Search Results for author: Weiyu Huang

Found 2 papers, 0 papers with code

Accelerating Transformer Pre-Training with 2:4 Sparsity

no code implementations2 Apr 2024 Yuezhou Hu, Kang Zhao, Weiyu Huang, Jianfei Chen, Jun Zhu

Training large Transformers is slow, but recent innovations on GPU architecture gives us an advantage.

Cannot find the paper you are looking for? You can Submit a new open access paper.