ml-mlip-nvalchemi

Goal

Exploit NVIDIA's NValchemi toolkit to run energy/force/stress predictions, geometry relaxations, and molecular dynamics for a batch of structures in a single GPU-parallel forward pass, instead of N sequential CPU loops. This is automatically activated when nvalchemi-toolkit is installed in the environment — the existing MCP tool surface (static_calculation, relax_structure, run_md) passes a list of structures and dispatches to the NValchemi backend transparently.

Background

NValchemi provides batched dynamics integrators (FIRE, NVT Nose-Hoover, NPT, etc.) and a BaseModelMixin interface. AtomisticSkills wraps each MLIP in a BaseModelMixin-compatible class: