Jan Lasek

Jan Lasek is a senior deep learning algorithms engineer at NVIDIA, focusing on large language models and recommender systems. His contributed projects include MLPerf Training, NeMo, and TensorRT Model Optimizer. He holds an M.S. in mathematics from the University of Warsaw and a Ph.D. degree in computer science from the Warsaw University of Technology.
Avatar photo

Posts by Jan Lasek

Illustration showing models and NeMo.
Generative AI / LLMs Sep 10, 2024

Post-Training Quantization of LLMs with NVIDIA NeMo and NVIDIA TensorRT Model Optimizer

As large language models (LLMs) are becoming even bigger, it is increasingly important to provide easy-to-use and efficient deployment paths because the cost of... 10 MIN READ