* Layer norm rollback 2 plugin when trt<8.6

* [inference][trt]modify test timeout  and test_trt_convert_activation bug fix (#54491)

* modify tensorrt ci timeout

* activation ci bug fix

* comment out  int8 mode test_trt_dynamic_shape_groupnorm

* Update layer_norm_op.cc

code style

[inference][trt]unary, bitwise_not,one_hot op and inspector ci adjust for TensorRT8.6 (#54251) (#54579)

* unary bitwise_not adapter tensorRT8.6 in Paddle-TensorRT

* one_hot_op ci fix

* Update test_trt_inspector.py

delete log

[inference][cherrypick] Implement layer_norm op using INormalization Layer and conv_fusion support bias's rank equal to input's rank  (#54590)

* [inference]conv_fusion support bias's rank equal to input's rank (#54477)

* support bias's rank equal to input's rank

* [inference][trt]layer_norm op with dynamic shape support INormalizationLayer in TRT8.6 (#54379)

* layer_norm op with dynamic shape support INormalizationLayer in TRT8.6

* Using trt layer to make layers_norm op in lower than trt8.6
layer_norm op with dynamic shape support INormalizationLayer in TRT8.6

---------
Co-authored-by: Nbukejiyu <52310069+bukejiyu@users.noreply.github.com>

* update roll convert

* mv all unittests test

* fix error

* fix error

* fix

* fix

* del unittests

* fix paddle_build.sh

* fix

* fix test

* fix add test

* fix

* fix

* fix

* merge develop

* fix

* fix

* fix

* fix

* fix

* merge develop

* fix test_async_read_write

* fix test_async_read_write

* merge develop

* fix

* fix import legacy_test

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix bug

* fix

* fix coverage test bug

* fix

* fix

* fix

* fix

* fix

* fix code sstyle

* fix code

* fix code

* fix

* fix

* fix

* del test_sequence_enumerate_op.py

* fix

* fix fp16 io

* disable precision test

* add tranfer_elim
* transfer layout elimination

* [dygraph]unify _non_static_mode() in_dygraph_mode() and in_dynamic_mode()

* [dygraph]unify _non_static_mode() in_dygraph_mode() and in_dynamic_mode()

* [dygraph]unify _non_static_mode() in_dygraph_mode() and in_dynamic_mode()

* [dygraph]unify _non_static_mode() in_dygraph_mode() and in_dynamic_mode()

* [dygraph]unify _non_static_mode() in_dygraph_mode() and in_dynamic_mode()

* [dygraph]unify _non_static_mode() in_dygraph_mode() and in_dynamic_mode()

* fixed cyclic reference that caused patial import

* fixed bad change

* fix bad import

* fix bad import

* fix bad import

* fix ut failed caused by change in_dynamic_mode

* fix ut failed caused by change in_dynamic_mode

* fixed usage of in_dynamic_mode() or in_dygraph_mode()

* revert python3 to python in .pre-commit-config.yaml

* fix merge conflicts

[Inference] add config.enable_low_precision_io api and remove rely on AnalysisConfig::Precison in trt (#52485)

* Improve Readability and Overall Clarity of Logging

* Adds the set_input_type API for specifying input data types

* Specifying input data types

* Revert "[inference][trt]add trt sparse weights switch (#53562)"

This reverts commit 4a69a536.

* remove kSPARSE_WEIGHTS

* remove kFASTER_DYNAMIC_SHAPES_0805 and add 'TrtMajorVersion' function

* Fused elementwises kernels and ops

* change fuse pass name

* adjust .pbtxt files

* adjust quantization attributes

* add missing arguments and fix others, review fixed

* simplify fused kernel registration

* fix elementwise unit tests

* reuse one fused elementwise op

* adjust proto

* Add supported datatypes

* Change 'Scale' to 'scale' in tests, change some tests to onednn

* Revert breaking changes

* Fix unit tests

* Delete obsolete test cases

* Delete commented out code

* Fix codestyle

* delete temporary condition

* fix conflicts and delete duplicate fusing

* Fix code after merge

* Move tests to new directory

* fix tests volatility

* Rename test_elementwise_add_onednn_op.py to test_elementwise_add_mkldnn_op.py

* Update CMakeLists.txt add mkldnn op test

---------
Co-authored-by: NSilv3S <slawomir.siwek@intel.com>

[inference Zero-Dim][trt] Add Zero-Dim tensor support for clip, cast, flatten_contiguous_range (#53769)

* [inference Zero-Dim][trt]clip,cast,flatten_contiguous_range trt op converter support zero dim

* softmax support

* support stack

* support_act
* delete_silu

* prelu op trt converter support zero dim

* support_expand_mish

* delete delete_fill_constant_op_pass and unsqueeze2_eltwise_fuse_pass

* fix trt Unary operation do not support 0d when TRT < 8.6

* update unary ut

* add rsqrt to unary_list

* move rsqrt to act_list

* Add trt pow converter.

* update to use AddConstantLayer

* add dims=0 ut

* trt support 0 dim

* trt support 0 dim

* update activation ut

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* support promote dtype for static amp training

* unify o1 and o2

* update for unittest

* fix op_role

* add use_promote arg

* fix doc

* add promote unittest

* polish unittests

* fix controflow and test