* allow fold fill_constant && allow nms3 into trt in int8 model
* use unordered_map
* fix CI failing

* update AUTHOR. test=kunlun

* update AUTHOR.

* [CodeStyle][py2][U004] unecessary explicit `object` inheritance in class definition

* fix an increment

* Split kernel registered, tests for uint/int added

* Split quantized

* Split output scales calculated only once

* NearestInterp test fix reversed

* DequantizeOutputs corrected

* removing dependent to fluid/framework/eigen.h in phi

* more fix according to PR-CI-Py3 fail

* disable distributed xpu tests

* test=kunlun

* test=document_fix;test=kunlun

* test=document_fix;test=kunlun

* test=document_fix;test=kunlun

* test=document_fix;test=kunlun

* support pow_double_grad op

* add unit test for pow double grad

* fix pow double grad

* optimize pow double grad kernel

* fix pow double grad kernel

* fix cast bug

* Fix undefined symbol: shm_open

* Fix for Windows

* Exclude APLLE

* Define ConvRunner to wrapper the call of cudnn conv functions.

* Use ConvKind in SearchAlgorithm.

* suqeeze2 transpose2 fuse onednn

* format

* fix output shape

* fix conflict

* format

* format

* remove useless

* remove log

* simply pass

* fix comment

* fix

* fix msg

* fix error msg

* format

*test=kunlun

* test=cuda117

* test=cuda11

* test=document_fix;test=cuda117

* test=document_fix

* fp16 pass support assign op

* choose assign op exec mode

* add unittest

* add cmakelist

add roll and roll_grad kernels and strided_slice and strided_slice_grad kernels, test=kunlun (#47368)

* add stat tool

* add roll and roll_grad kernels and strided_slice and strided_slice_grad kernels, test=kunlun

* test_paddle_multiprocessing support eager tensor pickler

* refine python lib link

* sort hooks

* add `name` for remove-tabs

* Get three grad lists in CPP to avoid gpu idle time

* Support legacy mode

* remove paddle.fluid.dygraph.nn.conv2D

* fix ut

* fix conv fp16 UT

* move cudnn hardcode outside GetExpectedKernelType

* add header file

* debug

* update interpreter_util with hardcode

* update interpreter_util headerfile

* solve activation hardcode

* debug with CI

* add mkldnn_op_list header file

* temporarily uncomment mkldnn

* temporarily uncomment mkldnn

* delete sequence_softmax cudnn hardcode

* add hardcode to data_transfer.cc

* update data_transfer headerfile

* try fix segment fault

* update cudnn&miopen_helper

* reset HasAttr of DygraphExctnCtx

* debug, this commit should pass all CI

* debug should pass CI, temporarily disable activation

* debug should pass CI

* fix default_attr=nullptr bug

* clean debug code

* Call SetDnnFallback function in the base class

* activation fallback to plain kernel

* fix default GetExpectedKernelType find wrong kernel

* search cudnn kernel instead of fallback

* fix cudnn_handle bug

* remove tanh use_cudnn

* restore tanh use_cudnn

* debug tanh

* fix tanh bug

* delete activation cudnn kernel

* polish code

* [CodeStyle][E262][E265] make comments start with `# `

* flake8 config

* init changes

* bnorm

* method signature

* change order

* bnorm

* removed unused args

* expand op donot use naive data parallel

* fix unittest

* remove fwd funcs

* migrate conv grads