Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of torch-sim-atomistic

torch-sim-atomistic - v0.3.0

Thank you to everyone who contributed to this release! @t-reents, @curtischong, and @CompRhys did great work squashing an issue with SimState concatenation. @curtischong continued his crusade to type and improve the TorchSim API. @orionarcher, @kianpu34593, and @janosh all made contributions that continue to improve package quality and usability. 🚀

What's Changed

🛠 Enhancements

  • Define attribute scopes in SimStates by @curtischong, @CompRhys, @orionarcher in #228
  • Improve typing of ModelInterface by @curtischong, @CompRhys in #215
  • Make system_idx non-optional in SimState by @curtischong in #231
  • Add new states when the max_memory_scaler is updated by @kianpu34593 in #222
  • Rename batch to system by @curtischong in #217, #233

🐛 Bug Fixes

  • Initial fix for concatenation of states in InFlightAutoBatcher by @t-reents in #219
  • Finish fix for SimState concatenation by @t-reents and @curtischong in #232
  • Fix broken code block in low-level tutorial by @CompRhys in #226
  • Update metatomic checkpoint to fix tests by @curtischong in #223
  • Fix memory scaling in determine_max_batch_size by @t-reents, @janosh in #212

📖 Documentation

  • Update README plot with more models by @orionarcher in #236, #237
  • Update citation.cff by @CompRhys in #225

Full Changelog: https://github.com/Radical-AI/torch-sim/compare/v0.2.2...v0.3.0

- Python
Published by orionarcher 12 months ago

torch-sim-atomistic - v0.2.2

Big thank you to @t-reents and @mstapelberg 🙏 who did an outstanding job first identifying and then fixing several implementation differences between ASE and torch-sim FIRE relaxation. Running fire, unit_cell_fire or frechet_cell_fire with md_flavor="ase_fire" (the new default) is now expected to match the corresponding ASE geometry optimization trajectory. If you encounter any remaining differences, please open an issue!

What's Changed

🛠 Enhancements

  • Add pbar: bool | dict = False keyword to optimize, integrate, static runners by @YutackPark in https://github.com/Radical-AI/torch-sim/pull/181
  • Remove unbatched code by @CompRhys in https://github.com/Radical-AI/torch-sim/pull/206

🐛 Bug Fixes

  • Fix installing conflicting optional dependencies via uv in pyproject.toml by @curtischong in https://github.com/Radical-AI/torch-sim/pull/188
  • Fix Fairchem import possibly failing silently until it reaches setup_imports() by @janosh in https://github.com/Radical-AI/torch-sim/pull/187
  • Fix unit and frechet cell FIRE optimizers not rescaling atom positions after each cell update by @janosh in https://github.com/Radical-AI/torch-sim/pull/199
  • metatensor models have been renamed to metatomic models by @Luthaf in https://github.com/Radical-AI/torch-sim/pull/205
  • Fix discrepancies between FIRE optimisations in ASE and torch-sim by @t-reents in https://github.com/Radical-AI/torch-sim/pull/203

📖 Documentation

  • stricter dead link checks: swap markdown-link-check for lychee by @janosh in https://github.com/Radical-AI/torch-sim/pull/194

🚧 CI

  • Test stresses in the ase consistency test. by @CompRhys in https://github.com/Radical-AI/torch-sim/pull/190

🧪 Tests

  • Directly compare ASE vs TorchSim Frechet cell FIRE relaxation by @AdeeshKolluru in https://github.com/Radical-AI/torch-sim/pull/146
  • more robust ordering checks for ts.static by @janosh in https://github.com/Radical-AI/torch-sim/pull/196
  • Difference in ASE FrechetCellFilter vs Torch-Sim (both md_flavors) + enhanced convergence testing by @mstapelberg in https://github.com/Radical-AI/torch-sim/pull/200
  • generate_force_convergence_fn default include_cell_forces to True (matching ASE) by @janosh in https://github.com/Radical-AI/torch-sim/pull/209

🏥 Package Health

  • Top-level SimState by @janosh in https://github.com/Radical-AI/torch-sim/pull/195
  • Pin Metatensor as tests broke with Metatrain release by @CompRhys in https://github.com/Radical-AI/torch-sim/pull/204

🧹 Linting

  • Remove debug print statements from tests and replace them with assertions by @janosh in https://github.com/Radical-AI/torch-sim/pull/210

New Contributors

  • @t-reents made their first contribution in https://github.com/Radical-AI/torch-sim/pull/203

Full Changelog: https://github.com/Radical-AI/torch-sim/compare/v0.2.1...v0.2.2

- Python
Published by janosh about 1 year ago

torch-sim-atomistic - v0.2.1

What's Changed

💥 Breaking Changes

  • Remove higher level model imports by @CompRhys in https://github.com/Radical-AI/torch-sim/pull/179 ### 🛠 Enhancements
  • Add per atom energies and stresses for batched LJ by @abhijeetgangan in https://github.com/Radical-AI/torch-sim/pull/144
  • throw error if autobatcher type is wrong by @orionarcher in https://github.com/Radical-AI/torch-sim/pull/167 ### 🐛 Bug Fixes
  • Mattersim fix tensors on wrong device (CPU->GPU) by @orionarcher in https://github.com/Radical-AI/torch-sim/pull/154
  • fix npt_langevin by @jla-gardner in https://github.com/Radical-AI/torch-sim/pull/153
  • Make sure to move data to CPU before calling vesin by @Luthaf in https://github.com/Radical-AI/torch-sim/pull/156
  • Fix virial calculations in optimizers and integrators by @janosh in https://github.com/Radical-AI/torch-sim/pull/163
  • Pad memory estimation by @orionarcher in https://github.com/Radical-AI/torch-sim/pull/160
  • Refactor sevennet model by @YutackPark in https://github.com/Radical-AI/torch-sim/pull/172
  • io optional dependencies in pyproject.toml by @curtischong in https://github.com/Radical-AI/torch-sim/pull/185
  • Fix column->row cell vector mismatch in integrators by @CompRhys in https://github.com/Radical-AI/torch-sim/pull/175 ### 📖 Documentation
  • (tiny) add graph-pes to README by @jla-gardner in https://github.com/Radical-AI/torch-sim/pull/149
  • Better module fig by @janosh in https://github.com/Radical-AI/torch-sim/pull/168 ### 🚀 Performance
  • More efficient Orb state_to_atoms_graph calculation by @AdeeshKolluru in https://github.com/Radical-AI/torch-sim/pull/165 ### 🚧 CI
  • Refactor test_math.py and test_transforms.py by @janosh in https://github.com/Radical-AI/torch-sim/pull/151 ### 🏥 Package Health
  • Try out hatchling for build vs setuptools by @CompRhys in https://github.com/Radical-AI/torch-sim/pull/177 ### 📦 Dependencies
  • Bump mace-torch to v0.3.12 by @janosh in https://github.com/Radical-AI/torch-sim/pull/170
  • Update metatrain dependency by @Luthaf in https://github.com/Radical-AI/torch-sim/pull/186 ### 🏷️ Type Hints
  • Add torch_sim/typing.py by @janosh in https://github.com/Radical-AI/torch-sim/pull/157

New Contributors

  • @Luthaf made their first contribution in https://github.com/Radical-AI/torch-sim/pull/156
  • @YutackPark made their first contribution in https://github.com/Radical-AI/torch-sim/pull/172
  • @curtischong made their first contribution in https://github.com/Radical-AI/torch-sim/pull/185

Full Changelog: https://github.com/Radical-AI/torch-sim/compare/v0.2.0...v0.2.1

- Python
Published by janosh about 1 year ago

torch-sim-atomistic - v0.2.0

Bug Fixes 🐛

  • Fix integrate reporting kwarg to arg error, https://github.com/Radical-AI/torch-sim/issues/113 (raised by @hn-yu)
  • Allow runners to take large initial batches, https://github.com/Radical-AI/torch-sim/issues/128 (raised by @YutackPark)
  • Add Fairchem model support for PBC, https://github.com/Radical-AI/torch-sim/issues/111 (raised by @ryanliu30)

Enhancements 🛠

  • [breaking] Rename HotSwappingAutobatcher to InFlightAutobatcher and ChunkingAutoBatcher to BinningAutoBatcher, https://github.com/Radical-AI/torch-sim/pull/143 @orionarcher
  • Support for Orbv3, https://github.com/Radical-AI/torch-sim/pull/140, @AdeeshKolluru
  • Support metatensor models, https://github.com/Radical-AI/torch-sim/pull/141, @frostedoyster @Luthaf
  • Support for graph-pes models, https://github.com/Radical-AI/torch-sim/pull/118 @jla-gardner
  • Support MatterSim and fix ASE cell convention issues, https://github.com/Radical-AI/torch-sim/pull/112 @CompRhys
  • Implement positions only FIRE optimization, https://github.com/Radical-AI/torch-sim/pull/139 @abhijeetgangan
  • Allow different temperatures in batches, https://github.com/Radical-AI/torch-sim/pull/123 @orionarcher
  • FairChem model updates: PBC handling, test on OMat24 e-trained model, https://github.com/Radical-AI/torch-sim/pull/126 @AdeeshKolluru
  • FairChem model fromdatalist support, https://github.com/Radical-AI/torch-sim/pull/138 @ryanliu30
  • New correlation function module, https://github.com/Radical-AI/torch-sim/pull/115 @stefanbringuier

Documentation 📖

  • Imoved model documentation, https://github.com/Radical-AI/torch-sim/pull/121 @orionarcher
  • Plot of TorchSim module graph in docs, https://github.com/Radical-AI/torch-sim/pull/132 @janosh

House-Keeping 🧹

  • Only install HF for fairchem tests, https://github.com/Radical-AI/torch-sim/pull/134 @CompRhys
  • Don't download MBD in CI, https://github.com/Radical-AI/torch-sim/pull/135 @orionarcher
  • Tighten graph-pes test bounds, https://github.com/Radical-AI/torch-sim/pull/143 @orionarcher

- Python
Published by orionarcher over 1 year ago

torch-sim-atomistic - v0.1.0

Initial release introducing torch-sim, a next-generation open-source atomistic simulation engine for the MLIP era.

- Python
Published by orionarcher over 1 year ago