[Cherry-pick] Use scaled_dot_product_attention in WavLM attention (#3252, #3265) #3264
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Outdated suggestions cannot be applied.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.
Summary:
Fix #3219.
torch.nn.MultiheadAttention
will throw an error iftorch.no_grad()
and mask are both given. The pull request fixes it by replacing the forward method withtorch.nn.functional.scaled_dot_product_attention
.Pull Request resolved: #3252
Reviewed By: mthrok
Differential Revision: D44798634
Pulled By: nateanl
fbshipit-source-id: abfa7fb84b7bd71848a92ab26da5a5f0f095c665