* Revert "Revert "Add copy from tensor (#34406)" (#35173)"

This reverts commit 32c1ec42.

* add template instantiation

* Add calculation for gru op

* Correct the types

* Remove mkldnn only

* Correct mkldnn ifdef

* Remove mkldnn ifdef

* Separate mkldnn quantizer test

* Correct Windows test

* Check different cmake fix

* Revert cmake change

* Cmake change 2

* Cmake change 3

This reverts commit ac33c0ca.

* add api

* temp save

* revert

* copytocpu async ok

* fix style

* copy sync ok

* fix compile error

* fix compile error

* api done

* update python async api

* fix compile

* remove async python api; add c++ async unittest

* remove python async api

* update unittest

* update unittest

* add C++ unittest for copytensor

* add unittest

* update namespace utils to class TensorUtils

* add unittest

* update unittest

* update unittest

* update code style

* update code style

* update unittest

* qkv

* ci_test

[Inference Tensorrt] Add attr for trt engine and handle the input seq problem for ernie var len. (#33575)

* Small changes related to BF16 fusion_gru and fusion_lstm

* Correct to pass arg by value

* Add conditions to rnn op

* Correct the spelling mistake

* Improving the test with checking activation

* Trigger CI

* - Second fix

- fix

* - fix

* - First fix to #33021

* download_verify

* checksum

* CI skip inference test if only python files modified, test=develop

* fix compilation error on ROCM, test=develop

* fix cmake error on PR-CI-ROCM-Compile, test=develop

* fix cmake model path

* update cmake

* fix unittest

* fix unittest

* Different machine generate different binary file, remove md5 check

* remove unnecessary functions

* support trt serialize when load model from memory

* delete conv_bn_fuse_pass before tensorrt, with which trt serialize engine id is not stable

* Revert "delete conv_bn_fuse_pass before tensorrt, with which trt serialize engine id is not stable"

performance degradation, fix in the future

This reverts commit fa6cd17e60b15df351efda379ddd00e9e9c1fea9.

* add delete conv_bn

* delete path when delete_cache_files

* update trt int8 calibrator to IEntropyCalibratorV2

* add delele opt_cache for trt_split_converter_test

* update paddle_fluid.so to paddle_inference.so

* bug fix of xpu lite engine, test=develop

* xpu zero copy tensor, test=develop

* revert paddle/fluid/inference/tests/api/CMakeLists.txt

* support xpu inference with analysis predictor, test=develop

* merge the cmake of the xpu toolchain, test=develop

* add c-apis, test=develop

* fix a bug in extern_xpu, test=develop

* update lite tag

* disable ut

* solve python3 incompatibility issues

* update checksum

* add dla

* add dla done

* add python api
Co-authored-by: Nshangzhizhou <root@szth-rp-fanyi-opera49.szth.baidu.com>

[XPU] Remove lite_xpu ut lite_resnet50_test since fusion pass changes introduced precision diff. test=develop (#30122)

* snap

* add inference api: DisableTensorRtOPs

* fix code style

* update api to experimental

* update variable name

* zero_copy_tensor supports int8_t

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)