynamic schema updates, TurboQuant compression, better monitoring, and stronger operational safeguards for production vector search.

Bringing Vector Reasoning to the Physical World

Because a robot shouldn't have to wait for a 5G signal to think: Decentralizing vector search for a local-first physical world

Breaking the Memory Wall: A Quantization Guide

How quantization can reduce memory usage by 32x without losing accuracy using Qdrant.