update benchmark for int8v2, QAT1, QAT2 accuracy and performance (#21641)

test=document_fix

change according to reviews
test=develop test=document_fix

improve some descriptions and some models
test=develop test=document_fix

update models benchmark data
test=develop test=document_fix

update int8v2 and qat2 performance
test=develop test=document_fix
paddle_tiny_install
lidanqing 5 years ago committed by Tao Luo
parent 9a4dd1bc25
commit bca0bbb33b

Diff Content Not Available