Fix sparse initializer type for SparseToDenseMatMul - #31830
Open
NIKHIL (Nikhi00718) wants to merge 1 commit into
Open
Fix sparse initializer type for SparseToDenseMatMul#31830NIKHIL (Nikhi00718) wants to merge 1 commit into
NIKHIL (Nikhi00718) wants to merge 1 commit into
Conversation
|
Azure Pipelines: There may be pipelines that require an authorized user to comment /azp run to run. |
NIKHIL (Nikhi00718)
marked this pull request as ready for review
August 9, 2026 18:27
|
Azure Pipelines: There may be pipelines that require an authorized user to comment /azp run to run. |
Contributor
|
NIKHIL (@Nikhi00718) please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.
Contributor License AgreementContribution License AgreementThis Contribution License Agreement (“Agreement”) is agreed to by the party signing below (“You”),
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Sparse initializers are currently converted to dense TensorProto values during graph construction, but their NodeArg type is inferred as
tensor(T)instead ofsparse_tensor(T). As a result, a validSparseToDenseMatMulmodel that references a sparse initializer is rejected during graph validation with a type error before the kernel is created.This change preserves the sparse type and shape metadata for sparse initializers both when NodeArgs are created and when initializer types are checked. Runtime materialization already uses the graph's sparse-initializer marker to create a SparseTensor OrtValue, so the existing execution path can handle the model once validation succeeds.
Fixes #31730.
Tests
python -m py_compile onnxruntime/test/python/onnxruntime_test_python_sparse_matmul.pygit diff --checkA native ONNX Runtime build was not available in the Windows environment used to prepare this pull request; the new test is intended for the repository's native CI matrix.