Merge pull request !3819 from jiangzhiwen/jzw/c_api_clue

Merge pull request !4300 from jjfeing/master

Merge pull request !4254 from yangjie159/fix-subgraph-input-kernels

Merge pull request !4327 from zhaodezan/master

Merge pull request !4216 from wangminggui/master

Merge pull request !4265 from zhangbuxue/support_two_mstypes_do_equal

Merge pull request !4324 from fuzhiye/tmp

Merge pull request !4323 from ling/fc

Merge pull request !3800 from baihuawei/multinomial-c

Merge pull request !4305 from lvchangquan/master

Merge pull request !4230 from zhaodezan/master

Merge pull request !4187 from hanhuifeng/tinybert_suit_gpu

Merge pull request !4269 from fary86/change_export_interface

2.Malloc output tensor in runtime for quant cast type op

Merge pull request !4298 from chenweifeng/maximumgrad

Merge pull request !4316 from john_tzanakakis/master_ms1_grpc

Merge pull request !4280 from wuxuejian/embedding_input_adapt

Merge pull request !4219 from huanghui/add-op-unique

Merge pull request !4294 from lyvette/tflite_parser

Merge pull request !4279 from VectorSL/master

Merge pull request !4308 from yuchaojie/fix_resnet_gpu_distribute_init

Merge pull request !4303 from liuxiao78/master

Merge pull request !4307 from YuJianfeng/internal_output

Merge pull request !4311 from anthonyaje/monitor_fix

Merge pull request !3771 from cathwong/ckw_c_api_textfile_nosampler

Merge pull request !4081 from ava/visionOps

Merge pull request !4312 from nhussain/fix_lite_builds

Merge pull request !4245 from nhussain/solarize

Merge pull request !3978 from Peilin/master

Merge pull request !4301 from liuzhongkai/leaky_relu

Merge pull request !4297 from guozhijian/code_sync_incubator_f3c32baf_to_master_fcfc75a3_0811

Merge pull request !4061 from LiHongzhang/fix_summary

Merge pull request !4292 from liubuyu/bug_fix2

Merge pull request !4306 from mengchunyang/master

Merge pull request !4276 from hangq/master

Merge pull request !4287 from yankai10/merge

add opencl prelu kernel