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.
The Journal of chemical physics145(17) (2016)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
physics.comp-ph 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 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.