dela a2c4217dae Document LatentMoE sigmoid routing, sparse dispatch, and K3 block figures ...

Ledger C10–C12 match the permute-pad-bmm path and Switch aux/z-loss.
Section 8 adds overview and component TikZ; MoE capacity is C_moe so it
does not collide with KDA chunk size.

2026-08-26 14:43:58 +08:00

632 KiB

Raw History

View Raw