Open Models Almanac
Methodsmodel architectureprediction head

specific method · filed under model architecture

Shared Multi-Token Prediction head

Uses shared MTP-head weights to predict future tokens recursively for speculative decoding.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See prediction head for the methods filed beside it.

Also called A shared MTP head.

sources
3
models
2
lab adopt it
1
strongest
core

Documented in

Evidence

3 quotes from 3 sources, one card per model, each opening with its strongest.

How sources treat it
used 2core 1
↑