This document is relevant for: Trn2, Trn3

Speculation

Design documentation for speculative decoding. For configuration guidance, see Speculative decoding in the features guide and the EAGLE3 tutorials for Llama 3.1 and GPT-OSS.

Topic	Description
Speculative decoding	EAGLE3 internals on Neuron

This document is relevant for: Trn2, Trn3