Skip to main content
Ctrl+K
NVIDIA PhysicsNeMo Framework - Home NVIDIA PhysicsNeMo Framework - Home

NVIDIA PhysicsNeMo Framework

NVIDIA PhysicsNeMo Framework - Home NVIDIA PhysicsNeMo Framework - Home

NVIDIA PhysicsNeMo Framework

Table of Contents

PhysicsNeMo Framework

  • Overview

Getting Started

  • System Requirements
  • Install Guide

User Guide

  • Training Recipe
  • Logging and Checkpointing
  • Model Architectures
  • PhysicsNeMo Distributed
    • Domain Parallelism
      • Domain Parallelism and Shard Tensor
      • Implementing New Layers for ShardTensor
      • Domain Decomposition, ShardTensor, and FSDP Tutorial
  • Physics-guided
  • Performance
    • Profiling
    • Torch Compile and External Kernels
    • GPU Optimized Layers
  • Data Curation
  • Model Evaluation and Inference
  • Symbolic Abstractions
    • Introductory Example

Examples

  • PhysicsNeMo Examples Catalog

Library Documentation

  • PhysicsNeMo
    • API Reference
      • PhysicsNeMo Models
        • PhysicsNeMo Modules
        • Fully Connected Network
        • Fourier Neural Operators
        • Graph Neural Networks
        • Convolutional Networks
        • Recurrent Neural Networks
        • Operator Models
        • Diffusion Models
        • Diffusion Preconditioners
        • Weather / Climate Models
      • PhysicsNeMo Datapipes
      • PhysicsNeMo Metrics
      • PhysicsNeMo Deploy
      • PhysicsNeMo Distributed
      • PhysicsNeMo ShardTensor
      • PhysicsNeMo Utils
      • PhysicsNeMo Launch Logging
      • PhysicsNeMo Launch Utils
    • Examples
      • Introductory Examples
        • Fourier Neural Operater for Darcy Flow
        • Physics Guided models for Darcy flow
        • Lid Driven Cavity Flow using Purely Physics Driven Neural Networks (PINNs)
        • MeshGraphNet for transient vortex shedding
        • Adaptive Fourier Neural Operator (AFNO) for weather forecasting
        • MeshGraphNet with Lagrangian mesh
        • Learning the flow field of Stokes flow
      • CFD Examples
        • MeshGraphNet for transient vortex shedding
        • AeroGraphNet for external aerodynamic evaluation
        • DoMINO: Decomposable Multi-scale Iterative Neural Operator for External Aerodynamics
        • Factorized Implicit Global Convolution Network
        • XAeroNet: Scalable Neural Models for External Aerodynamics
        • RNN for transient 2D Navier Stokes flow
        • RNN for transient 3D Gray Scott system
        • MeshGraphNet with Lagrangian mesh
        • Nested Fourier Neural Operater for Darcy Flow
        • Physics Guided models for Darcy flow
        • Learning the flow field of Stokes flow
        • Shallow Water Equations - Distributed GraphCast
        • Temporal attention model in Mesh-Reduced space for transient vortex shedding
        • Transolver for Darcy Flow
        • Diffusion-based-Fluid-Super-resolution
        • Thermal and airflow surrogate model for Datacenter design
        • DoMINO-Automotive-Aero NIM Fine-tuning
      • Weather and Climate Examples
        • ERA5 Data Downloader and Converter
        • GraphCast for weather forecasting
        • Adaptive Fourier Neural Operator (AFNO) for weather forecasting
        • Deep Learning Weather Prediction (DLWP) model for weather forecasting
        • Deep Learning Weather Prediction (DLWP-HEALPIX) model for weather forecasting
        • Diagnostic models in PhysicsNeMo (precipitation)
        • Unified Recipe for Training Global Weather Forecasting Models
        • Generative Correction Diffusion Model (CorrDiff) for Km-scale Atmospheric Downscaling
        • StormCast: Kilometer-Scale Convection Allowing Model Emulation using Generative Diffusion Modeling
      • Healthcare Examples
        • MeshGraphNet for Reduced-Order cardiovascular simulations
        • Fourier Neural Operator for Brain anomaly detection
      • Additive Manufacturing Examples
        • Virtual Foundary GraphNet
      • Molecular Dynamics Examples
        • Molecular Dynamics using GNNs
      • Geophysics Examples
        • Diffusion Model for Full-Waveform Inversion (FWI)
  • PhysicsNeMo Sym
    • Theory
      • Physics Informed Neural Networks (PINNs) in PhysicsNeMo Sym
      • Architectures In PhysicsNeMo Sym
      • Advanced Schemes and Tools
      • Recommended Practices in PhysicsNeMo Sym
      • Miscellaneous Concepts
    • PhysicsNeMo Sym Features
      • Geometry Modules
      • Computational Graph, Nodes and Architectures
      • Constraints
      • PhysicsNeMo Sym Configuration
      • Post Processing in PhysicsNeMo Sym
      • Performance
    • Examples
      • Introductory Example
      • 1D Wave Equation
      • 2D Seismic Wave Propagation
      • Coupled Spring Mass ODE System
      • Turbulent physics: Zero Equation Turbulence Model
      • Scalar Transport: 2D Advection Diffusion
      • Linear Elasticity
      • Inverse Problem: Finding Unknown Coefficients of a PDE
      • Darcy Flow with Fourier Neural Operator
      • Darcy Flow with Adaptive Fourier Neural Operator
      • Darcy Flow with Physics-Informed Fourier Neural Operator
      • Deep Operator Network
      • Interface Problem by Variational Method
      • STL Geometry: Blood Flow in Intracranial Aneurysm
      • Moving Time Window: Taylor Green Vortex Decay
      • Electromagnetics: Frequency Domain Maxwell’s Equation
      • Fully Developed Turbulent Channel Flow
      • Turbulence Super Resolution
      • Conjugate Heat Transfer
      • Parameterized 3D Heat Sink
      • Heat Transfer with High Thermal Conductivity
      • FPGA Heat Sink with Laminar Flow
      • Industrial Heat Sink
    • API Reference
      • Fundamental API
        • PhysicsNeMo Sym
        • PhysicsNeMo Sym Constraints
        • PhysicsNeMo Sym Inferencers
        • PhysicsNeMo Sym Validators
        • PhysicsNeMo Sym Monitors
        • PhysicsNeMo Sym Loss
        • PhysicsNeMo Sym Hydra
        • PhysicsNeMo Sym Geometry
        • PhysicsNeMo Sym Equations and Utils
  • PhysicsNeMo Curator
  • PhysicsNeMo CFD
  • Earth2Studio

Resources

  • Customizing PhysicsNeMo
  • Switching from DGL to PyTorch Geometric

Releases

  • Release Notes
  • PhysicsNeMo Sym
  • PhysicsNeMo Sym Features

PhysicsNeMo Sym Features#

Core features and capabilities of PhysicsNeMo Sym.

PhysicsNeMo Sym Features

  • Geometry Modules
  • Computational Graph, Nodes and Architectures
  • Constraints
  • PhysicsNeMo Sym Configuration
  • Post Processing in PhysicsNeMo Sym
  • Performance

previous

Miscellaneous Concepts

next

Geometry Modules
NVIDIA NVIDIA
Privacy Policy | Manage My Privacy | Do Not Sell or Share My Data | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright © 2025, NVIDIA PhysicsNeMo Team.