Batch forward method of the EMLE class #39
Conversation
This file contains 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
JMorado
force-pushed
the
feature_batch_predictions
branch
from
800306d to
94ec417
Compare
|
Many thanks for this, much appreciated. I had implement this crudely a while back on a local branch but it makes much more sense to add it now that the base class is batched. I should be able to take a look this afternoon. I mostly want to check any performance hit for supporting batched and non-batched tensors, although I don't think this should be an issue. If it makes more sense to just support batched use in future, then I can adjust the Sire TorchQMForce API for the next Sire release and we can drop the non-batch use for the EMLE models. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Hi,
Building on the changes made to the
forwardmethod ofEMLEBase, this PR introduces a batchedforwardmethod for theEMLEclass. The implementation is designed to be TorchScript-compatible and significantly improves (over 100-fold) the speed of static and induced EMLE predictions for batched use cases.This implementation has been very effective in accelerating some of my workflows/use cases. I’ve made efforts to ensure the changes are backward-compatible, but I’m happy to answer any questions or address any concerns.
Thank you!