Minseok Lee

Minseok Lee is one of the main developers of Merlin HugeCTR at NVIDIA. He specializes in analyzing and optimizing the end-to-end performance of GPU-accelerated applications. In graduate school, Minseok studied GPU architecture to maximize resource utilization, while publishing papers to related conferences such as HPCA, MICRO, and DATE.
Avatar photo

Posts by Minseok Lee

Data Science

Scaling Recommendation System Inference with NVIDIA Merlin Hierarchical Parameter Server

Recommendation systems are widely used today to personalize user experiences and improve customer engagement in various settings like e-commerce, social media,... 11 MIN READ
Data Science

Accelerating Recommender Systems Training with NVIDIA Merlin Open Beta

NVIDIA Merlin is an open beta application framework and ecosystem that enables the end-to-end development of recommender systems, from data preprocessing to... 9 MIN READ
Simulation / Modeling / Design

Introducing NVIDIA Merlin HugeCTR: A Training Framework Dedicated to Recommender Systems

Click-through rate (CTR) estimation is one of the most critical components of modern recommender systems. As the volume of data and its complexity grow rapidly,... 14 MIN READ
Recommenders / Personalization

Announcing NVIDIA Merlin: An Application Framework for Deep Recommender Systems

Recommender systems drive every action that you take online, from the selection of this web page that you’re reading now to more obvious examples like online... 17 MIN READ