← Search

Diana Liskovich

2 accepted papers

2024

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

ACL 2024long

We present LayerSkip, an end-to-end solution to speed-up inference of large language models (LLMs). First, during training we apply layer dropout, with low dropout rates for earlier layers and higher dropout rates for later layers, and an early exit loss where all transformer layers share the same e…

2022

Simple Local Attentions Remain Competitive for Long-Context Tasks

NAACL 2022long

Many NLP tasks require processing long contexts beyond the length limit of pretrained models. In order to scale these models to longer text sequences, many efficient long-range attention variants have been proposed. Despite the abundance of research along this direction, it is still difficult to gau…