* combine reduce_cuda codes

* support float16 in pten redcue_mean

* replace ReduceCudaKernel impl with pten reduce impl

* mv reduce funcs into reduce_cuda_impl

* rm unsed codes and headers

* mv GetReduceDim into reduce_cuda_impl

* recover GetReduceDim in reduce_op.h

* add new dispatch macro

* fix pool op output not inited and cause transform to pten::denseTensor error

* fix output tensor not initialized error

* rename new dispatch macro and format code style

* rm reduce_functor_op.h file

* refine structure for cuda and rocm

* update

* update

* update

* update

* fix bug:
1. atten: set the default value of attn_dropout_rate to None
2. ffn: add activation parameter

* Update the implement of reduceAnyKernel according to kernel primitive api
* Fix a bug in ReadData, ReadDataBc and ReadDataReduce when NX != 1

Implement FunctionTraits to support two kinds of elementwise functor and remove some old codes for broadcast. (#35688)

Revert "Implement FunctionTraits to support two kinds of elementwise functor and remove some old codes for broadcast. (#35487)" (#35686)

Implement FunctionTraits to support two kinds of elementwise functor and remove some old codes for broadcast. (#35487)

Describe

Add feed_forward for fused attention op.
(1) Encapsulate matmul impl (forward and backward) used in attention op.
(2) Implement bias_add (forward and backward) used in attention op.