fairchem-core-2.21.0

What’s Changed

• bind config to runner in ray entrypoint (#1995) @lbluque

New Features / Enhancements

• Ray batch serving small improvements (#2006) @zulissimeta
• added mass to AtomicData (#2018) @bkmi
• Allow mixed PBC (#2013) @lbluque
• Unify ray serve (#1931) @lbluque
• Add spatial partitioning for graph parallel atom distribution (#1984) @rayg1234

fairchem-core-2.20.0

What’s Changed

New Features / Enhancements

• [md] store additional properties + update tests (#1976) @mshuaibii
• feat: add benchmark toolkit for comparing inference configs against f… (#1938) @misko
• NPT support (#1972) @mshuaibii
• Add Checkpointing to RelaxRunner (#1951) @lbluque
• Add AllScAIP Model (#1851) @EricZQu
• Allow merging homogeneous batch 1 (#1940) @lbluque
• Expose seed argument in pretrained_mlip.get_predict_unit() to enable control over global random state (#1899) @pzeiger

Bug Fixes

• Regress model attrs patch (#1925) @lbluque
• Remove retain_graph from fairchem torchsim interface (#1924) @CompRhys

Documentation

• satisfy oss requirements (#1950) @mshuaibii

Deprecations

• remove regress_stress/forces and direct_forces properties (#1928) @lbluque
• mitigate unsafe pickle deserialization (#1935) @mshuaibii

Dependencies

• Patch for torchsim interface's change to extras fields (spin and charge no longer core fields) (#1960) @CompRhys
• pip: bump pymatgen from v2025.10.7 to 2026.3.23 (#1922) @dependabot[bot]

fairchem_data_odac-0.1.0

What's Changed

New Features / Enhancements

• Added ODAC25 models to pretrained.json and a package for odac data (#1719) @anuroopsriram
• Add pp_version flag to Vasp input sets (#1699) @Andrew-S-Rosen
• FairchemV2 UMA release 051325 (#1139) @rayg1234

Documentation

• satisfy oss requirements (#1950) @mshuaibii
• more style docs tweaks & typos (#1238) @zulissimeta

fairchem-core-2.19.0

What’s Changed

New Features / Enhancements

• fix(compile): Remove graph break in ChgSpinEmbedding rand_emb path (#1907) @misko

Bug Fixes

• resolve small edge case bugs (#1920) @mshuaibii
• Fix Triton import failed torch-sim (TS) CI. Clean TS interface to avoid for loop and ase. (#1901) @CompRhys
• Fix permute_wigner_inv bwd_dw kernel add more than 128 channel support (#1902) @misko

fairchem-core-2.18.1

What’s Changed

New Features / Enhancements

• md runner abstractions + improvements (#1835) @mshuaibii

fairchem-core-2.18.0

What’s Changed

• Turbo mode by default now gets the UMA 1.2 speed up (previously non default behind execution backend uma_fast_gpu).
• Running turbo mode with MD is now alot smoother and less slowdown from torch recompiles

New Features / Enhancements

• fix nvalchemi version (#1905) @misko
• Consolidate turbo and turbo_umas (#1898) @rayg1234
• Optimize md torch compile (#1892) @misko
• Reduce at higher precision (#1889) @rayg1234
• Upstream TorchSim Interface to prevent CI issues and slippage with fa… (#1895) @lbluque
• Default untrained predictions (#1883) @lbluque
• checkpoint surgery script (#1858) @misko

Bug Fixes

• single atom bug fix and test (#1882) @wood-b

Dependencies

• numpy 2.4 (#1862) @lbluque

fairchem-lammps-0.5.0

What’s Changed

New Features / Enhancements

• Enable Untrained Property Predictions Including Hessians (#1811) @lbluque

fairchem-core-2.17.0

What’s Changed

This release adds ability to predict stress outputs for UMA 1.2 and reduces recompilation issues for the new UMASFastGPU backend due to bugs in torch compile.

• Refactor MLP Energy/EFS Heads with Shared Helper Functions (#1734) @lbluque

New Features / Enhancements

• Enable Untrained Property Predictions Including Hessians (#1811) @lbluque
• Add Hessian matrix calculation support (#1735) @lbluque
• multi-node profiling script (#1845) @rayg1234

fairchem-core-2.16.0

What’s Changed

• UMA-S 1.2 Release!

New Features / Enhancements

• UMA-S 1.2 (#1861) @misko
• Refactor single atoms (#1732) @levineds
• add model id (#1859) @misko
• feat: add MOLE model support to DatasetSpecificMoEWrapper (#1848) @misko
• Add UnifiedRadialMLP for batched radial computation (#1831) @misko
• Umas fast gpu backend (#1826) @misko
• enbable GP for nvidia graphgen (#1791) @rayg1234
• [adsorbml] custom adsorbate support (#1822) @mshuaibii

Bug Fixes

• Disable chan balance compile (#1863) @rayg1234
• Revert 2 commits (#1860) @rayg1234
• Update inference settings (#1857) @wood-b
• Fix data loading imports in benchmarks (#1850) @lbluque
• Add workers arg to from_model_checkpoint (#1844) @rayg1234
• Quaternion-based Wigner D method for fixing y-aligned edges (#1771) @levineds
• Fix omc-is2re-polymorph reducer (#1837) @lbluque
• Revert graphgen v2 pre partitioning (#1838) @rayg1234
• add preemption state for runners that don't create it (#1834) @mshuaibii
• Fix per atom MAE bug (#1825) @EricZQu

Tests

• use uma-1p1 instead of uma-1 in tests (#1856) @lbluque

fairchem-core-2.15.0

What’s Changed

New Features / Enhancements

• Generic MD Runner (#1782) @mshuaibii
• nvidia graph gen support (#1737) @mshuaibii
• add fp64 inference setting (#1789) @levineds
• Execution backend (#1802) @misko
• embeddings update (#1765) @wood-b
• composition dropout (#1767) @wood-b
• Fuse the edge envelope into wigner_mapping_inv instead of applying on each layer (#1792) @misko
• channel charge and spin (#1768) @wood-b

Bug Fixes

• Fix flaky unit tests (#1805) @levineds
• bug fix (#1812) @wood-b
• [ray] unique dashboard + worker ports for multiple local clusters (#1787) @mshuaibii

Dependencies

• numpy 1.26+ compatibility (#1738) @bkmi