Tavi Halperin a4522017c5 feat: per-guide attention strength control in self-attention (#12518) ...

Implements per-guide attention attenuation via log-space additive bias
in self-attention. Each guide reference tracks its own strength and
optional spatial mask in conditioning metadata (guide_attention_entries).

2026-02-26 01:25:23 -05:00

27 KiB

Raw Blame History

View Raw