# DistMLIP: A Distributed Inference Platform for Machine Learning Interatomic Potentials

arXiv: https://arxiv.org/abs/2506.02023 · HTML: https://mlsanity.com/paper/2506.02023/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 68 references that are in the map.
- First posted on arXiv 28 May 2025.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials](https://mlsanity.com/paper/2101.03164/) (2021)
- [Equivariant message passing for the prediction of tensorial properties and molecular spectra](https://mlsanity.com/paper/2102.03150/) (2021)
- [GemNet: Universal Directional Graph Neural Networks for Molecules](https://mlsanity.com/paper/2106.08903/) (2021)
- [Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics](https://mlsanity.com/paper/2204.05249/) (2022)
- [The Open Catalyst 2020 (OC20) Dataset and Community Challenges](https://mlsanity.com/paper/2010.09990/) (2020)
- [Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics](https://mlsanity.com/paper/1707.09571/) (2017)
- [EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations](https://mlsanity.com/paper/2306.12059/) (2023)
- [Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs](https://mlsanity.com/paper/2302.03655/) (2023)
- [Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction](https://mlsanity.com/paper/2502.12147/) (2025)
- [TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials](https://mlsanity.com/paper/2306.06482/) (2023)
- [Scaling the leading accuracy of deep equivariant models to biomolecular simulations of realistic size](https://mlsanity.com/paper/2304.10061/) (2023)
- [Latent Ewald summation for machine learning of long-range interactions](https://mlsanity.com/paper/2408.15165/) (2024)
- [Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations](https://mlsanity.com/paper/2203.09697/) (2022)
- [Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians](https://mlsanity.com/paper/2501.09009/) (2025)
- [A predictive machine learning force field framework for liquid electrolyte development](https://mlsanity.com/paper/2404.07181/) (2024)
- [Machine-learning-accelerated simulations to enable automatic surface reconstruction](https://mlsanity.com/paper/2305.07251/) (2023)
- [Extending the limit of molecular dynamics with ab initio accuracy to 10 billion atoms](https://mlsanity.com/paper/2201.01446/) (2022)
- [The Reverse Cuthill-McKee Algorithm in Distributed-Memory](https://mlsanity.com/paper/1610.08128/) (2016)

## Built on by (most cited first, 5 of 5)

- [chemtrain-deploy: A parallel and scalable framework for machine learning potentials in million-atom MD simulations](https://mlsanity.com/paper/2506.04055/) (2025)
- [Smooth Dynamic Cutoffs for Machine Learning Interatomic Potentials](https://mlsanity.com/paper/2601.21147/) (2026)
- [Facet: highly efficient E(3)-equivariant networks for interatomic potentials](https://mlsanity.com/paper/2509.08418/) (2025)
- [Perspective: Towards sustainable exploration of chemical spaces with machine learning](https://mlsanity.com/paper/2604.00069/) (2026)
- [MALOQ: Massively Accelerated Learning of Operators for Quantum Transport](https://mlsanity.com/paper/2606.28911/) (2026)

## Abstract (arXiv)

Large-scale atomistic simulations are essential to bridge computational materials and chemistry to realistic materials and drug discovery applications. In the past few years, rapid developments of machine learning interatomic potentials (MLIPs) have offered a solution to scale up quantum mechanical calculations. Parallelizing these interatomic potentials across multiple devices poses a challenging, but promising approach to further extending simulation scales to real-world applications. In this work, we present DistMLIP, an efficient distributed inference platform for MLIPs based on zero-redundancy, graph-level parallelization. In contrast to conventional spatial partitioning parallelization, DistMLIP enables efficient MLIP parallelization through graph partitioning, allowing multi-device inference on flexible MLIP model architectures like multi-layer graph neural networks. DistMLIP presents an easy-to-use, flexible, plug-in interface that enables distributed inference of pre-existing MLIPs. We demonstrate DistMLIP on four widely used and state-of-the-art MLIPs: CHGNet, MACE, TensorNet, and eSEN. We show that DistMLIP can simulate atomic systems 3.4x larger and up to 8x faster compared to previous multi-GPU methods. We show that existing foundation potentials can perform near-million-atom calculations at the scale of a few seconds on 8 GPUs with DistMLIP.