* added transpose

* CI fix

* fix for transpose

* fix after review

* - some more MD changes

* - lint

* - compilation fixes

* - compilation fixes

* - lint

* - fix

* opt GetExpectedKernelType code of conv_transpose_op

* fix if error

* support pure bfloat16

* support bf16 linear

* update PR to pass CI

* tiny fix where_grad_kernel.cu

* add bfloat16 to selu_grad to pass CI

* fix selu grad compilation error

* fix P40 topk: Make the optimized topk compatible with P40.

* fix P40 topk: Make the optimized topk compatible with P40.

* fix P40 topk: Make the optimized topk compatible with P40.

Co-authored-by: Nliupeiyu <liupeiyu@cambricon.com>

* 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

* added fc int8 tests

* CI fix

* added skipping UTs for GPUs

* fixes for CI

* added support for residual connections inside fc

* fix for quant int8 bias

* - lint
Co-authored-by: Njakpiase <jakpia21@gmail.com>

* Relu6

* remove fluid handler

* add individual kernel signature

* coding style

* replace bounded_relu with clip

* whitespace

* code style

* fix clip_extra code in remove_training_info

* revert rnn opmaker clear

* init dropout

* small format fix

* fix pr comments

* add value test

* - Conv grad changed for MD

* - lint

* - compilation fix

* yet another lint

* support rsqrt_p

* refine code and ut

* add_prim_rsqrt

* fix ut

* add phi reduce_sum test=kunlun

* add fhi reduce_sum test=kunlun

* add fhi reduce_sum test=kunlun

* [BugFix]Fix reduce_mean/min/sum/prod, cumsum grad_op infershape bug

* fix typo

* fix typo

* Sum kernel migrated to phi

* Static cast added, file name changed

* OneDNNGetDataType to uppercase

* refactoring

* AddOneDNNHandler changed to SumOneDNNHandler

* clear extra attrs of look_up_table_v2 in opmaker

* fix bug

* Convert slice+grad oneDNN fluid kernels to PHI

* Change mutable_data to Alloc

* Refactor licences

* gaussian random

* mkldnn to onednn renaming

* fix merge conflicts

* remove fluid code

* onednn renaming

* gelu fwd

* sort activations

* gelu gradient

* remove unused macros

* merge conflicts

* fix merge conflicts

* remove extra contraint from gelu op

* fix sub sign reverse for mkldnn

* refactor code as comment

* remove useless

* format code