* save fused_attention memory when dropout_rate = 0.0

* add ut

* fix ut bug

* fix fused_layernorm_residual_dropout_bias_test.cu

* 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

* remove cudaDeviceContext

* remove more template

* fix rocm compile

* remove alias name CUDADeviceContext

* fix compile

* fix tests

* revert changes

* Support optional residual add in fused_attention and fused_feedforward.

* Add checkpoint and add the check of add_residual when pre_layer_norm is false.

* Add TODO and change the python api to add add_residual argument.

* remove needless deps in unittests

* add gpu marco

* fix other unittests

* fix kernel name error

* fix test_prepare_op

* fix failed dygraph unittests

* fix gpu failed tests

* fix cinn test failed

* fix cinn test failed

* fix dropout tests

Fused elementwise_add, dropout, elementwise_add and layer_norm into one operator, only support Forward. 
No Python API changed.