[Device]Support npu (#6159)

* support npu

* support pretrain

support pretrain

fix

* support lora

fix

fix

* support chatglm

fix

fxi

fix

[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

fix

fix

[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

fix

[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

fix

fix

fix

* Update train.py

* Update train.py

* fix

* fix

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix

* fix

* fix

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

colossalai/pipeline/schedule/interleaved_pp.py

@@ -2,7 +2,6 @@ from functools import partial
 from typing import Any, Callable, Dict, Iterable, List, Optional, Tuple, Union
 
 import torch
-import torch.cuda
 import torch.distributed
 from torch.nn import Module, ModuleList
 from torch.utils._pytree import tree_map
@@ -18,7 +17,7 @@ from ._utils import detach, get_batch_size, get_micro_batch, merge_batch, model_
 from .base import PipelineSchedule
 
 
-def _wait_p2p(wait_handles: List[torch.cuda.Event]) -> None:
+def _wait_p2p(wait_handles) -> None:
     if wait_handles is not None:
         for req in wait_handles:
             req.wait()

colossalai/pipeline/schedule/one_f_one_b.py

@@ -2,7 +2,6 @@ from functools import partial
 from typing import Any, Callable, Dict, Iterable, List, Optional, Union
 
 import torch
-import torch.cuda
 from torch.nn import Module
 from torch.utils._pytree import tree_map