* [Custom Op] Support extra_library_paths of load

* change API order

* change unittest parameter order

* [Tensor Operants & Prim-Relevant] Tensor supports compare operants

* fix dependence of test_comp_static

* fix unit test

* resgister for ftt_r2c, ftt_c2_r

* fix clang-format

* Add output defs for argsort kernel

* Update argsort_kernel.cc

* Update argsort_kernel.cu

* Update argsort_kernel.cc

* fix: fix broadcast object list

* fix: fix scatter object list

* remove fluid.layers.collective and related unittests.

* fix layers.init import

* fix all_gather method

* remove unused args in all_gather method

* fluid clean: remove fluid.ir to framework.ir and some funcs form fluid.layer.io to incubate.

* delete fluid.ir

* add_fp16_for_diff

* fix doc_for_fp16

* finish task

* fix some question.

* fix error

* change unittest:zeroDim.

* add multinomial output defs

* fix register on gpu

* limit protobu_version > 3.20.0

* limit protobu_version > 3.20.0

* [AMP OP&Test] Support float & bfloat16 when using cub

* fix compile error

* fix

* fix rocm compile error

* [phi][jit] rm Softmax StrideScal

* [phi][jit] rm kStrideScal

* [phi][jit] fix Softmax clean omission

* [phi][jit] fix Softmax clean omission

* [phi][jit] fix StrideScal clean omission

* [phi][jit] fix mkl SoftmaxKernel clean omission

* [phi][jit] fix test error

* [phi][jit] fix test error

* [phi][jit] rm NCHW16CMulNC

* [phi][jit] fix test error

* [phi][jit] rm HSum HMax

* [phi][jit] fix test error

* [phi][jit] rm StrideASum

* add AUTHORS.md

* [phi][jit] fix test error

* update unittest of fp16 for slice op

* set atol to default value

* update max_relative_eror

* support fetch empty tensor on CPUPlace

* fix the shape in unittest of empty output

* add bn vjp

* fix example

* fix code

* fix code

* fix cinn case

* fix code

* fix example

* fix code

* fix example

* fix example

* added paddle.polar to paddle

* added paddle.polar unitest

* failed to use pytorch for evaluating results, and changed with numpy implementation

* updated code style

* updated __init__.py

* updated code style

* fixed unitest code

* lkh test polar

* polar add

* fixed errors and optimized code

* fixed error

* optimized polor api

* updated code style

* updated code style

---------
Co-authored-by: Ndiadestiny <1247889154@qq.com>

* add sqrt composite rule/test

* add sqrt composite rule/test

* fix ops/sqrt, add cinn test

* fix sqrt_comp

* fix sqrt_comp

* fix sqrt_comp

* fix

* fix codestyle

* fix codestyle

* add fp16 test

* add ops/sqrt

* fix

* fix

* fix unitest

* fix

* fix

* fix

* init unit test commit, contains register thinking

* support inplace

* get inplaced x.grad

* Try support inplace and hook at the same time

* Support inplace, need debug

* Support inplace successfully

* Inplace use Tensor&, consistent with Tensor*

* fix MapPlainOutputs bug

* fix double grad inplace error

* rename flash_attn_raw to flash_attn_unpadded

* fix static api

* fix static return

* add dynamic support

* add more test

* fix bug

* change test

* change test

* add fp32 grad plus fp16 param in adamw

* add python UT

* fix test case

* in test_adamw_op py file, force the moment2 value LE 0

* add a compare option

* remove bf16 fused adam kernel case

* remove contexts in tensor_utils

* update from_blob

* update from_blob

* update from_blob

* fix bug

* fix bug

* update env setting

* update pass logic

* dist op support bf16

* backward cast update

* update setting

* update backward

* revert amp pass

* update fp16 backward logic

* register c_embedding bf16

* revert engine

* add unitest

* add unitest

* update unitest

* update cmake

* update math

* update math.py

* update unitest

* update unitest

* revise unitest

* revise unitest

* update unitest

* update unitest

* update unitest

* add rnn and searchsorted output defs

* add gpu kernel

* remove fluid thread_data_registry

* update

* fix bug

* split pass

* fix compile

* fix ut

* more time

* modify ut

* reduce dim

* fix compile

* reshape weight

* tensor

* remove enforce

* static shape ut

* batchsize

* reorder pass

* minus test cases

* windows timeout

* windows time out

* remove test for windows

* correct

* sssss

* xxx

* rm Executor._run_parallel

* remove compiledProgram related tests of standaloneExecutor