Dwayne Robinson

/azp run Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-amd-gpu-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,onnxruntime-binary-size-checks-ci-pipeline,Big Models

/azp run Linux Android Emulator QNN CI Pipeline

/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline,ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux CPU Minimal...

/azp run Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-amd-gpu-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,onnxruntime-binary-size-checks-ci-pipeline,Big Models

/azp run Linux Android Emulator QNN CI Pipeline

> This branch should not be merged until onnx v1.17 is ready. Thanks for confirmation. Ok, will defer merging. So then for any models that need the shape inference logic...

> For MeanVarianceNormalization, adding an epsilon attribute makes sense. @gramalingam: Concur. We encountered the missing epsilon while implementing the [Chromium WebNN backend atop ORT](https://chromium-review.googlesource.com/c/chromium/src/+/6758777). ONNX's other normalization operators have an...

### TLDR Propose doc update: ```diff axis - INT (default is '-1'): Describes the dimension Softmax will be performed on. Negative value means counting dimensions from the back. Accepted range...

> The root cause is that DML EP can't find kernels for QLinearSoftmax and QLinearLeakyRelu. That's some [non-ONNX contrib op](https://github.com/microsoft/onnxruntime/blob/main/docs/ContribOperators.md#com.microsoft.QLinearSoftmax) that DirectML doesn't know about (see [operator registration](https://github.com/microsoft/onnxruntime/blob/main/onnxruntime/core/providers/dml/DmlExecutionProvider/src/Operators/OperatorRegistration.cpp#L739C1-L739C90)). So the...

> Both the CPU and DML EPs are registered for LeakyRelu and Softmax, which are not supported `LeakyRelu` and `Softmax` are registered by the DML EP. https://github.com/microsoft/onnxruntime/blob/main/onnxruntime/core/providers/dml/DmlExecutionProvider/src/Operators/OperatorRegistration.cpp#L1061-L1062. `QLinearSoftmax` and `QLinearLeakyRelu`...