[WebNN EP] Enable Cast op for WebNN CPU backend

[Honry]

WebNN TFLite backend supports cast op but doesn't support casting to uint64 data type.

[Honry]

@guschmue, @fs-eire, @fdwr, PTAL, thanks!

[guschmue]

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

[guschmue]

/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

[guschmue]

/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]

Azure Pipelines successfully started running 3 pipeline(s).

[azure-pipelines]

Azure Pipelines successfully started running 9 pipeline(s).

[azure-pipelines]

Azure Pipelines successfully started running 7 pipeline(s).

[Honry]

@guschmue, could you please retrigger the failure CIs? Thanks!

[guschmue]

/azp run Linux GPU CI Pipeline,Linux GPU CI Pipeline (Linux_Test Linux_Test)

[azure-pipelines]

Azure Pipelines successfully started running 1 pipeline(s).

[guschmue]

Looks the 'Linux GPU CI Pipeline (Linux_Test Linux_Test)' pipeline is no more.
Can you merge with main to get that change ?

[Honry]

Looks the 'Linux GPU CI Pipeline (Linux_Test Linux_Test)' pipeline is no more. Can you merge with main to get that change ?

Do you mean rebasing this PR to latest main? I see all CIs pass now.

[fdwr]

👍 Hmm, that's surprising, because TF has tensorflow.uint64, unless TF Lite is more limited.