Skip to content

Issues: ACEsuit/mace

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

44 Open 248 Closed
44 Open 248 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

cuEq-accelerated MACE gives error for num_interactions=1
#749 opened Dec 13, 2024 by lucasdekam
MACE 0.3.9 can not jit compile model trained with previous versions bug Something isn't working
#741 opened Dec 9, 2024 by lohedges
11
RuntimeError: mat1 and mat2 shapes cannot be multiplied when calling get_potential_energy() bug Something isn't working
#728 opened Dec 2, 2024 by GUANGZChen
14
Unable to start finetuning enhancement New feature or request
#724 opened Nov 29, 2024 by cecilia-hong
14
Python 3.7 (and 3.8?) not supported bug Something isn't working
#699 opened Nov 15, 2024 by MicPellegrino
8
The inconsistent property key for Multihead bug Something isn't working
#692 opened Nov 13, 2024 by MengnanCui
2
Stacked at evaluation at the end of training for multi-GPU and patience termination bug Something isn't working
#677 opened Nov 8, 2024 by dbidoggia
3
Use proper logging instead of print statements enhancement New feature or request
#650 opened Oct 22, 2024 by Andrew-S-Rosen
@vue1999
MACE compile mode test failures with InternalTorchDynamoError and Unsupported exceptions in main bug Something isn't working
#639 opened Oct 15, 2024 by yixian929
1
better default for device used to _save_ model in run_train enhancement New feature or request
#635 opened Oct 11, 2024 by bernstei
2
Model architecture with --model="ScaleShiftMACE" enhancement New feature or request
#633 opened Oct 10, 2024 by wcwitt
1
Error when specifying more e0s then present in training set enhancement New feature or request
#605 opened Sep 23, 2024 by LarsSchaaf
1
universal loss (at least in multi-head-interface branch) does not support per-config weight bug Something isn't working
#558 opened Aug 20, 2024 by bernstei Merge multi-head finetuning + very large training support
Remove e3nn version pin enhancement New feature or request
#555 opened Aug 17, 2024 by Andrew-S-Rosen
12
Move to ruff for linting and formating? enhancement New feature or request
#534 opened Jul 27, 2024 by CompRhys
5
Change stress to virials internally enhancement New feature or request
#527 opened Jul 19, 2024 by ilyes319
Automatically add parameters to optimizer enhancement New feature or request
#525 opened Jul 19, 2024 by LarsSchaaf
Improve plotting script enhancement New feature or request
#524 opened Jul 18, 2024 by ilyes319
Problems with parallelization on CPU (Using LAMMPS) lammps
#520 opened Jul 17, 2024 by MarcoRavalli
1
Segmentation fault during LAMMPS-MACE-CPU run lammps
#519 opened Jul 17, 2024 by fcannizzaro-byte
1
Issue on integrating lammps with MACE potential lammps
#507 opened Jul 8, 2024 by aishwaryo
10
LAMMPS-GPU (mace) installed Failed lammps
#503 opened Jul 5, 2024 by waywaygirl
3
How to use LAMMPS to train a larger system? lammps
#476 opened Jun 20, 2024 by stargolike
6
How to use multi-training without slurm system? multi-gpu
#458 opened Jun 11, 2024 by stargolike
18
select pretrained configs for multihead replay with or without replacement? multi-head
#432 opened May 30, 2024 by bernstei
2
ProTip! Updated in the last three days: updated:>2024-12-10.