Files
qdrant/lib
Arnaud Gourlay d4e0f354da Single inverse rotation in TurboQuant symmetric L1 scoring (#9835)
The inverse Hadamard rotation is linear, so it distributes over
subtraction: |R'd1 - R'd2| = |R'(d1 - d2)|. Subtract the dequantized
vectors in rotated space and inverse-rotate the difference once,
instead of inverse-rotating both vectors per score call.

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-14 15:42:10 +02:00
..
2026-07-07 16:25:57 +02:00
2026-07-07 16:25:57 +02:00
2026-07-07 14:53:15 +02:00