* snap

* add inference api: DisableTensorRtOPs

* fix code style

* update api to experimental

* update variable name

* zero_copy_tensor supports int8_t

* register instance norm, test=op_version

* add the support the op version check for matmul, test=op_version

* add the op version check for the elementwise ops, test=op_version

* add the support check for elementwise_ops, test=op_version

fix ut:trt_resnext_test, trt_quant_int8_yolov3_r50_test, test_trt_dynamic_shape_ernie, test_trt_dynamic_shape_ernie_fp16_ser_deser, trt_cascade_rcnn_test (#29977)

* map matmul/squeeze2+matmul/reshape2+matmul to mul

* fix a bug in reset_tensor_array, test=develop

* ci coverage, test=develop

* oneps (3/4)
Co-authored-by: NMrChengmo <cmchengmo@163.com>
Co-authored-by: Nmalin10 <malin10@baidu.com>
Co-authored-by: Nchengmo <chengmo@baidu.com>

* enable_use_gpu has higher priority than FLAGS

* update.

* - Added infrastructre for new test

 - Added UT for Multiple models prediction

- cosmetic fixes

- lint

- lint fixes

* - Removed timeout for MMP test

* change hard_swish from plugin to layer

* add ut when threshold != scale

* fix tensorrt unittest precision error

* fix unittest precision error. test_trt_subgraph_pass && test_trt_dynamic_shape_transformer_prune

* fix tensorrt output shape error

* fix unittest tensorrt_engine_op_test

* fix code style for unitest

* remove -DSUPPORTS_CUDA_FP16 in cuda.cmake

* comile with cuda9

* add some unittest

* notest;test=coverage

* add unittest for trt plugin swish && split

* update ernie unittest

* fix some error message

* remove repeated judgement of CUDA version in mbEltwiseLayerNormOpConverter

* fix comile errror when CUDA_ARCH_NAME < Pascal"

* fix comile error

* update unittest timeout

* compile with cuda9

* update error msg

* fix code style

* add some comments

* add define IF_CUDA_ARCH_SUPPORT_FP16

* rename IF_CUDA_ARCH_SUPPORT_FP16 to CUDA_ARCH_FP16_SUPPORTED

* change avg pooling and global pooling to trt layer

* add support for static shape global pooling

* modify trt errmsg

* register op_version for addto

* upgrade pass capability

* change eq to le

* change eq to le

* fix merge

* skip_layernorm_op done

* add unittest

* slice op convertor support trt < 6

* skip_layernorm only work in ernie