* delivery skip_gc_vars from the main graph to each subgraph compiled by CINN

* rearrange format and annotation

* fix lacking namespace

* fix segmentation fault cinn subgraph doesn't own kSkipGcVarNames

* deliver all skip_gc_vars of main graph

* add vlog for skip_gc_vars

Add 0d Tensor Test Cases for cond, case, switch_case. Since the 3 APIs are control flow APIs, their support for 0d tensor relies on the underneath APIs. This PR just added test cases to prove that the 3 APIs have already handled 0d tensor well.

* modify setup.py and paddle_build.sh

* modify setup.py and paddle_build.sh

* modify setup.py and paddle_build.sh

* modify setup.py

* modify run_setup

* modify setup.py

* fix make_clean

* modify setup.py

* modify setup.py

* delete setting python_libary

* debug

* debug

* debug

* debug

* approve_for_setup,test=test=document_fix

* test

* remove deps and prior comm

* grad comm fuse

* add deps for amp&global norm

* stage2 broadcast prior deps

* stage2 grad overlap

* stream_analyzer bugfix

* overlap enable

* dep op namescope

* depend support multiple inputs

* check finite deps

* stage2 param comm overlap

* Set kD2HStream

* grad comm hierarchical

* grad comm hierarchical

* new unitest
Co-authored-by: Nchenruibiao <chenruibiao@baidu.com>

* fix get_single_test_cov.py bug

* debug

* update requirements.txt and setup.py.in

* update requirements.txt setup.py.in setup.py

This reverts commit 2c444dfa.

* add for-else

* add * for unpacking

* execute use kernel_key first

* change OpKernelType->KernelKey

* fix py3 compile error, remove redundant header files

* fix build_strategy_test

* fix DataType::RAW

* fix custom_type test: operator_test.cc

* fix transform place

* fix backends_are_same_class

* try fix place TransDataDevice

* support all KernelKey

* fix TransformData

* fix place_are_same_class

* fix merge

* fix test_params_no_grad

* fix specific place of GetExpectedKernelType

* fix specific place of GetExpectedKernelType

* fix GetKernelTypeForVar

* fix dtype error

* fix fetch_v2

* change GetKernelTypeForVar

* fix interpreter

* fix typo error

* polish codes

* polish codes

* polish codes

* fix conflict

* [CodeStyle][isort][UP019] sort imports and update deprecated type annotation in paddle/jit/api.py

* Revert "[CodeStyle][isort][UP019] sort imports and update deprecated type annotation in paddle/jit/api.py"

This reverts commit 0ca4d52c900199126e6433057d1514dbf9d4ee07.

* update deprecated typing

* Fix param and out grad names in dy2st for high order grad

* replace matmul with matmul_v2 in fuse passes

* Remove fusion logic from matmul

* removing fusion methods

* add proper name

* adjust namespaces

* move fc from fluid to paddle2.0

* fix unit test

* fix some examples

* fix some examples

* remove fluid.save_dygraph and fluid.load_dygraph use paddle.save and paddle.load instead

* move Sequential to paddle.nn

* modify convert_call_func.py Sequential reference

* remove related unitests

* remove fluid.dynamic.Sequntial

* test remove conver_call_func

* fix conflicts

* fix typro

* fix unitests

* fix sample_code

* fix unitest

* fix __init__

* [CodeStyle][py2] test dockerfile

* remove some deps for pip2.7

* clean python2

* remove pip upgrade

* use tar extract setuptools package

* downgrade setuptools

* Implement conv2d_fusion NHWC format using CUTLASS
* Add unit testing for CUTLASS Conv in inference
* Add experimental API for CUTLASS.

* [OpAttr]Fix Ignore AttriteTensor in IndicateDataType bug in grad_op

* add GetExpectedKernelType

* Use BroadcastKernel and ReduceKernel to optimize expand and expand_grad.

* Correct the axis when there is only 1 input in BroadcastKernel.

* Add the calculate of output's shape.