Add ConstantArgument support to fx_import #4244
Merged
Conversation
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
penguin-wwy
reviewed
Jun 30, 2025
|
@stellaraccident plz review this |
penguin-wwy
reviewed
Jun 30, 2025
stellaraccident
approved these changes
Jun 30, 2025
|
Looks like test are failing. Let's talk about this if it is due to a too old version of pt in the CI. |
penguin-wwy
approved these changes
Jul 1, 2025
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Outdated suggestions cannot be applied.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.
This PR will fix the following issue:
fx_importer NotImplementedError: MultiheadAttention layer with NeedWeight = false
The following error was raised before this fix:
Python Error: NotImplementedError: OutputKind.USER_OUTPUT for <class
'torch.export.graph_signature.ConstantArgument'>: ConstantArgument(name='',
value=None)
This occurs for an exported MultiheadAttention layer with "NeedWeight = false" which means weights are not going to be returned by the layer. So, the second output attn_output_weights will be None in this case.