[Cherry-pick] Use scaled_dot_product_attention in Wav2vec2/HuBERT's SelfAttention (#3253) #3261
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
…ytorch#3253) Summary: Replace the attention computation with `torch.nn.functional.scaled_dot_product_attention` to improve running efficiency. Pull Request resolved: pytorch#3253 Reviewed By: mthrok Differential Revision: D44800353 Pulled By: nateanl fbshipit-source-id: 41550d868c809099aadbe812b0ebe2c38121efb8
mthrok
approved these changes
Apr 11, 2023
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Outdated suggestions cannot be applied.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.
Summary:
Replace the attention computation with
torch.nn.functional.scaled_dot_product_attentionto improve running efficiency.Pull Request resolved: #3253
Reviewed By: mthrok
Differential Revision: D44800353
Pulled By: nateanl
fbshipit-source-id: 41550d868c809099aadbe812b0ebe2c38121efb8