* add align check

* refine

* add concat optimization

* refine

* remove annotation

* use alignas instead of aligned_storage

* move dropout_impl from fluid to phi

* move cuda_graph_with_memory_pool from fluid to phi

* update namespace

* remove cuad_graph in fluid

* fix mac-build

* fix bugs

* correct CodeStyle

* fix mac-build

* fix mutable_data

* fix stl include

* fix copy param

* refine cmake of framework

* add deps for dense tensor

* fix deps

* remove alloc(ctx)

* add depends on mkldnn

* test

* update

* fix gpu conetxt callback

* fix gpu callback

* fix callback early destruct problem

* refine randint kernel

* refine randperm kernel

* refine unbind kernel

* support op seed

* move unbind to phi

* revert infer shape

* add header file

* move concat_and_split to phi