A Compression-Compilation Framework for On-mobile Real-time BERT Applications
Wei Niu, Zhenglun Kong, Geng Yuan, Weiwen Jiang, Jiexiong Guan, Caiwen Ding, Pu Zhao, Sijia Liu
Abstract
Transformer-based deep learning models have increasingly demonstrated high accuracy on many natural language processing (NLP) tasks. In this paper, we propose a compression-compilation co-design framework that can guarantee the identified model meets both resource and real-time specifications of mobile devices. Our framework applies a compiler-aware neural architecture optimization method (CANAO), which can generate the optimal compressed model that balances both accuracy and latency. We are able to achieve up to 7.8x speedup compared with TensorFlow-Lite with only minor accuracy loss. We present two types of BERT applications on mobile devices: Question Answering (QA) and Text Generation. Both can be executed in real-time with latency as low as 45ms. Videos for demonstrating the framework can be found on https://www.youtube.com/watch?v=_WIRvK_2PZI
BibTeX
@inproceedings{ijcai2021p712,
title = {A Compression-Compilation Framework for On-mobile Real-time BERT Applications},
author = {Niu, Wei and Kong, Zhenglun and Yuan, Geng and Jiang, Weiwen and Guan, Jiexiong and Ding, Caiwen and Zhao, Pu and Liu, Sijia and Ren, Bin and Wang, Yanzhi},
booktitle = {Proceedings of the Thirtieth International Joint Conference on
Artificial Intelligence, {IJCAI-21}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Zhi-Hua Zhou},
pages = {5000--5003},
year = {2021},
month = {8},
note = {Demo Track},
doi = {10.24963/ijcai.2021/712},
url = {https://doi.org/10.24963/ijcai.2021/712},
}