A shared MTP head predicts future tokens recursively for speculative decoding.
1 more from this model
A shared MTP head predicts future tokens recursively for speculative decoding.
specific method · filed under model architecture
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.
3 quotes from 3 sources, one card per model, each opening with its strongest.
A shared MTP head predicts future tokens recursively for speculative decoding.
A shared MTP head predicts future tokens recursively for speculative decoding.
The model includes Multi-Token Prediction (MTP) layers using a shared-weight design across prediction heads