* add Paddle Trt config: with_interleaved

roi_align aligned supported

* Added shared_ptr<Allocation> member & corresponding interfaces to Storage

* Removed original pten::Allocation from Storage and adjusted the interfaces accordingly

* Fixed issues with storage offset

* Used place to malloc allocation for TensorStorage

* [Unify Tensors PR #3]Ported framework::Tensor interfaces to pten::DenseTensor

* Fixed issues with place

* Added comments

* Moved mutable_data with stream argument to DenseTensor

* Added set_offset interface

* Fixed CI issues,test=allcases

* [Unify Tensors PR #4] Port LoDTensor interfaces to DenseTensor

* Removed friend class EigenTensor/EigenMatrix/EigenVector from Tensor

* Modified framework::Tensor to inherit from DenseTensor

* Reverted changes too pten_layout() interface

* Removed friend classes

* Rearranged cfunction calls from tensor.data<void>() to tensor.data()

* Fixed CI issues

* Fixed lite issues

* Fixed data() interface issues,test=allcases

* Resolved IsInitialized() issues

* Fixed ResetHolder() issues

* Fixed MKLDNN & Storage issues

* Resolved ShareBufferWith() issues

* Fixed LoD issues

* bug fix

* remove blank

* c_api support std::string

* update

* update

* add NOTE

* fix delete error.

* Quantize nearest_interp and nearest_interp_v2

* Check if avx_core supported

* Add depthwise_conv2d to supported quantization list

* glog fix

* changed approach

* dynamic shape clone supported

* block warning when build demo_ci and infer_ut

* use build pipe line clone to test

* support external stream.

* update

* update

* update

* support FP16 for more ops

* add amp list tests

* refine reduce_mean_grad

* fix OP benchmark ci

* fix fp16 reduce_mean

* updat ut, but still have some problems

* remove mean/reduce_mean fp16 kernel

* add matmul_scale matmul_v2_scale fuse pass

* add scaletensor judge

* modify var name

* add timeout notest;test=coverag

* fix error commit

* fix use_mkldnn attr

* fix use_mkldnn attr

* Inspect the information inside a TRT engine.

* Follow up the google code style.

* Fix code error.

* add mkldnn conv3d_bias_mkldnn_fuse_pass ut

* update conv3d_bias_mkldnn_fuse_pass ut

* disable conv3d_bias_mkldnn_fuse_pass

* add ipu_inference

* resovle commments

* resolve comments

* add EnableIpu introduction

* rm line

* restore npu update

* add ernie and resnet50 test

* fix copyright time
Co-authored-by: Nyaozhixin <522190855@qq.com>

* add conv_gelu_mkldnn_fuse_pass

* add post ops

* reshape+transpose+matmul_v2

* in_name->input_name

* fix pr-ci-static-check

* add restriction on plugin supportsFormat to eliminate errors from TensorRT8

* ernie-varlen is only supported on architecture >= sm75

* fix_ele_convert: IElementWiseLayer can broadcast

* fix_ele_convert

fix: when ceil_model==true && Padding_algo!=SAME, (x-size)/stride != int, this convert is wrong (#37929)

* multithread_memory_optimize

* quantize slice op

* correct test

* fix code formatting

* fix

* Update stack_op_plugin.cu

comments

* refine structure for cuda and rocm

* update

* update

* update

* update

* add trt_mobilenet demo test

* only deliver trt_root in run.sh

* support data_format='NHWC' for prelu channel mode

* [NPU] reorganization for device API abstraction

* [NPU] delete old files

* [NPU] fix npu_collective_helper

* [NPU] fix collective_helper

* [NPU] fix ut

* [NPU] mod memory allocation and hccl_helper

* [NPU] fix place_type

* [NPU] split enfoce.h

* move acl* call into npu_info

* merge conflict

* fix merge

* merge conflict

* merge conflict

* matmul_convert_int8

* matmul_convert_int8

* matmulconvert_int8

* Matmul_int8_convert: tensor*tensor

* Matmul_int8_convert: tensor*tensor

* Matmul_int8_convert: tensor*tensor

* modify code about fp16 of dcnv2 trt

* fix_nearest

* fix_nearest

* fix_nearest

* fix_nearest