* update dynabert

* update

* update

* update

* add transformer_pruner to autocompress

* add auto

* update transformer pruner

* ptq-hpo support eval function

* update

* update

* update

* update docs

* add comment

* fix patterns

Co-authored-by: NiamWHTWD <28421344+iamWHTWD@users.noreply.github.com>

* fix demo

* fix demo

* fix distiller

* fix distiller

* fix distiller

* demo imagenet

* demo imagenet

* add an interface to predict the latency of compressed model

* just for rerun

* delete temporary model files
Co-authored-by: Nceci3 <ceci3@users.noreply.github.com>

* speedup_sparse_block

* speedup_sparse_block

* speedup_sparse_block
Co-authored-by: NminghaoBD <79566150+minghaoBD@users.noreply.github.com>

* fix opt's cmd for sparse model

* add hardware

* Remove redundant functions and adjust tests' file

* Remove redundant functions and adjust tests' file

* fix

* fix ac demo

* fix install

* update
Co-authored-by: NGuanghua Yu <742925032@qq.com>

* fix a pruner's bug

* support predict pruned model

* support predict pruned model

* support sparse model

* add interface for quick pruning

* add hardware list for latencyPredictor

* add ptq data-free method

* add source-free

* add source-free

* add asp

* update

* add fleet

* add docs

* rename

* fix unittest

* add new op type and support fp16 model

* preload predictors' model and speed up prediction

* preload predictors' model

* preload predictors' model

* Modified the save path of TMP files
Co-authored-by: NminghaoBD <79566150+minghaoBD@users.noreply.github.com>