Nicholas Noble

Nicolas Noble is a senior software engineer on NVIDIA's Dynamo team, working on distributed LLM inference infrastructure. He created the initial version of ModelExpress, the first piece of code in the project, and works across the benchmarking and runtime pieces around it, leveraging his experience from video game development to squeeze as much performance as possible out of the software and hardware stack. Nicolas studied in his home country, France, where he holds a degree from the University of Lorraine.
Avatar photo

Posts by Nicholas Noble

Agentic AI / Generative AI

ModelExpress: Distributing Model Artifacts at the Speed of Light

Every byte moved has a cost. As model checkpoints grow to hundreds of gigabytes or even a terabyte, that cost adds up quickly. To make things even worse, moving... 12 MIN READ