@inproceedings{ author={ L. Xu, Q. Anthony, Q. Zhou, N. Alnaasan, R. Gulhane, A. Shafi, H. Subramoni, D. Panda }, title={ Accelerating Large Language Model Training with Hybrid GPU-based Compression }, conference={ IEEE/ACM International Symposium on Cluster, Cloud, and Internet Computing 2024 }, year={ 2024 }, month={ May }, location={ Philadelphia, USA }, source={ http://nowlab.cse.ohio-state.edu/publications/ }, }