Skip to content
gentic.news — AI News Intelligence Platform

Technique · architecture

Mixture of Depths

A technique letting tokens skip transformer layers when unnecessary, allocating compute adaptively based on token importance.

Origin: Google DeepMind, 2024-04Read origin paper →Also known as: MoD
0
Products deploying
Avg research → prod
First commercial deploy

Deployment timeline

No verified deployments yet in our tracked product set.