[WebNN EP] Add constraints for MatMul#19713
Conversation
|
/azp run ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline |
|
/azp run Big Models,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 |
|
/azp run Windows GPU CI Pipeline,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 |
|
Azure Pipelines successfully started running 2 pipeline(s). |
|
Azure Pipelines successfully started running 7 pipeline(s). |
|
Azure Pipelines successfully started running 9 pipeline(s). |
fdwr
left a comment
fdwr
left a comment
There was a problem hiding this comment.
Approved if we add todo comments to indicate these are temporary workarounds until the XNNPack backend follows the WebNN spec.
|
/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 |
|
/azp run Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline,onnxruntime-binary-size-checks-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed |
|
/azp run ONNX Runtime Web CI Pipeline,Windows x64 QNN CI Pipeline |
|
Azure Pipelines successfully started running 2 pipeline(s). |
|
Azure Pipelines successfully started running 6 pipeline(s). |
|
Azure Pipelines successfully started running 9 pipeline(s). |
|
/azp run Big Models |
|
Azure Pipelines successfully started running 1 pipeline(s). |
fdwr
changed the title
### Description Add constraints to MatMul: - The input must be at least 2D. - CPU backend: The input rank must be the same. - CPU backend: The input shape except for the last two axis must be the same. ### Motivation and Context Prevent regression for some models.
4 participants
Description
Add constraints to MatMul:
Motivation and Context
Prevent regression for some models.