Alby M.

That's great! Thank you @felixmusil , very nice to have that available!

Hi @felixmusil, Thanks for the PR. Beyond Simon's point, while I'm happy to merge this, I want to be clear that we dropped the use of pickling for models /...

Actually, also, have you tested that this actually works once this fix is included? I remember there being other things broken with pickling as well... (Another warning: the ability to...

> Running this snippet shows that the results are the same within machine precision. > yes, if you run the failing example above with this fix, it works. Great, thanks...

Hi @felixmusil just curious if the above worked for you or if this is still an issue :slightly_smiling_face:

Hi @felixmusil , I'm seeing a few more commits to this PR— is this still something you are trying to do, or can we close this PR? (Was rebuilding the...

@felixmusil sounds good, I'll take a look at this again soon here for merging. Re multi-GPU support, take a look at this recent issue: https://github.com/mir-group/nequip/issues/210. Basically, unless you are really...

Hi @NicholasHattrup , > ValueError: After eliminating self edges, no edges remain in this system. This error means that for the given system state and cutoff, every single atom has...

Hi @keano130 , This should not be too hard to implement; the main thing is adding the displacement. (Since our edge vectors are calculated from `positions + cell @ periodic_image_number`,...

@keano130 check out the https://github.com/mir-group/nequip/tree/stress branch, which contains a first stab at an implementation (untested so far)