bfloat16 support for monomer models#930
Open
oliverdutton wants to merge 1 commit intogoogle-deepmind:mainfrom
Open
bfloat16 support for monomer models#930oliverdutton wants to merge 1 commit intogoogle-deepmind:mainfrom
oliverdutton wants to merge 1 commit intogoogle-deepmind:mainfrom
Conversation
Open
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Matches the casting in multimer for monomers
Runtime speedup of ~1.8x and reduces peak memory usage ~2x (for 759 residue protein, model_5)
Here's a colab link showing runtime improvement and no significant change in prediction output by visual inspection
No effect on default usage as bfloat16 turned off.
I've checked a profile on tensorboard and there's no float32 gemms with significant runtime.