github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-05 02:51:59 +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

8
tests/test_zero/test_gemini/test_inference.py
View File

@@ -7,11 +7,11 @@ from torch.nn.parallel import DistributedDataParallel as DDP
from torch.testing import assert_close
import colossalai
from colossalai.accelerator import get_accelerator
from colossalai.legacy.amp import convert_to_apex_amp
from colossalai.nn.optimizer import HybridAdam
from colossalai.testing import DummyDataloader, parameterize, rerun_if_address_is_in_use, spawn
from colossalai.utils import set_seed
from colossalai.utils.device import get_current_device
from colossalai.zero import GeminiDDP, GeminiOptimizer
from colossalai.zero.gemini.chunk import search_chunk_configuration
from tests.kit.model_zoo import model_zoo, run_fwd, run_fwd_bwd
@@ -47,7 +47,9 @@ def multi_chunk_init(model: torch.nn.Module, placement_config: dict):
def single_chunk_init(model: torch.nn.Module, placement_config: dict):
model = GeminiDDP(model, chunk_init_device=get_current_device(), pin_memory=True, **placement_config)
model = GeminiDDP(
model, chunk_init_device=get_accelerator().get_current_device(), pin_memory=True, **placement_config
)
return model
@@ -63,7 +65,7 @@ def exam_inference(placement_config: dict, model_name: str, model_init_func: Cal
torch_optim = torch.optim.Adam(torch_model.parameters(), lr=1e-3)
torch_model, torch_optim = convert_to_apex_amp(torch_model, torch_optim, amp_config)
torch_model = DDP(torch_model, device_ids=[dist.get_rank()])
init_dev = get_current_device()
init_dev = get_accelerator().get_current_device()
model = model_builder().to(init_dev)
for torch_p, p in zip(torch_model.parameters(), model.parameters()):