Merge pull request !7620 from zhaozhenlong/lite/op/non_max_suppression

Merge pull request !7629 from zhanghuiyao/fix_dscnn

Merge pull request !7607 from lilei/modify_normal

Merge pull request !7581 from lilei/modify_bug

Merge pull request !7643 from yangruoqi713/conv_dw

Merge pull request !7631 from xutianchun/mulit

Merge pull request !7649 from yuchaojie/quant3

Merge pull request !7633 from yuchaojie/quant2

Merge pull request !7583 from chenzhongming/zomi_master

Merge pull request !7530 from jiangzhiwen/lite/image_divide

Merge pull request !7598 from zyli2020/init_in_server

Merge pull request !7518 from anancds/tcp-server

Merge pull request !7632 from fuzhiye/tmp

Merge pull request !7627 from 王东旭/opencl_conv_remove_codegen

Merge pull request !7623 from xulei/lite_test0905

Merge pull request !7658 from EricZ/add_ir_folder

Merge pull request !7609 from h.farahat/cache_c++_api

Merge pull request !7483 from 34bunny/GPU-ucs

Merge pull request !7537 from Peilin/cbg-new-gpu-ops-repeat_elements

Merge pull request !7622 from yeyunpeng2020/primitive

Merge pull request !7513 from ghzl/kmeans-quant

Merge pull request !7192 from zhengjun10/transformer

Merge pull request !7635 from zhanghaibo/master

Merge pull request !7640 from zhanyuan/tmp

Merge pull request !7641 from jiangzhenguang/amend_deeplabv3_readme_in_master

Merge pull request !7628 from liyanliu96/liyan

Merge pull request !7626 from qujianwei/master

Merge pull request !7636 from baiyangfan/mode_export_bug

Merge pull request !7630 from liubuyu/master

2.free reduandent memory in fp16 kernels

Merge pull request !7572 from VectorSL/fix-reduce-pre