Fix beam search generation for GPT2 and T5 on model parallelism #9219
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Outdated suggestions cannot be applied.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.
What does this PR do?
This PR fixes beam search generation crash when the model layers are distributed on several devices (model parallelism). I have also added a test which showcase the bug on master and pass with the provided fix. Fixes issue #9200
This is my first contribution to Transformers, so please let me know if something seems wrong or can be improved! The added test doesn't actually test anything at the moment, just raises an error on master. Looking forward to some feedback on how you'd like to see that.
Before submitting
Pull Request section?
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
@LysandreJik
@alexorona
@patrickvonplaten