workaround for compile bug#390
Open
sef43 wants to merge 1 commit into
Open
Conversation
Collaborator
Author
|
The failures look to be from torchscript |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
this is a workaround for the issue reported here: openmm/openmm-ml#136
which is a torch compile bug: pytorch/pytorch#178871
Essentially when the model gets torch compiled if the number of atoms is not a multiple of 2 it can end up with an offset (i think deterministic) to the total energy from buggy generated triton code. The forces are not affected, relative energies after compilation are also not affected. The error appears when comparing energy from a non-compiled model with the energy from a compiled model.