* add update_loss_scaling_npu NPU kernel

* change TensorFromVec to Memset

* support mixed precision input for npu layer norm

* fix layer_norm npu kernel
Co-authored-by: Nzhiqiu <chenqiuliang@baidu.com>

* add npu kernel for concat op

* add npu kernel for concat op

* refine code

* update

* refine concat_grad

* support list of tensor as npu input

* add comment

* fix typo

* fix typo

add c_reduce_sum op

Add 3d Parallelism
Co-authored-by: NWangXi <wangxi16@baidu.com>
Co-authored-by: NJZ-LIANG <jianzhongliang10@gmail.com>
Co-authored-by: Nroot <root@yq01-sys-hic-k8s-v100-box-a225-0562.yq01.baidu.com>

* fix

* fix

* fix gather grad kernel diff

* fix gather grad kernel diff

* fix gather review bug

* fix softmax

* fix mean

* fix lookup_table_v2

* change transpose to transpose2

* fix bug

* rename npu op file

* fix reshape

* add topk op

* add cmake

* update topk npu op

* refactor func

* fix test not go npu TopKD bug

* NPUPlace(4) to NPUPlace(0)

* update comment
Co-authored-by: Noyjxer <1728722986@qq.com>

* add increment

* fix

* update test increment op inplace

* update increment op

* increment b = 2
Co-authored-by: Noyjxer <1728722986@qq.com>

* fix shape of dx

* refine code

* [npu] support npu kernel  for `expand`

* update unittest

* add TensorCopy in npu grad kernel

This reverts commit 468ac699.

* update mean op

* update mean op

* give a better test activation
Co-authored-by: Noyjxer <1728722986@qq.com>

* init

* fix bugs

* add mul

* add test mul

* add npu kernel for adam

* refine code

* disable test

* modify atol

* add reduce_sum

* fix broadcastd

* fix test

* fix

* add unsqueeze in reduce_sum

* add template

* add unittest for keep_dim

* test reduce_all
Co-authored-by: Nfrankwhzhang <frankwhzhang@126.com>