OneDFT: gradient support, atomic-grid models, and build fixes#192
Merged
awvwgk merged 1 commit intowavefunction91:skalafrom Apr 9, 2026
Merged
OneDFT: gradient support, atomic-grid models, and build fixes#192awvwgk merged 1 commit intowavefunction91:skalafrom
awvwgk merged 1 commit intowavefunction91:skalafrom
Conversation
tvogels
changed the title
tvogels
changed the title
tvogels
force-pushed
the
pr/vne3nn_v6_support
branch
from
80356bd to
4668823
Compare
tvogels
changed the title
awvwgk
approved these changes
Apr 9, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR extends OneDFT integration with three main changes:
EXC gradient support — Adds
eval_exc_grad_onedftthrough the full integrator stack (host + device). A new CUDA kernel transforms OneDFT per-component Vxc into the format expected by the existing GGA/mGGA gradient kernels.Atomic-grid model inputs — Models that require per-atom grid features (
atomic_grid_weights,atomic_grid_sizes) are now supported. In multi-rank MPI runs, gathered grid data is reordered from rank-order to atom-order before inference and gradients are reordered back before scatter.Build system fixes — The CMake OneDFT module now guards against duplicate
nlohmann_jsontargets, strips PyTorch-injected-gencodeflags fromCMAKE_CUDA_FLAGS, and correctly propagatesGAUXC_HAS_ONEDFTvia the config header. Loaded TorchScript models are cached to avoid redundant disk reads.Includes unit tests for the atom-reorder permutation logic and a carbon-atom gradient reference test.