Skip to content
conftrace_

early exit technique

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

token dependency (1) layer permutation (1) non-autoregressive generation (1) pre-trained language model (1) inference efficiency (1) early exit (1) text generation (1)

Papers

ELMER: A Non-Autoregressive Pre-trained Language Model for Efficient and Effective Text Generation EMNLP 2022