TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings

no code implementations • 4 Apr 2023 • Norman P. Jouppi, George Kurian, Sheng Li, Peter Ma, Rahul Nagarajan, Lifeng Nai, Nishant Patil, Suvinay Subramanian, Andy Swing, Brian Towles, Cliff Young, Xiang Zhou, Zongwei Zhou, David Patterson

For similar sized systems, it is ~4. 3x-4. 5x faster than the Graphcore IPU Bow and is 1. 2x-1. 7x faster and uses 1. 3x-1. 9x less power than the Nvidia A100.

TripLe: Revisiting Pretrained Model Reuse and Progressive Learning for Efficient Vision Transformer Scaling and Searching

no code implementations • ICCV 2023 • Cheng Fu, Hanxian Huang, Zixuan Jiang, Yun Ni, Lifeng Nai, Gang Wu, Liqun Cheng, Yanqi Zhou, Sheng Li, Andrew Li, Jishen Zhao

One promising way to accelerate transformer training is to reuse small pretrained models to initialize the transformer, as their existing representation power facilitates faster model convergence.

Knowledge Distillation Neural Architecture Search