* update inference part

* restore white space

* delete gather_ut skip_case

* add trt version limit

* change Vector to std::vector and provide MixVector class as a helper wrapper class

* solve the multi-gpu hang problem

* remove the duplicate template instantialize

* Copy vector to cpu

* add CopyToCPU

* xxx

* final version: fix the problem of all reduce

* remove mixvector dependence

* fix

* merge

* fix code

* fix by CI

* fix pass and convert_op for preln_ernie and add preln_ernie'flag in pass

* fix RecordEvent interface

* modify default level to 4

* update interface use

* add const default trace level

* update record event interface using

* update record event interface using

* update operator.cc

* update part2

* update part1

* fix include profiler.h header in ps server

* fix include profiler.h header in ps server

* fix profiler.h header

* rename pten dir to phi

* rename namespace to phi

* rename infrt pten dir to phi

* resolve conflict

* rename pten to phi in cmake

* revert all infrt change

* change needed files

* fix infrt failed

* fix inference failed

* Unify paddle/pten::framework::ddim into pten::ddim

* fix paddle namespace

* compile sucessfully

* fix npu src file

* fix conflict

* fix conflict

* fix tensorrt compiler error

* fix conflict

* fix conflict

* fix tesst file conflict

* fix conflict

* fix mlu file conflict

* fix mlu file conflict

* fix cinn header file conflict

* fix conflict

* fix conflict

* fix conflict

* fix conflict

* move blas related files
* move lapack related files

* fix and add more tests

* remove unwanted changes

* check only concat and elementwise

* move check to a function

* add todo comment

* Revert "fix ptq fc attr name fuse_activation->activation_type"

This reverts commit ffd023353a5e9b0fd15e81b9e9f9fe1794035017.

* first commit

* teller fix

* bug fix

* enable for pool2d only

* fix global_pooling issue

* pooling_type

* fix test

[Paddle-Inference] support preln-ernie: add preln_emb_eltwise_layernorm_op, preln_skip_layernorm_op (#39570)

* support preln_ernie: add preln_emb_eltwise_layernorm_op, preln_skip_layernorm_op

* support preln_ernie: add preln_emb_eltwise_layernorm_op, preln_skip_layernorm_op

* remove reshape and elementwise_add registry

* delete code

* fix bugs when run ci ut

* remove log

* fix bugs when run unit test

* fix bugs when run unit test

* fix bugs when run cinn

* fix bugs when run ci-mac-python3

* fix compile bugs

* fix compile bugs

* fix compile bugs

* fix bugs when run kunlun

* fix bugs when compile

* update code according comment

[Paddle-Inference] support preln_ernie: add preln_embedding_eltwise_layernorm_fuse_pass, preln_skip_layernorm_fuse_pass (#39508)

* support preln_ernie

* support preln_ernie

* Replace GeLU plugin with TRT built-in layers for approximate GeLU

* Add TensorRT built-in layer for nonapproximate GeLU

* #1 migrate dist-related type()-> dtype()

* move datatype function from pten -> fluid/framework

* change type() in imperative into convert(dtype())

* modify xx_tensor->type into xx_tensor->dtype

* change the set_type interface and the caller

* modify xx_tensor.type into xx_tensor.dtype

* fix mutable_data(place, dtype())

* change caller of mutable_data in pten and distributed

* change the caller of mutable_data in fluid/framework

* change the caller of mutable_data in imperative directory

* mutable_data: inference

* update the call of mutable_data

* transfer MakePenScalarArray MakePtenScalar ResetHolderWithType

* pass the compile. the next step is remove VarType in Pten

* fix all and remove VarType from pten. success in linux. Next task is other platform

* fix conflict with develop

* fix compiled error

* Fix reset conversion

* fix conflict

* fix compiled problem

* fix typo

* Fix << in tensor_utils.cc

* fix type->dtype

* fix unittest

* fix tensor init constructor

* fix DataTypeSize for BFloat16

* fix code style

* fix npu compiled error

* fix npu

* compile npu sucessfully

* fix conflict

* fix conflict
Co-authored-by: Nxiongkun <xiongkun03@baidu.com>

* prevent squashing pair u8 dequantize -> s8 quantize

* add relu op to check for uint8

* fix ptq fc attr name fuse_activation->activation_type

* fix

* add unit test

* remove unused variable

* test fix unsuccessful

* fix test and logic

* multiline comment

* remove cout

* Revert "fix ptq fc attr name fuse_activation->activation_type"

This reverts commit ffd023353a5e9b0fd15e81b9e9f9fe1794035017.

* fix ptq fc attr name fuse_activation->activation_type

* support ernie quant model with interleaved

* support ernie quant model with interleaved

* support ernie quant model with interleaved

* support ernie quant model with interleaved

* support ernie quant model with interleaved

* support ernie quant model with interleaved

* support ernie quant model with interleaved

* mkldnn conv fix

* definetion

* rebuild matmul pass: trt and gpu_cpu

* rebuild matmul pass: trt and gpu_cpu

* rebuild matmul pass: trt and gpu_cpu

* rebuild matmul pass: trt and gpu_cpu

* slice

* shuffle pass enhancement

* [Demo] custom kernel based on pten kernel

* merge and npu custom work well

* del comments

* delete other code

* fix CUDAContext

* fix not found small_vector.h

* support NPU

* fix NPUContext

* fix DeviceContext support

* add UT

* fix call

* add UT

* fix

* fix for comments and ut

* add MACRO control

* fix multi input output

* support env CUSTOM_DEVICE_ROOT

* deal with special cases

* fix for Windows

* try coverage with test_custom_kernel_dot.py

* fix test_custom_kernel_dot

* fix test_custom_kernel_dot

* fix merge

* fix merge

* fix CI

* update

* merge and fix

* remove WITH_CUSTOM_KERNEL

* fix merge

* merge and fix

* fix ut

* fix ut for mac

* add more UT

* add more UT

* fix

* shuffle channel pass

* add ut

* timeout fix

* makefile fix

* Paddle-Inference:fix_concat_slice

* Paddle-Inference:fix_concat_slice

* Paddle-Inference:fix_concat_slice

* Paddle-Inference:fix_concat_slice

* [Paddle-Inference]: fix concat slice

* [Paddle-Inference]: fix concat slice

* [Paddle-Inference]: fix concat slice

* update cmake file to remove fluid kernel

* add pten declaration.h to where pybind.h used

* fix sync_bn and tensorrt_engine

* refine detection_library

* fix interpreter_core

* support eager legacy

* fit eager legacy for pten

* fall back to cpu if not found kernel

* fix compile problem

* fix compile problem

* refine fallback logic

* fit operator.run()

* fix xpu compile

* fit for new_exec

* add REGISTER_OP_WITHOUT_GRADIENT

* un-cache pt_kernel_context

* fix compile

* fix cudnn

* fix compiling with on_infer

* fix mkldnn

* fix isfinite_v2

* fix xpu problem

* fix op_device

* refine fallback for xpu

* fix xpu compile

* merge develop

* refine code format

* fix compile

* fix compile

* add data_transfer

* fix PreparePtenData

* fix cpu context

* merge develop

* fix compile

* fix error device context

* fix xpu

* fix dev_ctx

* support npu weight unified H2D copy

* remove redundant variable

* [inference] update convert reduce op&ut,test=develop

* update

* update

* update

* add int32 support

* add int32 support

* add comments

* trt < 7.0 do not support int32

* test=develop

* update

* test=develop

* Added selected_rows and rw_lock to pten

* Renamed the unit test target to fix CI

* Removed Class SelectedRows in Fluid, changed include/cmake relationship, use pten::SelectedRows in Fluid

* Remove rw_lock.h,rw_lock_test.cc in fluid

* Use pten::RWLock and pten::AutoRDLock, fix CI

* Use pten::SelectedRows

* Use pten::SelectedRows

* Fix to pass NPU CI

* Use pten::SelectedRows, to pass NPU CI

* To fix NPU CI

* To fix NPU CI again

* transfer: string tinyformat errors and part of enforce into pten

* remove comment

* fix by code review

* assert is not compile in -DNDEBUG

* add string as dependences of paddle_inference

* move dynload from fluid to pten.

* fix ci compile

* fix windows ci compile.

* update

* update

* fix compile error

* Mish

* Change exp() library

* mish fuse pass

* mish attrs

* fixes

* mishop maker

* remove attrs

* mish kernal for bf16

* fc+mish fuse

* fix code format error

* Resolve merge conflicts

* Update mish operator version

* update mish variable to new naming convention

* Merged LoDTensor with Tensor,test=allcases

* Patched python level LoDTensor

* Patched python level LoDTensor

* Merge Tensor into DenseTensor

* Fixed namespace issues,test=allcases

* Fixed merge issues

* Fixed inference issues

* Fixed NPU test issues

* Fixed merge issues

* fix trt convert conv2d skip

* fix trt convert conv2d skip