* fix global gather and global scatter operators

Add Tokenizer related functionalities for Transformer model in order that the process of training and predicting is consistent.

* support the text string as an input Tensor
* support the "VOCAB"unordered_map<wstring, int> as an input Tensor to lookup tokens
* Tokenizer used for BERT. This tokenizer applies an end-to-end, text string to wordpiece tokenization.
* It first applies basic tokenization, followed by wordpiece tokenization.

* Support elementwise_add triple grad Kernel

* Change code-format to follow CI std

* [NPU] Add iou_similarity op

* [NPU] Add iou_similarity op

* [NPU] Add iou_similarity op

* fix replicate pad when input size is 0
* add unit test

* Add QR decomposition op

* Change codes to adapt to new svd_helper

* Update linalg.py

Restore the deleted comma

* Restore the deleted line

* Update linalg.py

* Update linalg.py

* Improve the qr code by reviews

* Update QR based on CI results

* Update qr doc, test=document_fix

* Change unsafe and ill-formed codes

* add pow2_warmup op

* remove contrib __all__

* add AttrT

* rename

* follow comments

* fix duplicate PADDLE_RESTRICT

* added softplus

* refactored softplus op

* deleted unnecessary file

* added missing file

* added formatting

* disabled tests if GPU is used

* added reviewer suggestion

* unified softplus kernel

[XPU AMP] 1. xpu support gradient acc 2. xpu support create tensor in dygraph 3. xpu support update weight params in amp (#36439)

* remove wrong restrict

* remove master_param_out __restrict__

* update

* native commit for triple grad of sigmod

* Updated unittests files

* init functional jacobian api

* Updated trible_test func

* Updated gradient_checker & test_script

* finish test with dtype float32

* add float64 test case

* polish code

* use atol=1e-5 with dtype float64

* fix for ci

* set timeout for test_jacobian

* fix dygraph grad to support high differential

* polish API docstring

* Updated gradient checker and some related files

* fix double grad strip error for high differential

* fix double grad strip error for high differential

* Add Sigmoid triple grad tests

* fix dygraph double grad dtype error when calling for high differential senario

* Updated triple grad teses func

* Use np.random to initialize ddx

* Updated triple_grad_check func

* add todo for gradient checker and refine some comments

* remove additional code

* add test for warnging in backward.py

* add tanh triple grad

* format python code

* refine code
Co-authored-by: Nveyron95 <veyron_wu@163.com>
Co-authored-by: Nlevi131 <limaolin01@baidu.com>

* support bert when exists matmul_v2

* update

* [NPU] Add density_prior_box op

* [NPU] Add density_prior_box op

This reverts commit bf748f24.

* merge momentum ops

* update

* add ut to improve coverage

* remove optimizer change

* fix error msg

* update ut

* add __restrict__ for CUDA

* update ut

* move merged_momentum_op to optimizer dir

* fix coverage

* update

* update

* update

* try make CI pass

* doc typo

* update doc string

* A leap of try for cudaLaunchCooperativeKernel

* fix bugs

* Totally replace the lar cuda kernel

* Fix bugs

* a test for lars merge

* Adding las_op_momentum infer_shape

* Fix codes

* use avg_numel instead of max_numel to acquire grid num

* modify unittest files about lars op

* Finally converge when merged-lars works

* fix ctest files

* add merged_operation kernel when cuda version is older than 11

* Fix code style

* fix ctest failure

* fix error

* fix all ctest error and change lars compute code of cpu

* fix bugs on v100.

* revert python modififation about lars

* revert python modification codes

- Lint

- Merge with develop

- lint

* native commit for triple grad of sigmod

* Updated unittests files

* init functional jacobian api

* Updated trible_test func

* Updated gradient_checker & test_script

* finish test with dtype float32

* add float64 test case

* polish code

* use atol=1e-5 with dtype float64

* fix for ci

* set timeout for test_jacobian

* fix dygraph grad to support high differential

* polish API docstring

* Updated gradient checker and some related files

* fix double grad strip error for high differential

* fix double grad strip error for high differential

* Add Sigmoid triple grad tests

* fix dygraph double grad dtype error when calling for high differential senario

* Updated triple grad teses func

* Use np.random to initialize ddx

* Updated triple_grad_check func

* add todo for gradient checker and refine some comments

* remove additional code

* add test for warnging in backward.py

* format python code
Co-authored-by: Nveyron95 <veyron_wu@163.com>
Co-authored-by: Nlevi131 <limaolin01@baidu.com>

* [NPU] modify for model deepfm

* [NPU] unit test delete precision control

* [NPU] add more unit test

* revert elementwise_mul related modification

* [NPU] add more unit tests for concat

* [NPU] fix elementwise_mul to support broadcast, test=develop

* remove debug files, test=develop

* add axis support, test=develop

* [NPU] add int64 kernel for scale and slice, test=develop

* remove int64 for scale, test=develop

* Fix stop_gradient in RunProgramOp

* fix reference

Add paddle.nn.functional.sparse_attention API

    本个PR主要将sparse_attention功能在python层进行了一层封装，OP的主体代码见：#PR35676

    此外，对于封装的python 接口，增加了相应的单测。