* Add the CRFDecoding and LayerNorm's test case

test=develop

* Fix the size checking issue

test=develop

* Remove the remnant code

test=develop

* Add TestAllImpls and double support

test=develop

* Clean Code

test=develop

* Add benchmark test for LayerNorm & CRFDecoding

test=develop

* inplace group

* test=develop

Refine the doc of reshape, stack

Removed duplicated code

resolve #15724

Fix lstm possible leak

fix enforce

test=develop

add sugar for fetching parameters and layers

1.Remove the code for setting mkldnn environment in the test_calibration.py;
2.Update the cmake file for MKLDNN environment enabling;
3.Update the INT8 inference doc.

test=develop

test=develop

Quantization inference passes

test=develop

Fix row_conv doc

* fix group_norm

* test=develop

* fix && test=develop

* fix && test=develop

* test=develop

* Fix debug mode in prior_box_op
* Refine code

test=develop

test=develop

test=develop

remove legacy v2 codes

fix optimize with different dtype

* Fix debug mode in fake_quantize_op
* Remove template specialization

test=develop

test=develop

test=develop

This also fixes linking to libpaddle_fluid.so built in debug mode

test=develop

support multiple var types for expand op

test=develop

* remove est_image_classification_resnet for mac
test=develop

* increate the timeout
test=develop