* 裁剪transformer模型trt支持；修复tensorRT不支持DeletePass的bug (#28517)

* skip_layernorm_op done

* add unittest

* slice op convertor support trt < 6

* skip_layernorm only work in ernie

* fix unittest

* fix unittest

* Fix TRT plugin registry without TRT lib (#25982)

* fix trt plugin registry without trt lib

* support trt4

* refine code style

* pick ea851796 from develop

* cherry-pick develop PR  #26273 && #27796

* fix unittest error

* fix unittest error

* remove const_cast
Co-authored-by: NPei Yang <peiyang@baidu.com>

* optimize slice TRT plugin

This patch removes unnecessary barrier for data transfer of needed offset,
so data transfer can be overlap with GPU kernel execution.

This patch also fixes incorrect name of slice plugin. That is, replaces
"layernorm" with "slice"

test=develop

* add serialize/deserialize to slice plugin

* add static shape slice trt plugin

* fix slice trt op convertor dynamic shape bug

* fix format by clang-format

* fix pylint format error

* fix problems commented by peiyang
Co-authored-by: NRyan Jeng <rjeng@nvidia.com>
Co-authored-by: NShang Zhizhou <shangzhizhou@baidu.com>
Co-authored-by: NRyan Jeng <rjeng@nvidia.com>

* [Paddle-TRT] Stack op plugin (#25605)

* add stack_op to CMakeLists

* add dim=3 support for scale op

* add trt stack op, test=develop

* remove debug message

* add stack plugin serialize

* remove slice, scale op, will add later

* enhence error message

* revise trt ernie test to conver the stack op CI testi, test=develop

* add stack op serialization

* fix test shape after adding stack op

* remove slice op, will add after implementing serialization

* roll back to min_graph=5 to avoid using slice op

* fix scale op output layer

* implement stack op createPlugin

* use workspace and move the defination to .cu

* move stack plugin creator definition to .cu, test=develop

* sync ut with develop
Co-authored-by: Nzlsh80826 <zlsh80826@gmail.com>

This commit fixs the compiling bug regarding unique_ptr of IOptimizationProfile.

IOptimizationProfile has protected dtor and is controlled by TensorRT
internally. Application shouldn't delete the pointer of IOptimizationProfile.
See TensorRT document: https://docs.nvidia.com/deeplearning/sdk/tensorrt-api/c_api/classnvinfer1_1_1_i_builder.html#a9ac47e100454151d8206ac91d543299a
test=develop
Co-authored-by: NJeng Bai-Cheng <jeng1220@users.noreply.github.com>

* add macro check for using TRT api dynamicRangeIsSet() (#25694)

* adjust minimum trt version for hard_sigmoid converter to 5130. test=develop (#24746)

* solve conflict

* fix crash when trt not found in python; update unittest model path

* fix multhead matmul's instable
test=develop

* fix multihead matmul bug
test=develop

* fix converage problem
test=develop
Co-authored-by: NZhaolong Xing <nhzlx.dragon@gmail.com>

test=release/1.8

* fix bug of prelu when rank not equal 4, test=develop

* fix prelu inference, test=develop

* fix api, test=develop

* fix shape when mode is chennel, test=develop

* remove debug code, test=develop

* add unittest, test=develop

test=develop
Co-authored-by: Nnhzlx <nhzlx.dragon@gmail.com>

* 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

* cherry-pick,Optimize the error messages of paddle CUDA API

* fix the error messages of paddle CUDA API

* Refactoring PADDLE_ENFORCE_CUDA_SUCCESS, and apply to curand/cudnn/cublas/NCCL

* remove build_ex_string

* OP clip, merge_lod_tensor, convert/elementwise error message enhancement. test=develop

* add elementwise pool2d, prelu, shuffle channel
test=develop

* add scale and refine concat eltwise conveter
test=develop

* refine elementwise converter
test=develop

* refine ut test and enforce error.
test=develop

* modify const cast
test=develop

* refine act conv2d pool2d fc, trt converter log
test=develop

* fix comments
test=develop

Revert "[Paddle-TRT] Add hard_sigmoid and hard_swish support(support MobilenetV3) (#23536)", test=develop (#23642)

This reverts commit cdc6d4e2.

* add hard_sigmoid trt op converter

* add hard_swish op converter and plugin. test=develop

* add full_like op. test=develop

* add dygraph support. test=develop

* increase coverage. test=develop

test=develop

* add dynamic plugin support.
test=develop

* change emb eltwise layernorm to math function
test=develop

* add emb eltwise layernorm
test=develop

* can run dynamic shape ernie
test=develop

* fix ci
test=develop

* add ut for trt ernie dynamic

test=develop

* refine dynamic shape c++ interface.
test=develop

* fix comments
test=develop

* fix comments
test=develop

* change the ci trt from version 5. to 6.0

* paddle-trt dynamic shape support init

* conv+bias or conv+bn dynamic shape support
test=develop

* modity trt engine opconvert
test=develop

* fix ci error
test=develop

[Refine Paddle-TRT INT8]: Support PaddleSlim's Resnet50, Mobilenetv1, Yolov3 models for Inference. (#22483)

* add int8 op teller for trt.

* refine trt int8

* add int8 op teller for trt.
test=develop

* add mutex for trt engine
test=develop

* add the test for copy_to_cpu
test=develop

faster build by reduce by-product, reduce linking library and fix compile warning of std=c++11 (#22164)

* add TRT support for instance_norm op

* add gelu plugin

* align trt bert with gpu

* add support for fused fc with relu,

* add unittest for bert trt

test=develop

added splitter "__" between weight name and suffix number to avoid conflicts.

* refine trt int8 for dynamic range set
test=develop

* refine trt int8
test=develop