* batch_norm_act_fuse_pass_init

* repair the unittest of batch_norm_act

* simplify_with_basic

* fix

* scale factor

* 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

* fc_elementwise_layer_fuse_pass

* fc_ele_layernorm_pass

* fc_elementwise_layernorm_pass

* fc_elementwise_layernorm_pass_amend

* optimize OP's compilation time, test=develop

* add more op and run ci test, test=develop

* CUDA Kernel register in cc file, test=develop

* fix macros, test=develop

* fix undefined symbol error, test=develop

* fix compilation error and undefined symbol, test=develop

* fix compilation error on Windows, test=develop

* fix compilation error on Windows, test=develop

* Add dlnne engine runtime

* Fix log

* Remove <const_cast> and remove unrelated modify with dlnne, +clang-format

* Fix CMakeList format error

* Add copyright message

* Fix dlnne CMakeList.txt

* Add some paddlepaddle_pass to support more networks

* Fix some format bug

* Add delete dropout_op pass

* Fix some format bug

* Fix format bug

* fix airank bert emb order

* move input num check to converter

* add input num check

* add unused var check white list

* support ernie trt-int8 for inference

* fix reshape

* support multihead_matmul_fuse_pass_v3

* fix compile problems

* embedding_eltwise_ln pass support lookup_table_v2

* suppoort matmul and matmul_v2 in qkv matmul

* delete include framework.pb.h

* fix error

* added support for fake_quantize_dequantize_abs_max op in quantization inference pass

* remove const_cast to pass ci

* remove compare operator to pass ci-coverage

* added detailed error message for unregistered tensorrt_subgrah_pass

* Unification of bfloat16 enablement process and refactor

* Remove unnecessary function

* Standardize the output name search

* Add conv transpose BF16

* Share function GetWeightsTz

* Adjust to review and fix op compatibility

* Add bias to unique handler name

* Remove errors related to paddle enforce

* Add conv2d_transpose to bf16 list and kernel refator

* Additionally change to not throw error from inside pass.

* use iwyu clean include second time, test=develop