* Delete the /paddle/fluid/platform/device/npu directory

* clear Cmakelists

* Try removing npu in the header file

* fix_gcc12_error

* fix gcc12 error

* fix gcc12 error

* add visit_place to phi/core/utils

* remove reference to operator.h in phi/kernels/funcs/math_function.h

* update data type from framework.proto to phi

* fix enforce error in fluid

* move sequence_padding to phi

* fix bugs

* fix bugs

* fix bugs

* fix bugs

* fix bugs

* fix bugs

* fix bugs

* fix bugs

* fix buga

* fix bugs

* revert and update phi::XPUContext

* decouple strided_memcpy

* move strided_memcpy

* move strided_memcpy to phi

* fix namespace

* update

* fix gpu compile bugs

* fix the div 0 error of sequence_concat
* Update test_sequence_concat.py

sequence_mask fix: when the input length is an empty tensor, the kernel tries to dereference illegal sentinel iterator (#49525)

* execute use kernel_key first

* change OpKernelType->KernelKey

* fix py3 compile error, remove redundant header files

* fix build_strategy_test

* fix DataType::RAW

* fix custom_type test: operator_test.cc

* fix transform place

* fix backends_are_same_class

* try fix place TransDataDevice

* support all KernelKey

* fix TransformData

* fix place_are_same_class

* fix merge

* fix test_params_no_grad

* fix specific place of GetExpectedKernelType

* fix specific place of GetExpectedKernelType

* fix GetKernelTypeForVar

* fix dtype error

* fix fetch_v2

* change GetKernelTypeForVar

* fix interpreter

* fix typo error

* polish codes

* polish codes

* polish codes

* fix conflict

* remove "gpu_primitives.h" in fluid namespace

* fix PR-CI-GpuPS fail

* fix PR-CI-GpuPS fail

* rm "paddle/fluid/operators/math.h" in phi

* rm "paddle/fluid/operators/math.h" in fluit

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

* more fix according to PR-CI-Py3 fail

* 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

This reverts commit f9134045.

* 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

* add predictor_engine

* add predictor_engine

* fix zero shape

* fix lodTensor

* fix unittest

* fix code style

* update CmakeList

* opt cudnn hardcode of sequence_softmax

* fix grad datatype

* namespace modify

* update by comment

* remove using lodtensor part1

* polish history code format

* remove needless using tensor

* remove needless using tensor

* resolve conflict

* replace tensor using

* fix format error

* revert needless changing

* fix rocm and npu compile error

* fix cinn compile error

* fix format error

* fix mkldnn format error

* fix mkldnn format error

* fix cinn compile error

* fix cinn compile error

* fix cinn compile error

* resolve conflict

* add sequence_unpad for xpu,*test=kunlun

* add sequence_unpad, *test=kunlun

* fix bug in testcase,should not be sequence_pad,*test=kunlun

* remove cudaDeviceContext

* remove more template

* fix rocm compile

* remove alias name CUDADeviceContext

* fix compile

* fix tests

* revert changes

* remove cudaDeviceContext

* remove more template

* fix rocm compile

* Rename BOOST_GET macros

* Fix conflicts

* fix init()

* delete test_device_context

* replace CPUDeviceContext with CPUContext

* fix test_scalar

* remove dot_op.cc

* fix compile

* add cross_entropy_with_softmax phi kernel

* remove softmax_with_cross_entropy kernel

* add softmax_with_cross_entropy grad kernel

* remove original op kernel

* refine cross entropy impl

* fix pointer error

* revert kernel cu change

* fix xpu failed

* fix cinn failed

* fix npu failed

* add forward sig

* add check_nan_inf for pt kernel

* remove repeat cmake item

* fix unittest error

* move gather.h gather.cu.h scatter.h scatter.cu.h to phi library

* fix CI

* fix rocm ci

* change Vector to std::vector and provide MixVector class as a helper wrapper class

* solve the multi-gpu hang problem

* remove the duplicate template instantialize

* Copy vector to cpu

* add CopyToCPU

* xxx

* final version: fix the problem of all reduce

* remove mixvector dependence

* fix

* merge

* fix code

* fix by CI