* enable async copy and  add wait before sync operation

* remove unneccessary wait

* add FillNpuTensorWithConstant

* refine

* fix fill_constant

* change TensorFromVector to FillNpuTensorWithConstant

* fix ignored api

* delete extra unittest

* fix little error

* fix update_loss_scaling_op_npu and check_finite_and_unscale_op_npu

* change TensorCopySync to TensorCopy

* delete useless Wait and add StreamWait

* fix npu_stream error

* fix check_finite_and_unscale_op_npu TensorCopy

* only save stream wait

* fix NPUDeviceContext in all c++ unittest

* delete wait
Co-authored-by: Nzhiqiu <chenqiuliang@baidu.com>

* fix NPUDeviceContext in all c++ unittest

* refine log
Co-authored-by: Npangyoki <pangyoki@126.com>

* change aclrtSynchronizeDevice to aclrtSynchronizeStream for better performace

* refine code

* support save load for NPU

* add save load npu unittest

* support np.array transform in NPU

* fix errors

* delete dygraph in unittest

* add Wait

* fix unittest

* fix review comment

* fix unittest problem

* fix little problem

* fix compile problem on cann 20.3

* fix ut

* fix test_mul

* fix check_finite_and_scale

* fix lookup_table_v2_grad

* fix cmake

* support print op

* fix npu kernel of cast op to handle casting to same dtype

* add comments

* enable async copy and  add wait before sync operation

* remove unneccessary wait

* add FillNpuTensorWithConstant

* refine

* fix fill_constant

* make TensorFromVector/TensorToVector sync

* support npu profiler

* add python api

* fix bugs

* add wrapper for incomplete type

* update profile proto

* record npu wait

* add xpu placeholder

* support npu for memcpy op

* add ut

* fix ut

* fix typo

Co-authored-by: Nbaiyangfan <baiyangfan@baidu.com>

* support GarbageCollector for npu

* fix typo

* fix gather_grad

* disable NPUDefaultStreamGarbageCollector on NPU

* init

* add todo

* add npu kernel for truncated_gaussian_random

* add sync

* fix concat_grad

* fix typo

* fix some op bugs

* fix some bugs

* follow comments

* fix log level

* add ut

* fix

* fix

* 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 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