* update nas and distill docs

* modified README and demo

* Update qat.rst

* Update quantization_api.rst

* Update quant_post_static_tutorial_en.md

* Update quant_aware_tutorial_en.md

* Update quant_aware_training_tutorial.md

* Update quant_aware_tutorial.md

* Update dygraph_quant_post_tutorial.md

* Update quant_post_static_tutorial_en.md

* Update quant_aware_tutorial_en.md

* Update quant_aware_training_tutorial.md

Co-authored-by: Nceci3 <ceci3@users.noreply.github.com>

* fix get sub model

* fix

* update

* update

* update include_self

* fix CMake issues of mkldnn quant demo

* remove deleted libs

* update

* fix dist

* fix

* remove hook

* fix skip layers

* fix depthwise

* fix depthwise

* fix depthwise

* add gp_nas

* add_syncbn

* fix when kernel size is even

* fix name

* fix weight_op

* update the doc of dygraph qat, test=develop, test=document_fix

* up, test=develop, test=document_fix

Fix the error of save_quantized_model when weight_preprocess is PACT

* fix shortcut

* fix when kernel_size in ss

* fix export

* fix dp

* fix export model prune param twice

* add comment

* fix unittest

* fix

* update

* fix docs

* update

Co-authored-by: Nceci3 <ceci3@users.noreply.github.com>

* update

* update

* Update mkldnn_quant readme
Co-authored-by: Ncc <52520497+juncaipeng@users.noreply.github.com>