Conversation
Luthaf
reviewed
Mar 12, 2026
| } else { | ||
| error->all(FLERR, "the model requested an unsupported dtype '{}'", mta_data->capabilities->dtype()); | ||
| } | ||
| auto system = this->system_adaptor->system_from_lmp( |
Member
There was a problem hiding this comment.
this should deal with requested inputs directly
Author
There was a problem hiding this comment.
idk if the current version is what you want
Author
|
Will be ready when #49 is merged |
GardevoirX
force-pushed
the
compute
branch
2 times, most recently
from
b68b2e0 to
7439141
Compare
Luthaf
reviewed
Jul 1, 2026
Author
|
Hm after removing the system energy output, we currently don't have a test for the global scalar output, what can be suitable? |
Luthaf
reviewed
Jul 8, 2026
Luthaf
left a comment
Luthaf
left a comment
Member
There was a problem hiding this comment.
Getting there, I think we can make this more convenient in 90% of the use cases by making more of the settings optional
Luthaf
reviewed
Jul 9, 2026
This allow to use metatomic ML models to compute properties of the system on the fly, for example to compute heat flux, dipole moments, NMR shieldings, …
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR aims to allow lammps to use
AtomisticModelsto compute propertiesUsage
compute <ID> <group-ID> metatomic <model_path> <property_name/[variant]> unit <unit> device <device> check_consistency <on/off> extensions_directory <extensions_directory> shape <scalar or vector> <vector_shape if shape == vector> types <type1> <type2> ...Example
lmp -i in.compute_metatomicRegarding determining the output shape
It is no longer feasible to determine it with a dummy system, because different outputs have different requirements on the system... e.g. heat flux need a system with PBC on, and the box size must be larger than the model's interactive range. Thus here I require the user to specify the shape (scalar/vector) and the size (if it's a vector) of their required properties. For users' convenience, we can later have a registry for standard outputs, so that users don't need to input the shape and size for standard outputs.