[Delivery] Win ARM64 wheels + QNN

Describe the feature request

Creating general issue to track ONNX DX on Windows ARM platform, particularly QNN.

Main problems:

• Lack of pre-build arm libs/binaries/wheels.

  The necessity of building from source even our own tools create huge obstacles and difficulties for DX. Launching basic SDK demos and examples like this requires a lot of time and mental resources. Days at best, instead of minutes or hours at worse.

• Necessity to mix/switch x64 and Arm environments to run basic demos.

  This is partially a result of previous problem. Qualcomm SDK and onnxruntime demos for QNN are not arm friendly. Some demos to the point of impossibility of execution on arm machine even with x64 emulation (see lack of AVX instructions emulation).

• Feels like a development kit rather than a development device.

  Due to the above issues, the DX with Python and ML feels like you are still using an experimental device and requires an additional x64 machine for development. Which is not the case for example for NodeJS/Web development, because everything is cross-platform or arm native already.

Opportunities to improve current state:

• Fix lack of python wheels for onnx toolkits and runtimes.
  • onnxruntime - @adrianlizarraga
  • onnxruntime-extensions - @wenbingl
  • onnx
• Make sure our demos are arm ready with no manual build of libraries.
  • onnxruntime-inference-examples
  • ... add more
• Make Olive toolkit available for win arm
  • Connect efforts of Win AI team and Olive team (Olive QNN optimizations)
• Invest to presence of 3rd party python libs on win arm
  • torch
  • numpy
  • ... add more
• Improve x64 emulator to support modern CPU instructions
  This can be a backup plan to cover some gaps can't be covered by ourself.

Describe scenario use case

The ability to use Windows ARM64 as main machine for ML development, not only as inference target.

Start with the linked onnxruntime issue 19161 and the onnxruntime-inference-examples entry point at c_cxx/QNN_EP/mobilenetv2_classification, then review the linked onnxruntime-extensions and Olive issues. This umbrella issue has no single file or test; completion would require defined ARM64 wheel and demo targets to be agreed and delivered.