github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-14 21:51:57 +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/ring.py
View File

@@ -3,9 +3,9 @@
import torch
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, synchronize
def ring_forward(tensor_send_next: torch.Tensor, parallel_mode: ParallelMode) -> torch.Tensor:
@@ -29,7 +29,7 @@ def ring_forward(tensor_send_next: torch.Tensor, parallel_mode: ParallelMode) ->
current_rank = gpc.get_global_rank()
tensor_recv_prev = torch.empty(
buffer_shape, requires_grad=True, device=get_current_device(), dtype=tensor_send_next.dtype
buffer_shape, requires_grad=True, device=get_accelerator().get_current_device(), dtype=tensor_send_next.dtype
)
# send to next rank
@@ -52,6 +52,6 @@ def ring_forward(tensor_send_next: torch.Tensor, parallel_mode: ParallelMode) ->
req.wait()
# To protect against race condition when using batch_isend_irecv().
synchronize()
get_accelerator().synchronize()
return tensor_recv_prev