onnxruntime

[QNN EP] Support float16 BatchNormalization on the HTP backend (#20391)

### Description
- Adds support for float16 BatchNormalization to the HTP backend.
- Fixes float32 support for BatchNormalization on the HTP backend when
`enable_htp_fp16_precision` is enabled.


### Motivation and Context
Support more models on the QNN HTP backend.