* first commit

* merged with develop

* merged with develop

* fix merge sequential one dims bugs

* scale kernel

* endline

* add inplace

* fix merge conflicts

* Merge conflicts

* add compile-time infermeta logic for stack infermeta.

* add unittest for stack infermeta where -1 exists in shapes.

* remove backward changes.

* fix amp kernel

* update to remove PADDLE_WITH_XPU macro

* add tensor array

* fix ci bugs

* fix ci bugs

* fix ci bugs

* fix ci bugs

* update by comment

* update code

* using mkldnn

* using with mkldnn macro

* fix use mkldnn

* concat workaround

* CI rerun

* Enable startup program for standalone executor

* Disable test_py_reader_using_executor

* Fix test_parallel_executor_mnist

* Fix CI errors

* Fix CI errors

* update protobuf format

* fix protobuf content

* fix file mode

* fix compiling error when gpu not exists

* fix compiling error when gpu not exists

* fix compiling error when gpu not exists

* fix compiling error when gpu not exists

* support rocm

[Paddle Inference] fix bugs in quant_conv2d_dequant_fuse_pass when weight is shared  between ops (#45719)

* fix_old_format

* fix bug in quant_conv2d_dequant

* fix bug in quant_conv2d_dequant

[Eager, Performance optimization] reduce_all interface move reduce_all flag from python to C++ (#45744)

* [Eager, Performance optimization] move reduce_all flag from python to c++

* polish reduce_all

* fix ci error

* fix errors

* [Eager, Performance optimization] reduce_max / min polish

* polish reduce_max / min

* update min/max kernel reduce_all logic

* fix a mistake

* fix ci errors

* fix errors

* set use_cudnn=true for conv2d

* clear opmaker of matmul_v2

* fix bug of set_attr

* add extra attr checker in infer_shape

* add silu converter

* fix grad error of grounorm op when cuda version==11.7

* remove int8 fallback

* gaussian random

* mkldnn to onednn renaming

* fix merge conflicts

* remove fluid code

* onednn renaming

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

* support onnx format quantized model

* update code

* add test

* add test

* fix

* fix test

* fix cmake

* update code

* change scale file path to calibration file path

* update code

* update code

* fix build bug

* fix build bugs

* fix

* fix

* fix compile error in gcc540

* remove extra attr of opmaker

* remove extra attr of gru

* revert scale

* fix bug of create_op

* add extra attr checker in infer_shape

* fix gelu

* [OpAttr]Fix complation error of XPU from Pool2dGradKernel

* test=kunlun

* [Eager] fix pool2d interface under eager mode

* add use_gpudnn for pool2d

* fix pool2d yaml conflicts

* fix pool2d yaml

* migrate memcpy to phi

* fix typo error

* fix typo error

* fix  bug and testcase

* fix typo, uniform_random_kernel.cc header

* fix Alloc pinned bug

* change GPUContext::GetPinnedPlace

* add GetPinnedPlace function

* add GetPinnedPlace function

* restore default throw error

* fix Unimplemented error

* skip StandaloneExecutor testcase

* delete memcpy_sig

* [Eager, Performance optimization] fix pool3d under eager mode

* polish code

* add config param for enable_dlnne and support calibration mode
* remove useless file
* refine code and add annotation
* refine code of Warnning tips