* support ernie trt-int8 for inference

* fix reshape

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

* upgrade comment string to raw string

* fix string in

* fix string with ' '

* revert update on comments

* upgrade only necessary

* fix sample code checker

* fix comments with '''

* Add test attribute in channelwise_quant op, 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

* Remove the output for moving_average_abs_max_scale op, test=develop

* saving inference model for user defined quantization model

* saving inference model for user defined quantization model

* fixed ci coverage

* Save output threshold by argname_index, test=develop

* add user defined func test=develop

* update test=develop

* update test=develop

* fix name conflicts test=develop

* add unittest test=develop

* change 2018 to 2020 test=develop

* add comment test=develop

* add comment for function test=develop

* fix details test=develop

* fix details test=develop

[Fix bug] Init scale node in OutScaleForTrainingPass and enable test_quantization_scale_pass UT (#24393)

* Init scale node in OutScaleForTrainingPass, test=develop
* Enable test_quantization_scale, test=develop

* 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

* add mul and matmul quantization, test=develop
* add test for matmul, test=develop

* Support  more ops in post training quantization, and save the output scale in quantized op.
* Update docs in post training quantization and qat 

* Fix bug for inserting add_quant_dequant_op to same variable repetitively in add_quant_dequant_pass, test=develop

* add post training quantization, test=develop
* specify the quantizable op type, test=develop

* move pool2d to add_quant_dequant_pass, test=develop

* add fake_quant_dequant_op for average pool2d
* add test

* add pool2d quantization support, only for max-pooling.

* add the partial quantization support.

* add quant_dequant_pass, test=develop

* Add quant_dequant before some ops, such as the elementwise_add op. This is required by TensorRT. test=develop