* fix embedding fused

* preln_res_bias_layernorm bugfix unroll opt

* code style refine

* NOLINT for codestyle

make fused_multi_transformer support dynamically set the cache_kvs' shape and support input prefix_caches. (#46777)

* make fused_multi_transformer support dynamically set the cache_kvs' shape and support input prefix_caches.

* delete_quantize_headerfile

* delete_requantize_headerfile

* op migrated, Copy(OneDNNContext, ...) added

* mutable_data & op registration in fluid removed

* refactoring

* OneDNNGetDataType to uppercase

* missing cpu check added, handler moved to .h file

* name changed to transpose_grad

* Copy changed back to TensorCopy

* Resizing corrected, Copy(OneDNNContext) removed

* fix:gather op

* add ut

support fp16 for deformable conv

* it is a test

* it is a test

* it is a test,test=coverage

* optimizing the proceess of generating ut_file_map.json

* optimizing the proceess of generating ut_file_map.json

* optimizing the proceess of generating ut_file_map.json

* optimizing the proceess of generating ut_file_map.json

* fix fp16

* remove debug info

* code style refine

* enable hard_swish_grad unit test

* remove unused argument

* optimize Paddle-TRT performance

* fix some doc bug test=document_fix

* fix some docs issues, test=document_fix

* beta -> \beta in softplus

* threshold -> \varepsilon in softplus

* parameter name

* delta -> \delta in smooth_l1_loss

* fix some docs test=document_fix

* fix docs test=document_fix

* fix docs && 增加空行 test=document_fix

* Update python/paddle/nn/functional/activation.py, test=document_fix

* Update python/paddle/nn/layer/activation.py, test=document_fix
Co-authored-by: NSigureMo <sigure.qaq@gmail.com>

* add lookup_table op_convert, add lookup_table plugin

* added transpose

* CI fix

* fix for transpose

* fix after review

* - some more MD changes

* - lint

* - compilation fixes

* - compilation fixes

* - lint

* - fix

* Fix undefined reference PD_IntArrayGetElementCount

* Delete PD_IntArrayGetSize Unused

* paddle-inference support custom-ops
Co-authored-by: NZhixin Yao <zhixiny@graphcore.ai>

* fix tolower
Co-authored-by: NZhixin Yao <zhixiny@graphcore.ai>

* Optimize performance of depthwise_conv_bwd of filter

* op-benchmark

* fix

* op benchmark

* merge bwd

* Optimize performance of depthwise_conv_bwd

* fix