Notify failure during torch-to-tosa when AtenEmptyMemoryFormat receives a tensor with a dimension of size zero #4353
+19
−0
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
|
@sahas3 @Hanumanth04 Can you take a look and necessary reviewers? |
sahas3
approved these changes
Oct 27, 2025
test/Conversion/TorchToTosa/torch-backend-to-tosa-backend-pipeline.mlir
Outdated
Show resolved
Hide resolved
… receives a tensor with a dimension of size zero
hariprasadravi
force-pushed
the
fixEmptyMemoryFormatUpstream
branch
from
dad20ea to
f32a4e6
Compare
|
LGTM. Thanks for making this change, Hari. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
The lowering for
torch.aten.empty.memory_formatproduces a non-conformanttosa.constwhen the output!torch.vtensorhas a zero-sized dimension. This fix detects this case and reports a failure, preventing the generation of invalid IR. This issue was first observed in the SAM2 image predictor model.