* fix dataloader exit error if user exit program when dataloader is still iterating. test=develop

* Unset ReserveSpace for inference program.

* Support training from an inference program.

* change prepend to append

* fix ut

* add testcase

* fix ut

* fix test_custom_relu_model

* fix model parallel

* rm parallel_help.py

* add embedding

* support backward return None.

* edit unittest.

* edit code according to CI

* Improve error information

* skip op has no fp16 kernel

* add ut

* add norm_by_times param to ctc_loss

* fix doc,test=develop

paddle.to_tensor will be translated to paddle.assign in Dy2stat, however paddle.assign doesn't support int, float, bool. This PR added the supports.

* [DOC] Clarify the difference between paddle.norm and np.linalg.norm

* add pp dygraph, test=develop

* Dygraph reocmpute

* unitest for Dygraph reocmpute

* dy recompute remove unitest for win and mac

`range` API set its output shape in dygraph but not in static graph, which can cause Dy2stat error. This PR set the shape of `range` API when possible.

* support save/load binary format tensor

* Fix error when create cudaplace

* Fix error when create cudaplace

* Fix error when create cudaplace

* get devive context from pool.

* move define of 'SerializeToStream' and 'DeserializeFromStream' to 'lod_tensor.cc' and 'selected_rows.cc'.

* support complex object

* improve coverage.

* improve coverage

* improve coverage.

* fix a bug.

* polish API

* save/load program

* paddle.save/load: layer

* deal with conflict

* if PY2, block test_paddle_save_load.TestSaveLoadLayer

* polish code.

* polish code

* edit unnittest

* The condition for object to be identified as state_dict becomes strict

* use 'core._cuda_synchronize'

* add Hub Module for easy to use pre-trained models.
*   support list, load, help fucntions.
*   support load models by github, gitee, local 
Co-authored-by: NLielinJiang <jianglielin@baidu.com>

* add pipeline layer

* update

* fix bug: when x.dim < y.dim, the result of compare_op is inverse to expected result

* support the cuda for fix the compare broadcast bug

* fix tc trt shape

* fix fc dynamic shape

* add fc shape assert

* update

* let paddle.utils.install_check support CPU package with GPU device

* use use_cuda in dygraph checking

* add unittest for install_check

Reduce max iter size to fix windows openblas test_yolov3 random failure.
Decrease batch size to fix pe related unittest random failure.

* remove useless ext headers

* fix boost header compile failed

* add c_identity op, test=develop

* refactor_check_finite_and_scale_npu_kernel

* fix compile

* add alloc_float_status op

* add alloc_float_status op

* add FloatStatus for check_finite_and_unscale

* refine code

* remove unneccessary logic

* refine for fleet

solve hccl communicate conflict (#32447)