TurboQuant: Redefining AI efficiency with extreme compression

https://research.google/blog/turboquant-redefining-ai-efficiency-with-extreme-compression/

TurboQuant: Redefining AI efficiency with extreme compression

I 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?

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.
Reminds me vaguely of Burrows-Wheeler transformations in bzip2.