Skip to content

Pass device to enable_model_cpu_offload in maybe_free_model_hooks #6937

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
sayakpaul merged 1 commit into from
Feb 12, 2024
Merged

Pass device to enable_model_cpu_offload in maybe_free_model_hooks #6937

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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 @@ -1423,6 +1423,7 @@ def enable_model_cpu_offload(self, gpu_id: Optional[int] = None, device: Union[t

device_type = torch_device.type
device = torch.device(f"{device_type}:{self._offload_gpu_id}")
self._offload_device = device

if self.device.type != "cpu":
self.to("cpu", silence_dtype_warnings=True)
Expand Down Expand Up @@ -1472,7 +1473,7 @@ def maybe_free_model_hooks(self):
hook.remove()

# make sure the model is in the same state as before calling it
self.enable_model_cpu_offload()
self.enable_model_cpu_offload(device=getattr(self, "_offload_device", "cuda"))
Copy link
Member

@sayakpaul sayakpaul Feb 11, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Personally I think it's a non-breaking change since we default to "cuda" for device in enable_model_cpu_offload().

Copy link
Collaborator

@yiyixuxu yiyixuxu Feb 12, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it's ok too :)


def enable_sequential_cpu_offload(self, gpu_id: Optional[int] = None, device: Union[torch.device, str] = "cuda"):
r"""
Expand Down Expand Up @@ -1508,6 +1509,7 @@ def enable_sequential_cpu_offload(self, gpu_id: Optional[int] = None, device: Un

device_type = torch_device.type
device = torch.device(f"{device_type}:{self._offload_gpu_id}")
self._offload_device = device

if self.device.type != "cpu":
self.to("cpu", silence_dtype_warnings=True)
Expand Down