Bump matgl from 2.0.6 to 2.1.1

[dependabot]

Bumps matgl from 2.0.6 to 2.1.1.

Release notes

Sourced from matgl's releases.

v2.1.1

• Merged TensorNet (PyG) and TensorNetWarp into a single TensorNet class with optional warp acceleration (use_warp parameter; auto-detected when nvalchemi-toolkit-ops is installed).
• Moved warp-accelerated TensorEmbedding and TensorNetInteraction layers to matgl.layers._embedding_warp and matgl.layers._graph_convolution_warp.
• Made nvalchemiops an optional dependency throughout: _pymatgen_pyg, _ase_pyg, and warp layer imports all fall back gracefully to pymatgen-based neighbor list construction when the package is absent.

v2.1.0

• Bug fix for accidental change of default backend.
• Training module updated for QET support.

v2.0.9

• Bug fix for missing Atoms2Graph export.

v2.0.8

• Bug fix for missing Atoms2Graph export.

v2.0.7

• Refactored PyG TensorNet embedding and interaction blocks to pure PyTorch for improved compatibility. (@​kenko911)
• Improved handling of stress units in PESCalculator. (@​kenko911)
• Enabled returning intermediate crystal features from CHGNet and TensorNet models. (@​bowen-bd)
• Added GPU-accelerated neighbor list construction and improved CUDA neighbor list performance and retry logic. (@​zubatyuk)
• Integrated NVIDIA TensorNet Warp CUDA kernels into the main branch. (@​atulcthakur, @​zubatyuk)
• Improved QET training support via updates to Atoms2Graph, collate_fn_pes, and MGLDataset (including include_ref_charge). (@​kenko911)
• Documentation updates for QET, including references and DOI links. (@​kenko911)

Changelog

Sourced from matgl's changelog.

2.1.1

• Merged TensorNet (PyG) and TensorNetWarp into a single TensorNet class with optional warp acceleration (use_warp parameter; auto-detected when nvalchemi-toolkit-ops is installed).
• Moved warp-accelerated TensorEmbedding and TensorNetInteraction layers to matgl.layers._embedding_warp and matgl.layers._graph_convolution_warp.
• Made nvalchemiops an optional dependency throughout: _pymatgen_pyg, _ase_pyg, and warp layer imports all fall back gracefully to pymatgen-based neighbor list construction when the package is absent.

2.1.0

• Bug fix for accidental change of default backend.
• Training module updated for QET support.

2.0.9

• Bug fix for missing Atoms2Graph export.

2.0.7

• Refactored PyG TensorNet embedding and interaction blocks to pure PyTorch for improved compatibility. (@​kenko911)
• Improved handling of stress units in PESCalculator. (@​kenko911)
• Enabled returning intermediate crystal features from CHGNet and TensorNet models. (@​bowen-bd)
• Added GPU-accelerated neighbor list construction and improved CUDA neighbor list performance and retry logic. (@​zubatyuk)
• Integrated NVIDIA TensorNet Warp CUDA kernels into the main branch. (@​atulcthakur, @​zubatyuk)
• Improved QET training support via updates to Atoms2Graph, collate_fn_pes, and MGLDataset (including include_ref_charge). (@​kenko911)
• Documentation updates for QET, including references and DOI links. (@​kenko911)

Commits

• 299148f Update changelog and version.
• 131be0e Some cleanup.
• b4a4266 Fix lint errors and coverage upload.
• dd311d8 Try to fix test errors with warp.
• 6537747 Fix mypy errors.
• a86abf5 Make warwp and nvalchemiops optional in tests.
• 8f05ee9 Refactor warp implementations.
• f304284 Updated workflows.
• f78419c Make sure workflows are tested with and without warp.
• e5401ee Update uv.lock.
• Additional commits viewable in compare view