github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-01 09:07:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

[npu] change device to accelerator api (#5239)

Browse Source 
* update accelerator

* fix timer

* fix amp

* update

* fix

* update bug

* add error raise

* fix autocast

* fix set device

* remove doc accelerator

* update doc

* update doc

* update doc

* use nullcontext

* update cpu

* update null context

* change time limit for example

* udpate

* update

* update

* update

* [npu] polish accelerator code

---------

Co-authored-by: Xuanlei Zhao <xuanlei.zhao@gmail.com>
Co-authored-by: zxl <43881818+oahzxl@users.noreply.github.com>
This commit is contained in:
Hongxin Liu
2024-01-09 10:20:05 +08:00
committed by GitHub
parent dd2c28a323
commit d202cc28c0
128 changed files with 1773 additions and 868 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
colossalai/legacy/communication/utils.py
View File

@@ -3,9 +3,9 @@ from typing import List, Tuple, Union
import torch
import torch.distributed as dist
from colossalai.accelerator import get_accelerator
from colossalai.legacy.context.parallel_mode import ParallelMode
from colossalai.legacy.core import global_context as gpc
from colossalai.utils import get_current_device
TensorShape = Union[torch.Size, List[int], Tuple[int]]
@@ -35,7 +35,7 @@ def send_obj_meta(obj, need_meta=True, next_rank=None) -> bool:
if next_rank is None:
next_rank = gpc.get_next_global_rank(ParallelMode.PIPELINE)
tensor_kwargs = {"dtype": torch.long, "device": get_current_device()}
tensor_kwargs = {"dtype": torch.long, "device": get_accelerator().get_current_device()}
if isinstance(obj, torch.Tensor):
send_obj_nums = torch.tensor(1, **tensor_kwargs)
dist.send(send_obj_nums, next_rank)
@@ -74,7 +74,7 @@ def recv_obj_meta(obj_shape, prev_rank=None) -> torch.Size:
if prev_rank is None:
prev_rank = gpc.get_prev_global_rank(ParallelMode.PIPELINE)
tensor_kwargs = {"dtype": torch.long, "device": get_current_device()}
tensor_kwargs = {"dtype": torch.long, "device": get_accelerator().get_current_device()}
recv_obj_nums = torch.empty((), **tensor_kwargs)
dist.recv(recv_obj_nums, prev_rank)
if recv_obj_nums.item() == 1: