Add an auto_expand option to SinusoidalPositionalEmbedding
#5555
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
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Outdated suggestions cannot be applied.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.
Before submitting
No; I'm discussing it in a Meta internal chat.
No; I didn't find docs in the repo.
Not applicable.
What does this PR do?
In the fairseq SinusoidalPositionalEmbedding module, when the input length exceeds the number of pre-computed embeddings, the embeddings are expanded and written back to the weights field of the module.
However, mutating fields of a module can cause subtle bugs in multithreading environments.
This diff provides an auto_expand option to SinusoidalPositionalEmbedding to control whether the expanded embeddings are written back to the module.
The default is set to True, so the default behavior is not changed.
If you encounter bugs in multithreading environments, set auto_expand=False.
PR review
Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.
Did you have fun?
Make sure you had fun coding 🙃