[Torch] Enable dtype inference for operations with list-type operands #4406
+36
−3
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Outdated suggestions cannot be applied.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 type inference task consists of two subtasks: shape inference and dtype inference. For operations such as
torch.aten.cat, shape inference works correctly, but dtype inference fails. This commit fixes that issue.Enable loop unrolling within
DtypeCalculateOpregions to support dtype inference for operations with list-type operands, such astorch.aten.cat. This commit extendsFullyUnrollPrimLooppattern to also unroll loops contained inDtypeCalculateOpregions, enabling the simplification pass to promote dtype information through operations like torch.aten.cat.