* decouple memory copy

* fix ci bugs

* fix ci compile bugs

* fix rocm compile

* fix ci bugs

* decouple_memory

* perfect memory utils

* fix ci bugs

* fix inference bugs

* fix custom test bugs

* fix converage bugs

* modify code according comment

* modify namespace

* deal with compile bugs

[PHI Decoupling] remove "paddle/fluid/platform/float16.h" and "paddle/fluid/platform/for_range.h" in phi. (#47817)

* rm "paddle/fluid/platform/float16.h" in phi

* rm "paddle/fluid/platform/for_range.h" in phi

* refine cmake of framework

* add deps for dense tensor

* fix deps

* remove alloc(ctx)

* add depends on mkldnn

resort .cu headers, set clang-format not sort include block and consider .cu as main source file (#43633)

* migrate increment addmm multinomial cholesky kernels to phi

* test pr39869

* test pr39869

* fix style and ci