* fix reading flags from env

* fix problem caused by async run

* support partial grad

* support elementwise_add_grad npu kernel

* add unittest

* fix bug?

* add npu sub op

* fix typo

* rename test

* fix bug

* fix bug

* add fp16 kernel

* fix typo

* support sub grad op

* support elementwise_sub_grad op
Co-authored-by: Nfrankwhzhang <frankwhzhang@126.com>

[feature] support npu operator