* 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

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

* up, test=develop, test=document_fix

* update

* update

* add quant tutorial

2. Add missing api index.rst
3. Fix comment in filter_pruner
4. Update links in API docs

* add trt/x86cpu deploy doc

* add dygraph quant quick start

* add post quant quick start

* quant quick start doc refine

* fix doc

* fix doc

* move quick start to right path

* fix index

* add export model and depth

* update

* add ofa api docs

* quant quick_start update

* quant quick_start update

* add ofa_ernie
* add ofa_bert
* add bert and update ernie

* post_quant_static: remove the cache params, add optimize_model params, test=develop
Co-authored-by: NBai Yifan <me@ethanbai.com>

* use default settings and update benchmark data
Co-authored-by: Ncc <52520497+juncaipeng@users.noreply.github.com>