A model-agnostic JAX-to-LAMMPS framework runs machine learning potentials in million-atom multi-GPU molecular dynamics with near-ideal strong and weak scaling.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.comp-ph 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
chemtrain-deploy: A parallel and scalable framework for machine learning potentials in million-atom MD simulations
A model-agnostic JAX-to-LAMMPS framework runs machine learning potentials in million-atom multi-GPU molecular dynamics with near-ideal strong and weak scaling.