Skip to content

make enable_sequential_cpu_offload more generic for third-party devices #4191

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

Merged
merged 2 commits into from
Jul 21, 2023
Merged

make enable_sequential_cpu_offload more generic for third-party devices #4191

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d5a904d
make enable_sequential_cpu_offload more generic for third-party devices
ji-huazhong Jul 21, 2023
c3b66d0
make style
ji-huazhong Jul 21, 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
4 changes: 3 additions & 1 deletion src/diffusers/pipelines/pipeline_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1127,7 +1127,9 @@ def enable_sequential_cpu_offload(self, gpu_id: int = 0, device: Union[torch.dev

if self.device.type != "cpu":
self.to("cpu", silence_dtype_warnings=True)
torch.cuda.empty_cache() # otherwise we don't see the memory savings (but they probably exist)
device_mod = getattr(torch, self.device.type, None)
if hasattr(device_mod, "empty_cache") and device_mod.is_available():
device_mod.empty_cache() # otherwise we don't see the memory savings (but they probably exist)

for name, model in self.components.items():
if not isinstance(model, torch.nn.Module):
Expand Down