* polish code comments

* polish data_device_transform.cc

* [Auto Parallel] Change the import way of Auto Parallel (#46115)

* fix strategy (#46256)

* [Auto Parallel] performance improvement for Sharding-DP hybrid parallelism (#46180)

* remove no need grad allreduce communication when sharding-dp

* remove no need grad allreduce communication when sharding-dp

* bugfix

* bugfix

* bugfix
Co-authored-by: NYulong Ao <aoyulong@baidu.com>
Co-authored-by: NJZ-LIANG <jianzhongliang10@gmail.com>

* Support matmul_v2 in Paddle-TensorRT converter.

* Fix TransDataBackend Error when call unsqueeze using MKL Tensor

* Add UT

* Refine UT

cherry-pick : #46016, #46021, #45974

* [Sparse]Sparse add support gpu (#45974)

* [Sparse]Remove unused code (#46021)

* [Sparse] Add infer meta (#46016)

* fix linspace error in amp

* fix log

* fix amp error

* support cast op backward refuse forward and fix some bugs (#46173)

* support cast op backward refuse forward

* Fix the bug of high order unit test framework

* support sign op backward refuse forward (#46002)

* add scope cache & reuse

* add gc scope for end of each train step

* del scope reuse for jit

* refine code

* test

cherry-pick from #45826
LayoutAutotune 支持 inplace 类型的OP
 根据 Add eager layout autotune #45409 修改意见调整UseAutotune
将LayoutAutotune判断放到controller中，与AMP 判断保持一致

[vision.ops.nms] Fix return order error and duplicate results with specific inputs (#46148) (#46193)

* fix return order error and duplicate results with specific inputs

* [cherry-pick] extend reduce_sum,reduce_sum,eq,ne,ge,abs,pow,etc higher order operators

* add reduce_mean,reduce_sum primitive ops
* add ne_p gt_p primitive operators
* add ge_p abs_p primitive oparators
* add cast primitive operators
* add pow,square prim2oirg rules
* add elementwise_div orig2prim rule

* [cherry-pick] add mean,sum,ge,gt,ne,abs,etc higher-order differentiation operators(#45888)

* add reduce_mean,reduce_sum primitive ops

* add ne_p gt_p primitive operators

* add ge_p abs_p primitive oparators

* [dy2static] support user to use decorator in their program (#45768)

* support deco

* fix deco ast type

* arg_str

* 1

* support callable deco

* code style

* codestyle

* test_error

* fix decos in another file

* recover conflict codes

* [BugFix] fixed a bug in decorator transformer, it can not analyze decorator with params correctly (#46055)

* fix deco call

* add raise

* add test

* add warn, fix paddle api

* fix error type

* fix coverage

* add unit test for sum higher level op (#45961)

* support slice op backward refuse forward and add high level unit test (#45960)

* support tile op backward refuse forward (#45942)

* support expand_v2 op backward refuse forward (#45941)

* support concat backward refuse forward (#45940)

Co-authored-by: NRichardWooSJTU <37864677+RichardWooSJTU@users.noreply.github.com>

* [AutoParallel] adapt gradient merge pass (#45915)

* adapt gradient merge

* fix op_role

* fix strategy

* [Auto Parallel] Gradient Fuse Allreduce (#45643)

* bugfix (#45332)

* dist embedding support lookup table v1

* add unitest

* customize wait_comm

* group gradients

* bugfix

* update program

* [Auto Parallel] Improve the APIs (#45776)

* [Auto Parallel] Use c++ dist attr in the completion process

* [Auto Parallel] Add minor changes

* [Auto Parallel] Use c++ dist attr in the completion process

* [Auto Parallel] Add minor changes

* [Auto Parallel] Add the serialization process for dist attrs

* [Auto Parallel] Remove unnecessary comments

* [Auto Parallel] Fix some bugs

* [Auto Parallel] Fix the code style

* [Auto Parallel] Remove unnecessary impls

* [Auto Parallel] Fix the importing error

* [Auto Parallel] Fix the copy from bugs of op dist attr

* [Auto Parallel] Replace the use of constexpr if

* [Auto Parallel] Redesign the shard_tensor, shard_op and ProcessMesh

* [Auto Parallel] Change API of the completion unittest

* [Auto Parallel] Fix the bug when set_attr an int

* [Auto Parallel] Add the unittest for the serialization

* [Auto Parallel] Add some unit tests

* [Auto Paralle] Unify the strategy

* [Auto Parallel] Improve the engine api

* [Auto Parallel] Reset the changes made to the framework

* [Auto Parallel] Change the engine unittest

* [Auto Parallel] Update API of the completion and partitioner

* [Auto Parallel] Update unit tests using engine api

* update shard annotation

* [Auto Parallel] Remove the modifications of other modules

* [Auto Parallel] Add docs for APIs

* add new strategy

* [Auto Parallel] Replace the logger

* [Auto Parallel] Restore the test_program.py

* [Auto Parallel] Change the import rules

* [Auto Parallel] Add the examples for Engine

* [Auto Parallel] Do some minor changes

* [Auto Parallel] Remove yaml dependency

* [Auto Parallel] Fix the unittests

* add valid after train

* bug fix
Co-authored-by: Nzhaoyingli <zhaoyingli@baidu.com>
Co-authored-by: Ncaozhou <caozhou@radi.ac.cn>
Co-authored-by: Ncaozhou <48191911+Caozhou1995@users.noreply.github.com>

* [Auto Parallel] Bugfix allreduce fuse for MP (#46086)

* bugfix

* bugfix

* typos fixed

* update strategy (#46138)
Co-authored-by: Nzhaoyingli <86812880+zhaoyinglia@users.noreply.github.com>
Co-authored-by: NJZ-LIANG <jianzhongliang10@gmail.com>
Co-authored-by: Nzhaoyingli <zhaoyingli@baidu.com>
Co-authored-by: Ncaozhou <caozhou@radi.ac.cn>
Co-authored-by: Ncaozhou <48191911+Caozhou1995@users.noreply.github.com>

* unify  core_avx and core_noavx

* fix except error

* revert mac compile logic

* revert dylib to so

* add core_noavx branch

* remove core_noavx

* replace paddle_core by lib paddle

* polish var name

* replace paddle_core by libpaddle

* update custom device commit

* polish code by comments

（cherry-pick）Fix split infershape in static mode and add convert rules for fill_any_like op (#46079)

* Fix split bug in static mode (#45906)

* fix split bug in static mode

* modify code style

* modify code style

* add unit test for split

* add convert rules for fill_any_like op in paddle science (#45985)

* add convert rules for fill_any_like op in paddle science

* add unit test for fill_any_like op in paddle science

* modify fill_any_like convert rule

* modify fill_any_like convert rule dtype

* skip forward save

* fix bug

* more ci for jit skip forward

* normalize yaml file name (#45894)

* Clear extra attributes of activation op in OpMaker (#45772)

* clear extra attr of activation op in opmaker

* fix syntax bug

* fix mkldnn kernel

* fix merge conflict

* fix bug

* [PHI] Normalize yaml op label (#45976)

* normalize yaml op label

* revert op_compat yaml change

* fix prelu and rnn compat problem

* replace api by op

* support assign op backward refuse forward (#45879)

* normize yaml backward op label (#46028)
Co-authored-by: Nzyfncg <zhangyunfei07@baidu.com>
Co-authored-by: NCharles-hit <56987902+Charles-hit@users.noreply.github.com>

[ Dy2Static ] Fix bugs when select inputs meeting different shape or undefined-var (#45916) (#46020)

* fix select_input with different shape errors:
1. select_input_with_buildin_type directly return non-undefinedvar branch when meeting undefined var
2. the output shape of select_input is inferred from inputs.

* reverse the logic in select_input

Support 0 shapes input Tensor for MKL slice kernel

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

* Allow manaully set py_reader name in standalone executor

* Fix CI errors

* adapt lazy init and fix pass

* add unittest

* update comment

* fix amp and sharding

* remove clip_by_norm

* convert_call support staticmethod for class.

* while support for python container.
It is convenient to convert more dynamic graph codes into static graphs.

* cond support python container

* add unittest for staticmethod convert_call

* fix bugs

* add unittest for item interface

* fix bugs

* change to np.testing.assert_allclose

* code format

* fix comments.

* code format

* Enhance slice to support 0 dims Tensor

* Add UT

* modify slice infershape

* code style

* modify slice_unittest

* 1. fix non-local error while dealing push_pop names
2. escape "'" in push_pop_names to avoid syntax errors.
3. unified the non-local stmt creation processes in getter and setter.
4. split the nonlocal_names and getter/setter names.

* fix bugs

* 1. revert setter and getter, push_pop_names must have non-local

* fix bugs.

* code format

* support more op for high level

* add unit test for high level op

* remove unnecessary comments

* add gemm_epilogue

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