Update knn_datastore.py #9
Merged
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
chang torch.zeros(...).to(queries.device) to torch.zeros(..., device=queries.device)
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Outdated suggestions cannot be applied.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.
change
chang
torch.zeros(...).to(queries.device)totorch.zeros(..., device=queries.device)reason
.to() is slow because it needs to transfer data from main memory to GPU memory. For large tensors, creating them directly in GPU memory is much faster.
result
After changing these two lines, knn-mt and adaptive knn-mt can be much faster(about 3x ~ 4x), and the inference speed will not differ much from NMT.