Paweł Gadziński

Paweł Gadziński is a deep learning performance engineer at NVIDIA, specializing in the development of the Transformer Engine library. He is passionate about deep learning frameworks and accelerating large-scale model training performance. He earned his degree in Computer Science from the University of Warsaw.
Avatar photo

Posts by Paweł Gadziński

Simulation / Modeling / Design

How to Optimize Transformer-Based Models for Low-Precision Training

Transformer architectures are the backbone of many modern large language and generative AI models. As these models grow in size, training runs consume more GPU... 9 MIN READ