alt Hacker NewsI did not understand what polarQuant is.
Is is something like pattern based compression where the algorithm finds repeating patterns and creates an index of those common symbols or numbers?
Replies
mrugge • today at 6:56 AM
1. Efficient recursive transform of kv embeddings into polar coordinates 2. Quantize resulting angles without the need for explicit normalization. This saves memory via key insight: angles follow a distribution and have analytical form.
➕ show 1 reply
viktorcode • today at 8:56 AM
The way I understand it, it's a way of compressing vectors by switching from their per-component representation to polar coordinates representation, where the nearby vectors are clumped together to a single line, allowing to describe them by different lengths
https://mesuvash.github.io/blog/2026/turboquant-interactive/ has a little visualisation