Speed up SMILES Transformer model inference#17
Open
kmaziarz wants to merge 8 commits into
Open
Conversation
mrwnmsr
approved these changes
Jun 8, 2026
Collaborator
|
decent speedup indeed! |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Our SMILES Transformer model is based on forked and modified code from
opennmt. This PR bundles together several tweaks to that code which don't change model output but significantly speed up inference time. Majority of the changes are related to being more careful about GPU-CPU sync points and avoiding recomputing things unnecessarily. Inference time reduction varies from 25% for a batch size of 1 to nearly 50% for larger batch sizes.