This project is a parallel simulation engine and molecular dynamics simulator designed to model the physical movements of atoms and molecules. It functions as an interatomic potential framework for calculating forces between particles and a materials analysis tool for computing thermodynamic, structural, and transport properties of solids and fluids. The engine is distinguished by its high-performance computing capabilities, utilizing spatial-domain decomposition and message-passing interface communication to distribute workloads across processors. It supports multi-backend GPU acceleration v
MACE - Table of contents - About MACE - Documentation - Installation - pip installation - pip installation from source - Usage - Training - Evaluation - Tutorials - CUDA acceleration with cuEquivariance - Weights and Biases for experiment tracking - Pretrained Foundation Models - MACE-MP:…
Notes: This is currently a development branch of ACE (though we are still tagging versions regularly). For the latest stable version see DEV-v0.8.x Preliminary Documentation, WIP.
This package implements the Allegro E(3)-equivariant machine learning interatomic potential.
Les fonctionnalités principales de mir-group/allegro sont : Interatomic Potentials.
Les alternatives open-source à mir-group/allegro incluent : lammps/lammps — This project is a parallel simulation engine and molecular dynamics simulator designed to model the physical movements… acesuit/acefit.jl — Generic Codes for Fitting ACE models. acesuit/mace — MACE - Table of contents - About MACE - Documentation - Installation - pip installation - pip installation from source… aiqm/torchani — TorchANI 2.0 is an open-source library that supports training, development, and research of ANI-style neural network… apax-hub/apax — apax[^1][^2] is a high-performance, extendable package for training of and inference with atomistic neural networks.… acesuit/ace1.jl — Notes: This is currently a development branch of ACE (though we are still tagging versions regularly). For the latest…