* trim trailing whitespace

* fix `.cmake-format.py`

* revert npu ut changes, avoid npu ci error

* fix bug in PostTrainingProgram for certain cases

* fix bug in PostTrainingQuantizationProgram for not full quantization case

* fix coverage ci

* add new ptq method ptf

* add post training quantization mobilenetv1 test for ptf

* add post training quantization mobilenetv1 test for ptf test=allcases

* use yapf to format all python file

* yapf exclude two unittests file for they rely on writing and reading file, and format will break them

* disable diff_py_file because too many diff files cause command following failed

* add adaround post-quant method

* add some op for full_quantization

* make post training quant API support dataloader

* fix single card 8 unittests in new executor

* fix

* fix

* Support sub graph quant-post

* refine ptq according comments
* reuse the module to calculate kl threshold

* Support converting the model from fp32 to fp16

post quantize support insert fake_quantize_dequantize node before the OPs that will be used in VIS's faceid models (#30659)

test=develop

* Collect weight threshold of lstm, test=develop

* Remove the cache in post_traning_quantization, test=develop

* Conv2d_transpose and mul support channnelwise quantization, test=develop
* Skip collecting out threshold for output tensor of which the type is not fp32 or fp64, test=develop
* Fix error in test_user_defined_quantization, test=develop
* Add depthwise_conv_bn_fuse, test=develop
* Add conv_transpose_bn_fuse_pass for post_training_quant, test=develop

* Save output threshold by argname_index, test=develop

* Post_training_quantization supports optimize model by fusing, test=develop

* Weight quantization support channel_wise_abs_max method to achieve higher accuracy

* Collect output scale for quantized op and fused op
* Post_training_quantizaion sets batch_generator to support lod tensor

* Post_training_quantizaion supports min_max methon