Machine Learning Interatomic Potentials: Advancing Open-Source Software for Efficient and Scalable Molecular Simulation

TL;DR

mlip v2 is an advanced, scalable, and flexible open-source library that enhances machine learning interatomic potentials for efficient molecular simulations with new architectures and features.

Contribution

It introduces a unified, extensible framework with a new backend, architectures, and simulation capabilities, significantly improving scalability and flexibility over previous versions.

Findings

Accelerated model inference with e3j backend.

New Mixture-of-Experts architecture for large datasets.

Enhanced electrostatics and simulation features for complex systems.

Abstract

Machine learning interatomic potentials (MLIPs) enable atomistic simulations with near ab initio accuracy at significantly reduced computational cost, but their broader adoption is often limited by fragmented tooling, limited scalability, and inflexible software design. We present mlip v2, a new generation of the mlip library that advances efficient and scalable molecular simulation through a unified and extensible framework. The new release features a targeted API redesign with improved modularity and control, enabling flexible customization of training, data processing, and simulation workflows. It further integrates a new high-performance backend for equivariant operations, e3j, significantly accelerating model inference and simulations. In addition, the framework introduces a range of entirely new capabilities, including the eSEN architecture with a Mixture-of-Experts formulation for scalable training on large and diverse datasets, improved handling of electrostatics through more physically grounded charge modeling and long-range interaction treatment, and advanced simulation features such as NPT ensembles and nudged elastic band methods. Together, these extensions significantly broaden the scope of MLIP applications, enabling efficient modeling of complex, reactive, and out-of-equilibrium systems, and bridging the gap between ML research and practical molecular simulation applications. The library is available on GitHub and on PyPI under the Apache license 2.0.