github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-06 19:40:28 +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/zero/gemini/utils.py
View File

@@ -6,7 +6,7 @@ import torch
import torch.distributed as dist
import torch.nn as nn
from colossalai.utils import get_current_device
from colossalai.accelerator import get_accelerator
from .chunk import Chunk
@@ -18,11 +18,11 @@ def get_temp_total_chunk_on_cuda(chunk: Chunk, dtype: torch.dtype):
if chunk.cuda_shard is not None:
shard_temp = chunk.cuda_shard
else:
shard_temp = chunk.cpu_shard.to(get_current_device())
shard_temp = chunk.cpu_shard.to(get_accelerator().get_current_device())
shard_temp = shard_temp.to(dtype)
total_temp = torch.zeros(chunk.chunk_size, dtype=dtype, device=get_current_device())
total_temp = torch.zeros(chunk.chunk_size, dtype=dtype, device=get_accelerator().get_current_device())
gather_list = list(torch.chunk(input=total_temp, chunks=chunk.pg_size, dim=0))
dist.all_gather(tensor_list=gather_list, tensor=shard_temp, group=chunk.torch_pg)