[Inference] Replace groupNorm when data types are bf16 and fp16, and data format is NHWC implementation. (#55399)

* finish

* cpergroup odd

* fix bf16

* single channel

* code style

* jingdu duiqi

* add head_file

* add bf16 head file

* bf16 2

* bf16

* bf16 head

* bf16 compile

* py test

* bf16 compile

* bf16 compile

* unset py test

* nhwc

* test

* mean var

* bf16 success

* su

* ctest success

* use is_same_as

* is_same

* use is_same

* rtol

* gpu_stream

* del sigmod

* fix bfloat16 type

* use cuda_bf16_hpp

* use_cuda_arch

* bfloat162float2

* del inplace_tol

* del max_releative_tol

* temp store

* jingdu duiqi

* temp store

* plugin

* jingdu duiqi

* duiqi

* include cuda.h

* del half

* half single

* ci

* add const

* ci

* cudamemset

* del printf

* fp16 test

* add half compute

* del br16 ci

* del ci

* ci approve

* del fluid include

* fix security bug

[CodeStyle] replace `assert np.allclose` with `np.testing.assert_allclose` and `assert np.array_equal` with `np.testing.assert_array_equal` (#55385)

* update TestAPI arguments to enable param_attr and bias_attr in test_layer_norm_op

* add bf16 condition in test_layer_norm_op

* add fast_math condition

* simple reaplce

* for debug

* fix bugs

* fix some bugs

* del fill_constant_batch_size_like

support stride

* add fp16 and bf16 support for poisson

* add fp16 and bf16 support for searchsorted

* fix bug

* Update test_searchsorted_op.py

fix function name

* Update test_poisson_op.py

fix function name

* fix bug

* remove the searchorted

* Update test_poisson_op.py

* fix bug of TestPoissonBF16Op

* Update test_poisson_op.py

* Update test_poisson_op.py

* Update test_poisson_op.py

* fix bug of import

* fix bug

* update

* update

* add complex dtype for tanh

* add test case

* support complex for sin, cos and tan

* support gpu

* fix error in cpu

* fix gpu error

* set check_prim to False only for complex type

* bugfix fused_multihead_matmul

* fix test case of fused multihead matmul

---------
Co-authored-by: Nbukejiyu <395822456@qq.com>

* add int32/int64 for outer/matmul Kernel.

* fix by comment.

* fix by comment

【inplace api】batch add inplace api paddle.log_, paddle.i0_, paddle.nn.functional.leaky_relu_... (#55576)

* batch add inplace api

* add inplace test

* add activation inplace

* fix test

* remove atan2 ge, gt, le, lt, nq

* remove atan2 ge, gt, le, lt, nq

* fix windows ci error

* rerun ci

* fix typro

* fix bugs

---------
Co-authored-by: Nzhangrui34 <v_zhangrui34@baidu.com>

* remove api staticrnn

* move select_input/output to static/controw flow

* delete some func, only remain Switch

* clean fluid.layers.controw_flow

* remove fluid.layers.controlflow

* fix conditional_block ut

* Fix LayerNormForward perf issue

* Bugfix, fast_layer_norm OOB

* apply pre-commit

---------
Co-authored-by: NShijie Wang <jaywan@nvidia.com>

* fix random fail of test_bilinear_interp_v2_op

* reset if compiledProgram

* [尝试] 给tensor增加一个属性, 这个属性是一个定值 1

* 暴露gradnode 并构建gradnode新的方法(用来测试)进行暴露给python python端可以访问

* 开发grad_fn、next_functions两个API 并暴露到python端- 做一些规范化处理

* 增加一个单元测试

* 优化 code-style

* 将单侧文件迁到正确的位置

* 优化 code-style

* 删除无用注释

* 解决 __main__ has no attribute

* 修改单侧文件

* 修改单侧脚本-temp

* 解决 grad_fn next_functions api 接口导致内存异常的问题

* 修改单测内容

* 解决 code-style 问题

* add IndexPutGradInfermeta to fix backward error in static-mode

* codestyle

* Fix test failed on cudnn.

* Fix codestyle.

* fix new launch

* fix ps uit

* [尝试] 给tensor增加一个属性, 这个属性是一个定值 1

* 暴露gradnode 并构建gradnode新的方法(用来测试)进行暴露给python python端可以访问

* 开发grad_fn、next_functions两个API 并暴露到python端- 做一些规范化处理

* 增加一个单元测试

* 优化 code-style

* 将单侧文件迁到正确的位置

* 优化 code-style

* 删除无用注释

* 解决 __main__ has no attribute

* 修改单侧文件

* 修改单侧脚本-temp

* Fix TRT multihead matmul UT failure

* fix

* fix

* fix

* fix

* fix

* fix coverage ci

* add test case