Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Bugs] Fix bugs in colo optimwrapper #1426

Merged
merged 3 commits into from
Nov 14, 2023
Merged

[Bugs] Fix bugs in colo optimwrapper #1426

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
6b169e0
fix bugs when using colossalai hybrid plugin as it can not been deepcopy
HIT-cwh Nov 10, 2023
16d381e
fix bugs in contextmanager
HIT-cwh Nov 10, 2023
c8ce4dc
fix comments
HIT-cwh Nov 14, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 10 additions & 5 deletions mmengine/_strategy/colossalai.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,20 +94,25 @@ class ColossalAIOptimWrapper(OptimWrapper):

def __init__(self,
optimizer: torch.optim.Optimizer,
booster: Booster,
booster: Optional[Booster] = None,
accumulative_counts: int = 1):
super().__init__(optimizer, accumulative_counts=accumulative_counts)
self.booster = booster

@contextmanager
def optim_context(self, model: nn.Module):
assert isinstance(self.booster, Booster), \
'Please set the booster attribute before using ' \
'`ColossalAIOptimWrapper`.'
if self.booster.plugin.support_no_sync():
sync_context = self.booster.no_sync(model, self.optimizer)
no_sync_context = self.booster.no_sync(model, self.optimizer)
else:
yield
return
if not self.should_sync():
with sync_context:
if self.should_sync():
yield
else:
with no_sync_context:
yield

def backward(self, loss: torch.Tensor, **kwargs) -> None:
Expand Down Expand Up @@ -305,7 +310,6 @@ def prepare(
# optim_wrapper is required by booster
if optim_wrapper is not None and isinstance(optim_wrapper, dict):
optim_wrapper.setdefault('type', 'ColossalAIOptimWrapper')
optim_wrapper.setdefault('booster', self.booster)
optim_wrapper_type = OPTIM_WRAPPERS.get(optim_wrapper['type'])
if optim_wrapper_type is None:
raise ValueError(f'Failed to find {optim_wrapper["type"]} in '
Expand All @@ -318,6 +322,7 @@ def prepare(
'`ColossalAIOptimWrapper` (or subclass), but got '
f'{optim_wrapper_type}')
optim_wrapper = self.build_optim_wrapper(optim_wrapper, model)
optim_wrapper.booster = self.booster # type: ignore

if optim_wrapper is not None:
self.model, self.optim_wrapper = self._wrap(
Expand Down
Loading