* add tile_grad composite rule

* support 0-D output and 0-D as indice in __getitem__

* fix tests

* fix inference and UT

* add unittest for setitem

* fix xpu test

* fix xpu 0-d

* support auto generate for op adam optimizer

* remove unnecessary files

* support auto generate for op adamw optimizer

* support auto generate for op merged_adam optimizer

* use manual_signature in adam_

* Fix bug of reduce_sum op. When input.numel() > INT32_MAX, its result
is wrong.

* Remove climits.

* Fix bug of BlockDesc::MoveFrom(). It's used to rebuild main_program_desc from ProgramDesc modified by Fusion Pass. As some fused operators need to create new Variables in modified ProgramDesc, MoveFrom function uses std::move() function to move these VarDesc to main_program_desc. As a result, their pointers holded by modified ProgramDesc become nullptr. When call block()->Program()->proto() function, it will call ProgramDesc::Flush() function at first, which may cause a segmentation fault.

* mv inference/api infer_ut

* mv test

* merge develop fix error

* fix

* fix build error

* fix build error

* fix bug

* fix tester_helper.h

* fix analyzer_transformer_profile_tester.cc

* fix

* fix mac

* fix mac

* fix error

* fix

* fix

This reverts commit 543efcc5.

* remove ASCEND* keyword

* update docstring

* bug fixed

* bug fixed

* [CustomOP error] Add attrs type check

* fix global variable order bug

* include unordered_set

* fix ParseAttrStr compile error

* update

* update

* Revert "update"

* fix bug

* update

* [CustomDevice] add recompute support

* update

* trans fused attention to phi

* add optional parm

* trans fused_attention_grad to phi

* add fused attention grad register info

* fix include

* test=kunlun

* add fused attention to static build list

* add remove

* update remove

* fix performance bugs

* fix ci bugs

* optimize gap between generation step

* remove useless header

* unify_kernel

* fix compile bugs

* fix py3 bugs

* fix xpu bugs

* update

* fix bug

* fix bug

* fix bug

* fix bug

* remove c++14 assert and remove include tensor.h in phi

* first commit

* restruct c++ interface to divide linear from matmulwithcublaslt

* finish building in cublaslt impl

* fix code bugs

* fix host cost

* add some changes

* add autogen code support for mean_all op

* bug fixed

* bug fixed

* bug fixed

* fix graph_reindex

* fix

* Update op_compat.yaml

* update

* fix bug

* update

* fix bug

* update

* fix bug

* Add prelu, clip_by_norm, multi_dot tests

* Fix code

* Fix code

* add gn vjp

* fix 0

* fix args num

* fix type

* debug2

* remove unused expand

* support fp16

* fix typo

* fix reshape bug

* test3

* test4

* fix bug3

* add comment

* update

* fix bug

* update

* fix bug