Performance Improvement: Offloading IOAdapter Resize and FlowFormer++ Compute Weight to CUDA #58
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
|
Thank you for the PR. Could you also update the compute_weight function in flowformer and matchflow models? |
|
Can you also add the argument indexing="ij" in torch.meshgrid to avoid warnings? |
hmorimitsu
approved these changes
Feb 21, 2024
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Outdated suggestions cannot be applied.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
This pull request introduces a significant performance improvement by offloading the
resizeoperation in IOAdapter and thecompute_weightoperation in FlowFormer++ to CUDA, whenever CUDA is available. This change aims to reduce CPU usage substantially and leverage GPU acceleration for enhanced processing speed.Changes
resizemethod in IOAdapter to detect CUDA availability and execute on GPU when possible.compute_weightfunction to perform computations on CUDA instead of the CPU.