* Support different dtypes of inputs for broadcast for dropout optimization  (#52093)

* change judgement for DropoutGradGPUKernelDriver

* add UnrollerWithoutVecSize and after this Loaddata to be refined

* pass unittest

* use same unroller with XPU

* BroadcastWithInt64Index

* BroadcastDataLoader template partial specialization

* fix compile errs in ROCms

* PR comment

* dropout_nd_optimization (#51479)

* with printf

* add DropOutNdForwardKernel

* PR comment

* Dropout optimize & clean broadcast inT and ElementwiseType (#52969)

* change judgement for DropoutGradGPUKernelDriver

* add UnrollerWithoutVecSize and after this Loaddata to be refined

* pass unittest

* use same unroller with XPU

* BroadcastWithInt64Index

* BroadcastDataLoader template partial specialization

* fix compile errs in ROCms

* clean ElementwiseT and InT for BroadcastKernel

* default axis and clean inT

* remove redundant fast divmod computation

* optimize drop_nd & drop_nd_grad

* optimize BroadcastDataLoader bf16 fp16

* rm InT etc. after merge develop

* delete constexpr for windows ci

* fix conflict

* fix conflic with develop

* fix conflic

* new clean

* clean

* Fix xpu2 kp compile error (#53548)

* fix conflict

* conflict

* remove contexts in tensor_utils

* update from_blob

* update from_blob

* update from_blob

* fix bug

* fix bug

* refine reduce_all

* move reduce_all_flag from python to c++

* fix infer shape bug

* fix bug;

* fix sum infer meta bug

* fix reduce sum grad gpu bug

* fix amin amax bug;