* Rename internal gradient variables in multiple backward
* so that they have different names with previous backward
* For example:
*  y = x * x, grad = fluid.gradients(fluid.gradients(y, x) + y * y, x)
* In second-time backward, gradient variable names of partial
* forward network (y * y) may be have same names with first-time
* fluid.gradients(y, x).

test=develop

* update local data preprocess doc

* update for 1.8 QAT

* update benchmark data
Co-authored-by: NWojciech Uss <wojciech.uss@intel.com>
test=release/1.8
test=document_fix

* fix kron_op: when only one input needs gradient, test=develop
* fix a typo in paddle.complex.matmul, test=release/1.8

* test=develop fix generate_proposals

* delete paddle.nn  api, test=develop

* fix optest, test=develop

* delete paddle.optimizer, paddle.meric, paddle.framework, paddle.io, test=develop

* fix optest, test=develop

* fix test_trace_op.py, test=develop

* fix test_activation_op.py, test=develop

* fix CrossEntropyLoss op en doc, test=develop

* delete unittests,test=release/2.0

* Add meshgrid op (#23736)

* update paddle/tensor, test=develop

* update linalg,py, test=develop

* update nn/functional, test=develop

* delete paddle/tensor/*, test=develop

* merge upstream, test=develop

* update __init__, test=develop

* pass ci, test=develop

* add reshape in paddle.complex, test=develop
* fix typos in paddle.complex.kron's comment, fix unittest, test=release-2.0

* merge latest. test=develop

* move full_like to fluid.layers

* copy api from paddle to paddle.fluid, test=develop

* fix optest, test=develop

* add decorator, test=develop

* add fake_interface_only, test=develop

* remove some dygraph_not_support, test=develop

* change dygraph to imperative, test=develop

* cherrypick: add kron op (#24105)
* add kron op and fluid.layers.kron
* add paddle.complex.kron

* update index sample

* API/OP (affine_channel, group_norm, layer_norm, random_crop, unpool, log_loss) error message enhancement test=develop

* adapt old version pretrain model load, test=develop

* fix infer error & multiple input error, test=develop

* Error message enhancement of 6 op, test=release/2.0
* refine huber loss unittests, test=release/2.0

* fix test_multiprocess_dataloader_base timeout. test=develop.
test=release/2.0

test=release/2.0

* Init complex number neural network, test=release/2.0

* Improve doc writing

* Fix elementwise add & sub

* Fix elementwise mul act

* a) add ut for complex variable; b) remove arg act in elementwise_ops

* Add trainable_statistics in attr for batch_norm
* Unifying behavior of dynamic graph and static graph

* add nll_loss op test=develop

* cherry-pick: fix converage ci (#23738)

test=release/2.0-beta

* modity ut
test=release/2.0-beta

test=release/2.0-beta, cherry-pick PR #23809: add 'seed' arguemnt of randint API

* change compare op fore_cpu true to false; test=develop

* pick fix warpctc bug in dygrpah mode; test=develop

* QAT: support range-based quantization and scales from attribute

* added support for channelwise

test=release/2.0

* fix tribilinear unitest, test=release/2.0

* add random seed,test=release/2.0

* Chery_pick:[Eernie TRT]: add slice op and add emb eltwise layernorm fp16 support (#23723)

* refine ernie trt dynamic shape support
1. add slice op converter
2. add emb eltwise layernorm fp16 support
test=develop

* fix dynamic shape test ut
test=develop

* fix comments.
test=develop

* fix comments
test=develop

* cherry-pick [BUG]: Head number can only be > 1 on multihead op (#23974)

* support the head number == 1
test=develop

* fix slice op error.
test=develop

* cherry-pick :disable trt test, test=develop (#23984)

test=release/2.0-beta

* add diag_embed op (#23385)

* add diag_embed op, test=release/2.0-beta

* solved a conflict, test=release/2.0-beta