* pr1

* pr2

* pr3

* fixed unitest

* adopt for scale

* Fix scale kernel for low precision, cherry pick #50998.

* Fix the FP16 precision problem of add_n. (#50129)

* Change squared_l2_norm to reuse ReduceKernel, and register fp16 and bf16 kernel, which is cherry pick #48315.

* Cherry-pick the fix of MPTypeTrait in KP, which is implemented in #50993.

* Cherry-pick the multi-precision support of AdamW for bf16, #48041.

* Fix compiling error.

* Cherry-pick the fix of CubTensorReduceImpl for bfloat16 in #50993.

* Fix unittest.

---------
Co-authored-by: Nliuruyan <44316842+liuruyan@users.noreply.github.com>

* Broadcast the master weight along with param for distributed training.

* Fix codestyle.

* Cherry-pick the register of bfloat16 for amp_kernel, pull request #45541.

* Cherry-pick the master_grad support of adamw, pull request #51141.

* add bf16 for some ops in static mode (#51582)

* Add bfloat16 support for some api in static mode.

* Fix codestyle.

* Revert the change of layer_function_generator.py.

---------
Co-authored-by: Shaojie WANG <wsjmessi@163.com>

* Register exp/expm1/logit bf16 activation op kernels (#48702)

* register more bf16 ops

* update to register coresponding backward ops

* Addition of bf16 type support for Compare OP  (#46413)

* first commit

* clarify the quotes

* change code style format

* support bfloat16

* add bfloat16 support for more ops (#48272)

* [Bfloat16]register bfloat16 datatype for squared l2 norm (#50908)

* Sync the pull request #51903.

* Add some header files back.

* modify cmake file for cuda11.8 compile (#49020)

* modify cmake file for cuda11.8 compile

* add op_library(fused_embedding_eltwise_layernorm_op DEPS bert_encoder_functor)

* Fix compling error.

* Cherry-pick pull request #51396.

---------
Co-authored-by: Nsneaxiy <32832641+sneaxiy@users.noreply.github.com>
Co-authored-by: Nlimingshu <61349199+JamesLim-sy@users.noreply.github.com>
Co-authored-by: Shaojie WANG <wsjmessi@163.com>
Co-authored-by: Nzqw_1997 <118182234+zhengqiwen1997@users.noreply.github.com>

* fix fc kernel diff

* disable fc_elementwise_layernorm_fuse_pass

* disable scale op in amp pass

* Do not insert redundant cast op

* fix fused_fc_elementwise_layernorm kernel diff

* fix fc kerenl diff

* resolve conflict

* fix format error

* fix fold for large bs

* fix fold for large bs

* fix pre-commit

* cherry-pick:Some version of TensorRT don't support qkv_plugin

* cherry-pick:support coverage CI

* [MLU] fix compute error of dropout op (#45923)

* [MLU] add mergedAdam kernel. (#45965)

* [MLU] add int64 support for mlu one_hot_v2 (#46313)

* [MLU] fix profiler compile failure (#46208)

* [MLU] add barrier_op kernel. (#46417)

* [MLU] fluid: add mluop (#46429)

* [MLU] add huber_loss kernel. (#46455)

* [MLU] add mlu kernel for add_reduce_max_grad (#45651)
Co-authored-by: Nliupeiyu <liupeiyu@cambricon.com>

* [MLU] add_fluid_mluop_yolo_box (#46573)

* [MLU] fix phi::Tensor compile error of mlu. (#46649)

* [MLU] add fluid MLUOps prior_box (#46585)

* [MLU] fix cmake error (#46772)

* [MLU]fix unittest of sync_bn (#46797)

* [MLU] add masterparam support for mlu adamw. (#46804)

* [MLU] add int64 support for allgather. (#46830)

* [MLU] fix compile error & add mlu blacklist function. (#47439)

* [MLU] fix softmax_with_cross_entropy failed in 370-X8.

* [MLU] fix cncl stuck caused by multiple initializations.

* [MLU] fix code style check.
Co-authored-by: Nqipengh <huangqipeng@cambricon.com>
Co-authored-by: Ncifar10 <41565156+cifar10@users.noreply.github.com>
Co-authored-by: Lux et Veritas <1004239791@qq.com>
Co-authored-by: Nliupeiyu <liupeiyu@cambricon.com>
Co-authored-by: Nronnywang <ronny1996@163.com>

* cherry-pick 45860

* [BUG FIX]Fix MetaTensor's bug when run infermeta (#46265)

* fix sum bug

* fix ci bugs

* fix ci bugs

* update code according comment

Fix CUDA11.8 Unittest Accuracy

* [Release2.4] Revert python link prs (#48573)

* Revert "Fix mac link python (#48017)"

This reverts commit 3fa7a736.

* Revert "[Cherry-pick] Fix python link error (#47811)"

This reverts commit ff642c68.

* Update config.go

* fix custom operator backward=None (#48656)

* [Custom Extension] Fix custom double_grad backward=None (#49224)

* fix custom double_grad backward=None

* fix custom_relu.cu bug && polish testcase of double_grad

* remove old dynamic graph test

* add import fluid

* add import fluid
Co-authored-by: NChen Weihang <chenweihang@baidu.com>

* [Release2.4] Revert python link prs (#48573)

* Revert "Fix mac link python (#48017)"

This reverts commit 3fa7a736.

* Revert "[Cherry-pick] Fix python link error (#47811)"

This reverts commit ff642c68.

* Update config.go

* fix mixed precision inference
Co-authored-by: NChen Weihang <chenweihang@baidu.com>

Co-authored-by: NMing-Xu Huang <mingh@nvidia.com>

* [Release2.4] Revert python link prs (#48573)

* Revert "Fix mac link python (#48017)"

This reverts commit 3fa7a736.

* Revert "[Cherry-pick] Fix python link error (#47811)"

This reverts commit ff642c68.

* Update config.go

* [Paddle Inference] Add float_to_half_pass to support  inference with mixed precision (#47993)

* [Inference] optimize some code and fix some bug (#48780)

* clean ir_pass_manager and fix map_depthwise_conv_to_conv_pass

* fix unitest timeout

* [Paddle Inference] clean unused code  (#48392)

* fix

* update

* update
Co-authored-by: NChen Weihang <chenweihang@baidu.com>