Optimize temporal dropout using vectorized masked_fill#51
Open
dearabhin wants to merge 1 commit into
Open
Conversation
meta-cla
Bot
added
the
CLA Signed
ahmedemam992
approved these changes
Apr 23, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR optimizes the temporal dropout implementation in
tribev2/model.pyto remove a cross-device memory transfer and CPU bottleneck.Currently, the dropout mask is generated using a Python
forloop over the batch dimension, withtorch.randdefaulting to the CPU. This breaks the CUDA execution graph for every item in the batch.This patch vectorizes the operation directly on the GPU using
masked_fill_, which improves training speed and memory efficiency.Resolves #50