Qualcomm AI Engine Direct - Quantizer refine for qat (#6513)

* [Qualcomm AI Engine Direct - Quantizer refine for qat]

- Reorginize qualcomm/quantizer
- Split quantizer/utils.py to
-- qconfig
-- annotators
-- observers directory
- Change coresponding callees
- Rename get_default_Nbit_qnn_ptq_config to get_NaNw_qnn_ptq_config
- Add 16a4w conv test* (It is not compared with original model)

* Fix baed on comments

- Move and rename param_observer.py to per_channel_param_observer.py
- Add todo to merge qconfig

* Add a comment

- Add todo for per_channel_param_observer.py

* [Fix lint]

---------

Co-authored-by: Joey Tsai <chunit@qti.qualcomm.com>