* optimize performance

* fix

* improve coverage

* fix

* fix

* Fix leading dimension setting error in fused_gemm_epilogue_grad_op.

* Add dyload to cuBlasLt functions.

* Added cublasLtMatmulAlgoGetHeuristic to improve performance.

* Added FLAGS_cublaslt_exhaustive_search_times to cublasLt epilogue

* Added UTs to FLAGS_cublaslt_exhaustive_search_times

* Added warmup runs in algo searching of Gemm epilogue.

* Update copyright and documents.

* Fixed error handling.

* [Eager] Fix CastPyArg2Scalar in Long case

* Add more test cases for paddle.clip

* Use PyLong_AsLongLong

* Support double grad check of op in Eager mode

* fix bugs of backward yaml

* adjust code format

* fix nms op doc missing default value

* Hackathon 23

* fix bug

* fix pylint error

* try

* fix CI-Coverage

* update and add more unittest

* update

* support int16 argmax kernel

* add fp16 test

* add _grad_name and _grad_value for eager tensor

* fix paddle_enforce

* fix paddle_enforce 2

* fix grad_name

* _grad_value return lodtensor rather than tensor

* fix

* 增加logspace的算子描述

* 增加logspace的形状推断

* 增加logspace核函数实现

* 在python中增加logspace接口

* 增加logspace单测

* 增加logspace

* Update logspace_kernel.cu

* Update logspace_op.cc

* 调整代码格式

* Update doc of logspace

* Update tensor.py

* Update logspace_op.cc

* Update logspace_kernel.cc

* Update logspace_kernel.cu

* Update test_logspace.py

* 调整 logspace 的位置

* 调整代码格式

* gradients; test=document_fix

* fix VarType; test=document_fix

* fix vartype; test=document_fix

* cumsum; test=document_fix

* t; test=document_fix

* fix custom op pinned input error

* fix compile error

* double accessor and show_scale

* double accessor and show_scale

* rename

* fix bug in pslib config

* add unittest

* reduce performance influence

* add unit test

* fix

* changes for md in tensor

* ci fix

* Temporarily limited dims for test

* ci fix

* removed unnecessary includes

* added reviewers suggestions

* checkouted two files to avoid changing more than 19 in single PR

* minor fix

* reverted one file to reduce files changed to 19

* fix according to suggestion

* add kernel summary

* improve coverage

* make fast through to linear

* make fast through to linear

* add to do for later upgrades

* support build once for now

* fix bug for MultiplicativeDecay

* remove changes to test_lr_scheduler.py

* [Eager]Fix full_like/clip with np.generic type as attribute

* support numpy genertic

* remove usless code

* fix pad3d infer shape

* add dist reshape impl_idx=2

* fix cmakelist

* [Phi]Fix expand_sig infershape BUG under static graph mode

* [Phi]Fix expand_sig infershape BUG under static graph mode

* [Phi]Fix unittest

* [Phi]Fix unittest