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

* 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>

* remove prelu land ookuip_table plugin, adjust .h include location

* clean code and adjust some .h

* update

* test,test=develop

* test,test=develop

* test,test=develop

* test,test=develop

* test,test=develop

* test,test=develop

* delete delete_fill_constant_op_pass and unsqueeze2_eltwise_fuse_pass

* add flags for phi

* fix compile bugs

* fix ci bugs

* fix inference bugs

* fix cinn' bugs

* fix cinn bugs

* perfect code according comment

* fix ci bugs

* fix ci bugs

* [CustomDevice] add pipeline parallel support

* update

* update

* mv inference/api infer_ut

* mv test

* merge develop fix error

* fix

* fix build error

* fix build error

* fix bug

* fix tester_helper.h

* fix analyzer_transformer_profile_tester.cc

* fix

* fix mac

* fix mac

* fix error

* fix

* fix

* remove c++14 assert and remove include tensor.h in phi

* Paddle-Trt: Replace fc mul matmul matmul_v2 with matrix_multiply

---------
Co-authored-by: NZhang Jun <ewalker@live.cn>

* Support two inputs of multihead attention named qk_multihead