fairchem-core-1.2.0

What’s Changed

New Features / Enhancements

• Do not shadow built in property (#841) @lbluque
• add script to port old equiv2 checkpoint+yaml to hydra version (#846) @misko
• Delete distributed option - Always use DDP (#833) @rayg1234
• Torch compile + export escn (#826) @rayg1234
• Add mean e to escn energy head (#828) @rayg1234
• add run group (#827) @rayg1234
• add option to apply mean to energy (#818) @rayg1234
• fix gemnet scaling factors fit.py and add a test (#819) @misko
• Add check to max num atoms (#817) @misko
• Use abs run_dir paths by default (#820) @rayg1234
• FM-v4 branch into main (#752) @misko
• refactor and deprecate old equiformerv2 (#812) @misko
• Fuse all hydras (#814) @rayg1234
• Rank2 tensor head (#792) @lbluque
• Explicitly initialize weights even if initialization method is "uniform" (#809) @misko
• Activation checkpoint equiformersv2 (#811) @rayg1234
• add resolution flag to escn (#804) @misko

Bug Fixes

• Add inference_only option to trainers (#850) @lbluque
• Sort dbs AseDBDataset (#837) @lbluque
• update to gemnet-oc hydra force head to work with amp (#825) @wood-b
• Load normalizers patch (#824) @lbluque
• load linref and normalizer on cuda device when resuming from checkpoint (#813) @misko