This work introduces EE-Tuning, a lightweight and economical solution to training/tuning early-exit large language models (LLMs). In contrast to the common approach of full-parameter pre-training, EE-Tuning augments any pre-trained (and possibly fine-tuned) standard LLM with additional early-exit layers that are tuned in a parameter-efficient manner, which requires significantly less computational resources and training data. Our implementation of EE-Tuning achieves outstanding training efficiency via extensive performance optimizations, as well as scalability due to its full compatibility with 3D parallelism. Results of systematic experiments validate the efficacy of EE-Tuning, confirming that effective early-exit LLM inference can be achieved with a limited training budget. In hope of making early-exit LLMs accessible to the community, we release the source code of our implementation of EE-Tuning at https://github.com/pan-x-c/EE-LLM.
@article{arxiv.2402.00518,
title = {EE-Tuning: An Economical yet Scalable Solution for Tuning Early-Exit Large Language Models},
author = {Xuchen Pan and Yanxi Chen and Yaliang Li and Bolin Ding and Jingren Zhou},
journal= {arXiv preprint arXiv:2402.00518},
year = {2024}
}