[Feature] remove an 'assert' statement in favor of a 'raise' statement to make MultiScaleDeformableAttention compatible with torch.compile()#3126
Open
isaacfinberg wants to merge 2 commits intoopen-mmlab:mainfrom
Conversation
|
+1, this is a blocker for me as well |
|
+1 |
|
+1, Would love for this to be fixed |
|
+1 would be great to see this fixed :) |
|
+1 would be great to have this fixed! |
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.
Motivation
The goal is to make MultiScaleDeformableAttention compatible with torch.compile().
Modification
The only modification is to change an assert statement to a raise statement and add an error message.
BC-breaking (Optional)
N/A
Use cases (Optional)
The use case is using torch.compile() to make training and inference faster.
Checklist
Before PR:
After PR: