add provider_options in onnxruntime.InferenceSession

[xieofxie]

Is your feature request related to a problem? Please describe.
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...].

We only have provider and provider_options, but we also need to config provider_options in some scenarios

https://onnxruntime.ai/docs/execution-providers/QNN-ExecutionProvider.html#running-a-quantized-model-on-windows-arm64-onnxruntime-qnn-version--1180

Describe the solution you'd like.
A clear and concise description of what you want to happen.

Add this to

diffusers/src/diffusers/pipelines/onnx_utils.py

Line 78 in 4f3ec53

return ort.InferenceSession(path, providers=[provider], sess_options=sess_options)

And also pass it from pipeline creation

Describe alternatives you've considered.
A clear and concise description of any alternative solutions or features you've considered.

Additional context.
Add any other context or screenshots about the feature request here.