OUTLETS: Output-Length Prediction from Speculative Decoding Backbones
This work identifies a structural connection between speculative decoding (SD) and length prediction: latent representations produced by the draft decoder in advanced frameworks (e.g., EAGLE-3) encode signals that are predictive of generation length.
Wei-Huang Wen, Ying-Ying Liu, Yi-Chuan Liu et al.
· 0 citations