* update the infer shape of matmul,  test=release/1.6

* add unittests of matmul, test=release/1.6

* change func names, test=release/1.6

* test=develop, communicator_is_sgd_optimizer flags

test=release/1.6

【cherry-pick】 fix fill_constant shape with -1 and enhance cross_entropy test=release/1.6 (#20722) (#20728)

* improve the performance of capi in PD_PredictorRun (#20665)

* alter the capi of PD_PredictorRun to provide proper function, test=release/1.6

test=release/1.6

* - Flushing mkl-dnn cache

test=develop

- Disabled clearing cache for LoadModel

- Added clearing of mkl-dnn cache when Executor is created

test=develop

- Do not clear for GPU places

test=develop

- compilation fix

test=develop

* - Moved clearing of mkl-dnn cache in destructor of executor

test=develop

* - Compilation fix

test=develop

- Reverted conditional clearing of mkl-dnn cache in Executors's
  destructor

test=develop

- compilation fix

* fix op log bug, test=release/1.6

* add unittests, test=release/1.6

* Fix communicator slow bug & fix communicator stop bug (#20366)

* test=develop,Fix communicator slow bug

* test=develop, delete if() in stop_worker()

* test=develop

* fix UT, test=develop

* fix bug in fetch handler, test=develop

* fix bug in fetch handler, test=develop

* test=develop, fix fetch barrier bug

* test=develop, bug fix

* test=develop, bug fix

* test=develop, fix bug

* test=develop,test=release/1.6

* add condition judgement for performance improvement test=develop

* add condition judgement for performance improvement test=develop

* refine code style test=develop

test=develop
Signed-off-by: Nzhaoyuchen <zhaoyuchen01@baidu.com>

test=release/1.6 test=document_fix

* Support fp16 in fused_elemwise_activation_op.
* Fix unit testing in ONLY-CPU mode.

* bug fix: invalid learning rate decay in pserver async mode

* refine API.spec, test=develop

* add nn.py to test,test=develop

* fix by removing new.spec, test=develop, test=document_fix

* refine scripts when PYTHON_ABI is empty, follow partial comments, add extra cpp api doc, test=develop, test=document_fix

* remove extra doc changes, remove API.spec, test=release/1.6

* remove API.spec in release/1.6, test=release/1.6

* support dump multi file
test=develop

* dump fix num file
test=develop

test=release/1.6

* disable nccl test

* Update version.

* fix term core only

* fix transpiler error

* fix protobuf memory leak (#11177)

fix protobuf memory leak

* "change eigen mirror"

* test=document_fix

* test=document_fix

* add input type and dtype check, enhance shape error message for concat_op (#20101)

* add input type and dtype check, enhance shape error message for concat_op
test=develop

* enhance shape check
test=develop

* improve coverage

test=develop

* enhance input type chec for concat (#20584)

test=develop

* add expand_as op, test=develop

* add expand_as op,test=develop

* add expand_as op,test=develop

* add nn.py, test=develop

* delele paddle_enforce, test=develop

Fix parse content in CreatePreLoadReaders. Before this fix, if you use dataset.set_parse_content and dataset.preload, parse content didn't work.

* add data type check, test=develop

* polish error messages, test=develop

* polish error messages, test=develop

* Remove support for the CPU architecture matmul, test=develop

* fix syntax bug, test=develop

* modified group_norm's unittest for pass statement, test=develop

* fix group_norm's bug: scale or bias is None which causes segmentation fault, test=develop

fix conv_transpose's bug: compatible with Anylayout setting: cherry-pick 20589

* fix recurrent bug
test=develop

* Fix while op bug
test=release/1.6

* add unit test
test=release/1.6

* Fix docs of gru_unit and dynamic_gru.

Fix basic_gru in rnn_impl.py.

Add error messages for param_attr setting in layer_norm api.

Add int64 dtype for expand.

test=develop

* Reopen unit-tests of basic_gru/basic_lstm in rnn_impl.py.
test=develop

* Add unit test for layer_norm api.
test=develop

* Remove the deprecated gru doc fix. test=develop

* Fix basic_gru test coverage. test=develop

* Update API.spec. test=develop

* Update API.spec. test=develop

* Fix test_basic_gru coverage test. test=develop

* Update test_basic_gru in test_layers to use fluid.data
test=develop

* Update test_basic_gru for coverage. test=develop

* Add Multihead matmul fuse pass (#20167)

* Add multihead fuse pass for ernie opt

* Refine softmax

test=develop

* Refine cuda kernel

* Refine cuda version

* Refine cmake

test=develop

* refine header file

* refine test case and pass
* refine comments

* Delete useless code.

test=develop
Signed-off-by: Nzhaoyuchen <zhaoyuchen01@baidu.com>

* Add seq2seq api related code (#19820)

* fix expand bug  (#20340)

* fix expand bug test=develop

* fix style test=develop

* fix style test=develop

* fix style test=develop

* fix style test=develop

* Fix the assign data check (#20564)

* Fix the assign data check. test=develop

* Fix test_assign_op.py. test=develop

* Update API.spec