Skip to content

[WebNN] Fix bug in int64 data type support validation#26169

Merged
fdwr merged 2 commits into
microsoft:mainfrom
Honry:fix-int64-bug
Sep 29, 2025
Merged

[WebNN] Fix bug in int64 data type support validation#26169
fdwr merged 2 commits into
microsoft:mainfrom
Honry:fix-int64-bug

Conversation

@Honry

@Honry Honry commented Sep 26, 2025

Copy link
Copy Markdown
Contributor

Only allows int64 data type when current WebNN context totally doesn't support int64 but support int32.

Only allows int64 data type when current WebNN context totally
doesn't support int64 but support int32.
@Honry

Honry commented Sep 26, 2025

Copy link
Copy Markdown
Contributor Author

@fdwr, @guschmue, PTAL, thanks!

fdwr
fdwr previously approved these changes Sep 26, 2025

@fdwr fdwr left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Only allows int64 data type when current WebNN context totally doesn't support int64 but support int32

Can you explain the nature of the bug more, and which Chromium backend or ORT EP encounters the issue?

Comment thread onnxruntime/core/providers/webnn/builders/helper.cc Outdated
@fdwr

fdwr commented Sep 26, 2025

Copy link
Copy Markdown
Contributor

/azp run ONNX Runtime Web CI Pipeline,Windows GPU CI Pipeline,Linux Android Emulator QNN CI Pipeline,Windows GPU WebGPU CI Pipeline,Windows OpenVINO CI Pipeline

@fdwr

fdwr commented Sep 26, 2025

Copy link
Copy Markdown
Contributor

/azp run Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,Windows ARM64 QNN CI Pipeline,Windows CPU CI Pipeline

@fdwr

fdwr commented Sep 26, 2025

Copy link
Copy Markdown
Contributor

/azp run Windows GPU CUDA CI Pipeline,Windows GPU DML CI Pipeline,Windows GPU Doc Gen CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI

@fdwr

fdwr commented Sep 26, 2025

Copy link
Copy Markdown
Contributor

/azp run Windows GPU TensorRT CI Pipeline,onnxruntime-binary-size-checks-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,Windows x64 QNN CI Pipeline,Big Models

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 1 pipeline(s).

@fdwr

fdwr commented Sep 26, 2025

Copy link
Copy Markdown
Contributor

/azp run Test Linux CUDA x64 Release,Test Linux TensorRT x64 Release,web_Debug / build_onnxruntime_web,web_Release / build_onnxruntime_web

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 2 pipeline(s).

@azure-pipelines

Copy link
Copy Markdown
No pipelines are associated with this pull request.

1 similar comment
@azure-pipelines

Copy link
Copy Markdown
No pipelines are associated with this pull request.

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 2 pipeline(s).

@Honry

Honry commented Sep 26, 2025

Copy link
Copy Markdown
Contributor Author

Only allows int64 data type when current WebNN context totally doesn't support int64 but support int32

Can you explain the nature of the bug more, and which Chromium backend or ORT EP encounters the issue?

Currently we only fallback int64 data type to int32 for the backend that totally doesn't support int64. But for some other backends, e.g. TFLite, there're partial ops that don't support int64 (e.g. ScatterND's indices only supports int32), current code doesn't fallback these ops and still passes int64 indices to scatterND, then it will throw error.

@guschmue guschmue added the ep:WebNN WebNN execution provider label Sep 26, 2025

@fdwr fdwr left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

👍

Comment thread onnxruntime/core/providers/webnn/builders/helper.cc
@fdwr

fdwr commented Sep 27, 2025

Copy link
Copy Markdown
Contributor

/azp run ONNX Runtime Web CI Pipeline,Windows GPU CI Pipeline,Linux Android Emulator QNN CI Pipeline,Windows GPU WebGPU CI Pipeline,Windows OpenVINO CI Pipeline

@fdwr

fdwr commented Sep 27, 2025

Copy link
Copy Markdown
Contributor

/azp run Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,Windows ARM64 QNN CI Pipeline,Windows CPU CI Pipeline

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 1 pipeline(s).

@fdwr

fdwr commented Sep 27, 2025

Copy link
Copy Markdown
Contributor

/azp run Windows GPU CUDA CI Pipeline,Windows GPU DML CI Pipeline,Windows GPU Doc Gen CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI

@fdwr

fdwr commented Sep 27, 2025

Copy link
Copy Markdown
Contributor

/azp run Windows GPU TensorRT CI Pipeline,onnxruntime-binary-size-checks-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,Windows x64 QNN CI Pipeline,Big Models

@fdwr

fdwr commented Sep 27, 2025

Copy link
Copy Markdown
Contributor

/azp run Test Linux CUDA x64 Release,Test Linux TensorRT x64 Release,web_Debug / build_onnxruntime_web,web_Release / build_onnxruntime_web

@azure-pipelines

Copy link
Copy Markdown
No pipelines are associated with this pull request.

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 2 pipeline(s).

@azure-pipelines

Copy link
Copy Markdown
No pipelines are associated with this pull request.

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 2 pipeline(s).

@fdwr

fdwr commented Sep 28, 2025

Copy link
Copy Markdown
Contributor

Retrying failed "Windows ARM64 QNN CI Pipeline".

@fdwr fdwr merged commit 710856f into microsoft:main Sep 29, 2025
91 of 93 checks passed
fs-eire pushed a commit that referenced this pull request Oct 24, 2025
Only allows int64 data type when current WebNN context totally doesn't
support int64 but support int32.
naomiOvad pushed a commit to naomiOvad/onnxruntime that referenced this pull request Nov 2, 2025
Only allows int64 data type when current WebNN context totally doesn't
support int64 but support int32.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ep:WebNN WebNN execution provider

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants