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.
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.