Skip to content

Blog

Welcome to the NVIDIA PhysicsNeMo blog! Here you'll find the latest insights, tutorials, and updates about the PhysicsNeMo framework. Discover how neural operators, GNNs, and generative AI models can enhance your engineering simulations and workflows.

Optimizing and Scaling DoMINO

DoMINO is one of the most popular and accurate models in PhysicsNeMo, with top accuracy metrics as measured by physicsnemo-cfd. Originally developed by and for PhysicsNeMo, DoMINO has been overhauled for performance optimizations and scale out enhancements. In this blog post, we'll highlight the performance enhancements we've made to DoMINO - giving more than 30x end to end speed up on DrivAerML training - as well as how you can use them from PhysicsNeMo for your own models.

Accelerating AI Physics development with PyTorch and PhysicsNeMo

This tutorial blog is designed for AI researchers and scientific machine learning (SciML) developers who wish to leverage PhysicsNeMo in creating AI Physics models. NVIDIA PhysicsNeMo is built upon PyTorch, the leading standard for AI model development. Organizations can utilize the native PyTorch stack and PhysicsNeMo to go from proof-of-concept development to production-scale training and inference workflows, achieving significant performance and operational efficiencies through enterprise-hardened PhysicsNeMo modules. This blog will demonstrate how AI researchers and SciML developers can progressively integrate PhysicsNeMo modules into their PyTorch stack.

PhysicsNeMo 25.08 - New Release Announcement

We're excited to announce the latest PhysicsNeMo release! It's packed with powerful new workflows and recipes for CAE application developers. With a key emphasis on the developer experience, this update is designed to help you build, train, and deploy state-of-the-art Physics AI solutions with unprecedented speed and simplicity. We've streamlined every step of the process, from data prep to model evaluation, so you can focus on innovation, not infrastructure. Here are some key highlights of this release: