Radek Osmulski – Medium

Radek Osmulski

Published in
NVIDIA Merlin

How to preprocess data using NVTabular on multiple GPUs?

Multi-GPU machines are becoming much more common. Training deep learning models across multiple-GPUs is something that is often discussed.

Apr 13, 2023

How to preprocess data using NVTabular on multiple GPUs?

Apr 13, 2023

Published in
NVIDIA Merlin

Learn how Meta, Alibaba, ASOS, and Kuaishou Technology are delivering recommendations at scale (at…

Over the last couple of months, the Merlin team has been all about aligning the features of our software with customer needs and developing…

Mar 8, 2023

Learn how Meta, Alibaba, ASOS, and Kuaishou Technology are delivering recommendations at scale (at…

Mar 8, 2023

Published in
NVIDIA Merlin

How to run Merlin on Google Colab

Colab provides access to GPUs for new learners and enables experienced practitioners an easy way to experiment with the Merlin recommender…

Jan 24, 2023

How to run Merlin on Google Colab

Jan 24, 2023

Published in
NVIDIA Merlin

Transformers, multi-GPU, HPO, and more are here for Recommender Models in the 22.11

We recently released a new version of the Merlin Framework! We added a couple of features that can help you train better models faster and…

Dec 1, 2022

Transformers, multi-GPU, HPO, and more are here for Recommender Models in the 22.11

Dec 1, 2022

Published in
NVIDIA Merlin

Building a Diverse Models Ensemble for Fashion Session-Based Recommendation for RecSys2022…

A team from NVIDIA took part in the recent ACM RecSys 2022 Challenge. The team consisted of several NVIDIA Kaggle Grandmasters and…

Sep 20, 2022

Building a Diverse Models Ensemble for Fashion Session-Based Recommendation for RecSys2022…

Sep 20, 2022

Published in
NVIDIA Merlin

Exploring Production Ready Recommender Systems with Merlin

by Radek Osmulski and Benedikt Schifferer

Jul 5, 2022

Exploring Production Ready Recommender Systems with Merlin

Jul 5, 2022

Published in
NVIDIA Merlin

Scale faster with less code using Two Tower with Merlin

by Radek Osmulski, Benedikt Schifferer, Ronay Ak and Gabriel Moreira

Jun 21, 2022

Scale faster with less code using Two Tower with Merlin

Jun 21, 2022

How to build a Deep Learning system that will answer questions about the Harry Potter universe?

To achieve our goal, which is to build a Q&A system that will answer questions about the Harry Potter universe, we will use NVIDIA Riva and…

Aug 6, 2021

How to build a Deep Learning system that will answer questions about the Harry Potter universe?

Aug 6, 2021

How to use the power of the community to learn faster

Community is the most powerful force behind online learning. It is the reason why MOOCs have a limited impact and tight-knit communities…

May 21, 2021

How to use the power of the community to learn faster

May 21, 2021

Published in
The Startup

Going From Not Being Able to Code to Deep Learning Hero

A detailed plan based on experience

Jan 14, 2021

Going From Not Being Able to Code to Deep Learning Hero

Jan 14, 2021

Radek Osmulski

Radek Osmulski

I ❤️ ML / DL ideas — I tweet about them / write about them / implement them. Recommender Systems at NVIDIA

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams