* Support dynamic shape in multiclass_nms3 Plugin for Paddle-TensorRT.

* cherry pick delay tensorrt log
* Update trt_plugin.h

* Allow manaully set py_reader name in standalone executor

* Fix CI errors

* [CustomDevice] add dy2static support

* update

* add fusion dir and fuse_softmax_mask kernel

* remove fusion kernel dir

* migrate infershape

* fix code errror

* Enhance slice to support 0 dims Tensor

* Add UT

* add audio feature dataset

* fix coding style

* fix coding style2

* rm librosa

* rm voxceleb

* rm librosa in test

* add scipy fftpack

* add functional

* fix setup

* fix setup2

* rm colorlog

* refactor dataset __init__.py

* fix converage

* fix librosa import error

* fix windows test

* fix windows ci

* rm datasets

* fix setup

* remove testdata

* add librosa in requirement

* add librosa in requirement2

* change librosa to 0.8.1

* update ci docker

* fix ci error

* fix ci error2

* fix ci coverage

* fix converage

* fix coverage

* rm audio_base in test, notest,test=coverage

* fix copyright

* rm backend

* rm compliance&&add function test

* fix setup

* fix windows

* fix windows2

* fix test timeout

* fix ci time issue

* rm test_audio_feature

* avoid windows isssue, tmp

* note windows isssue

* skip windows issue

* fix dtype in layers.mfcc && fix ci-static-check

* add relative accuracy

* modity API.spec

* skip cuda11.2 test

* skip cuda11.2 test2

* skip cuda11.2

* gaussian random

* mkldnn to onednn renaming

* fix merge conflicts

* remove fluid code

* onednn renaming

* Move classes from mkldnn_reuse.h to onednn_reuse.h

* Migrate pool+grad, clip+grad and cast oneDNN kernels to PHI

* Refactor grad kernels into separate files

* Fix CI failures

* Fix Codestyle

* Implement reviewer suggestions

* Add new lines after includes for readability
Co-authored-by: NSilv3S <slawomir.siwek@intel.com>

* add gemm_epilogue

* xpu-paddlepaddle-40 [任务] fused_gemm_epilogue 支持 test=kunlun

* [OpAttr]Refine Teller logic if encounter OpDesc with Variable type Attribute

* fix iterator

* fix typo

* fix lambda expr

* fix ptr

* stop pass filter int32/int16/int64/bool inputs in cond_op

* fix bugs: except block 0, the backward vars and forward vars exist in different blocks.

* fix code by review

* add save kernel

* add save_sr_kernel

* remove original save_op

* add save gpu kernel

* remove combine kernel

* add port.h include

* add save selected rows test

* remove useless kernel.h

* fix infermeta bug for vector input and output

* add unittest

* Construct exec and ctx only once in cond op to speed up

* Fix construct function error

* gaussian random

* mkldnn to onednn renaming

* fix merge conflicts

* Migrate reduce_op oneDNN kernels to phi

* Remove unnecessary header

* remove fluid code

* onednn renaming

* Change std::vector<int64_t> to IntArray

* Fix code style

* Move classes from mkldnn_reuse.h to onednn_reuse.h

* Move more functions from mkldnn_helper.h to onednn_helpper.h

* Change MKLDNN to OneDNN in VLOG message

* Implement reviewer suggestions
Co-authored-by: NSilv3S <slawomir.siwek@intel.com>

Adapt tensor output_size for conv2d_transpose and depthwise_conv2d_transpose

* enable memory optimize when fp16.

* optimiza params sync between cpu and gpu.

* clear extra attrs of reduce op in opmaker

* fix reduce_mean