* General optimization for no_varlen embedding layernorm

* fix wrong handler name

* mkldnn_engine -> onednn_engine

* remove fluid/errors.h imports

* remove fluid/enforce.h imports

* remove note and unnecessary import

* remove fluid/pretty_log.h imports

* remove fluid/place.h imports

* remove fluid/data_layout_transform.h imports

* remove fluid/device_context.h imports

* remove mkldnn_helper code

* remove fluid/mkldnn_reuse.h imports

* pretty_log import

* memory_optimize and mkdlnn problem

* update

* update

* update

* fix some transformer unitest

* clean ir_pass_manager and fix map_depthwise_conv_to_conv_pass

* fix unitest timeout

* general optimization no_varlen embedding layernorm

* delete Bias and ResidualData in OpMaker of conv2d

* delete extra input of conv3d

* refactor pass of conv_bias_fusion

* fix mkldnn dependency

* fix mkldnn compile

* fix test_conv_bias_mkldnn_fuse_pass

* police some code

* remove useless log

* fix analyzer_vit_ocr_tester

* fix conv_activation_mkldnn_fuse_pass

* fix test_analyzer_ocr

* add fused_conv_sig

* fix performence regression

* fix performance regression

* isort all files

* revert conflicting files

* revert conflicting files

* revert conflicting files

* Analysis API interface for disabling fc passes

* Unit tests corrected

* Python API added

* test runs only when PADDLE_WITH_MKLDNN

* Fc op changed to relu in matmul_op_test

* Disable fc passes in tests where acc drops

* code formating

* Unit test for analysisConf added

* Unit test gpu added

* fc passes disabled when iterations=0 in gru test

* style

* passes disabled when fp32 in gru test

* fc passes disabled in lstm test

* Import from inference, not fluid in doc

* allow fold fill_constant && allow nms3 into trt in int8 model
* use unordered_map
* fix CI failing

* [CodeStyle][E712] use `if cond`/`if cond is True` for comparison with `True`

* revert changes in fluid

* revert unrelated file

* revert changes in norm

* revert changes in auto_parallel_amp

* fix norm and auto_parallel_amp

* revert a typo fix due to fixed at #47477

* fix predictor memory write overflow

* update config

* re-blacken python code

* temporarily disable date and diff_py_file

* skip a format

* test=infer-coverage

* remove using lodtensor part1

* polish history code format

* [CodeStyle] remove all future import

* revert test_error.py

* restore future import in example code

* [Paddle Inference]support n lookup_tables fuse to embeddinglayernorm(1): add some funtion for embedding

* trim trailing whitespace

* fix `.cmake-format.py`

* revert npu ut changes, avoid npu ci error

* [CodeStyle] trim trailing whitespace in .md and .rst

* empty commit, test=document_fix

* update

* update

* update

add constant folding pass， for some model，it will get less latency；

* Reduce pool2d test configuration

* Reduce depthwise_conv2d test configuration

* Reduce trt_convert_conv2d_fusion test configuration

* Reduce trt_convert_conv2d test configuration

* Reduce trt_convert_conv2d_transpose test configuration

* Reduce trt_convert_hard_swish test configuration

* Enhance trt auto scan test error message and mechanism

* Increase FP16 trt ut tolerance

* test

* update

make linux link both paddle_inference_shared and paddle_inference_c to aoivid size increase (#44180)

This reverts commit bbe99555.