* Implement conv2d_fusion NHWC format using CUTLASS
* Add unit testing for CUTLASS Conv in inference
* Add experimental API for CUTLASS.

* refactor conv_activation_mkldnn_fuse_pass

* refactor conv_affine_channel_mkldnn_fuse_pass

* fix conv_activation_mkldnn_fuse_pass

* fix mkldnn unittest

* refactor int8_scale_calculation_mkldnn_pass and params_quantization_mkldnn_pass

* refactor conv_elementwise_add_mkldnn_fuse_pass

* fix quant

* refactor conv_bn_fuse_pass

* fix conv_bn_fuse_pass

* refactor depthwise_conv_bn_fuse_pass

* fix unittest

* fix conv_bn_fuse_pass

* remove redundant conv2d in params_quantization_mkldnn_pass

* fix params_quantization_mkldnn_pass_tester

* clean ir_pass_manager and fix map_depthwise_conv_to_conv_pass

* fix unitest timeout

* update memory_optimize pass

* add config param for enable_dlnne and support calibration mode
* remove useless file
* refine code and add annotation
* refine code of Warnning tips

* update trt workspace size param

* update

* update

* update

* use int64_t

* use int64_t

* upate

* update

* inference add convert to mixed model ability.

* revert 40531

* update

* new general transformer inference support

* update lite compile cmake

* Update delete_fill_constant_op_pass.cc

* Update analysis_config.cc

* add mkldnn int8 pass [step3]

* Add test for compute_propagate_scales_mkldnn_pass

* update pass

* update api comment and python api
Co-authored-by: Nwozna <joanna.wozna@intel.com>

* add flatten2,reshape2,squueze2_trt_fuse_pass  test cast

* add flatten2,reshape2,squueze2_trt_fuse_pass  test cast

* add flatten2,reshape2,squueze2_trt_fuse_pass  test cast

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

* add Paddle Trt config: with_interleaved

* 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

* 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

* add dla

* add dla done

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

* snap

* add inference api: DisableTensorRtOPs

* fix code style

* update api to experimental

* update variable name

* Add bfloat16 softmax and gelu

* Add pass attr bfloat16_enabled_op_types

* Changes from review

* fp16 result ok

* change -DWITH_NVINFER_PLUGIN toconfig.EnableTensorRtOSS

* auto detect special slice op converter for ernie with trt oss

* ernie oss only support fp16

* fix special_slice_plugin serialize bug

* matmul in tensorrt ok

* ernie unittest ok

* add matmul tensorrt unittest

* remove demo code