Skip to content

Reduce WanAnimate TorchAO test input sizes to prevent OOM #13541

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

Open
jiqing-feng wants to merge 3 commits into
base: main
Choose a base branch
from
+3 −3
Open

Reduce WanAnimate TorchAO test input sizes to prevent OOM #13541

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e5f4b23
Reduce WanAnimate TorchAO test input sizes to prevent OOM
jiqing-feng Apr 22, 2026
6520b25
Merge branch 'main' into torchao-fix-wananimate-oom
jiqing-feng Apr 22, 2026
803e0ed
Merge branch 'main' into torchao-fix-wananimate-oom
jiqing-feng Apr 22, 2026
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
6 changes: 3 additions & 3 deletions tests/models/transformers/test_models_transformer_wan_animate.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -224,7 +224,7 @@ def get_dummy_inputs(self):
"""Override to provide inputs matching the tiny Wan Animate model dimensions."""
return {
"hidden_states": randn_tensor(
(1, 36, 21, 64, 64), generator=self.generator, device=torch_device, dtype=self.torch_dtype
(1, 36, 5, 16, 16), generator=self.generator, device=torch_device, dtype=self.torch_dtype
),
"encoder_hidden_states": randn_tensor(
(1, 512, 4096), generator=self.generator, device=torch_device, dtype=self.torch_dtype
Expand All @@ -233,10 +233,10 @@ def get_dummy_inputs(self):
(1, 257, 1280), generator=self.generator, device=torch_device, dtype=self.torch_dtype
),
"pose_hidden_states": randn_tensor(
(1, 16, 20, 64, 64), generator=self.generator, device=torch_device, dtype=self.torch_dtype
(1, 16, 4, 16, 16), generator=self.generator, device=torch_device, dtype=self.torch_dtype
),
"face_pixel_values": randn_tensor(
(1, 3, 77, 512, 512), generator=self.generator, device=torch_device, dtype=self.torch_dtype
(1, 3, 13, 512, 512), generator=self.generator, device=torch_device, dtype=self.torch_dtype
),
"timestep": torch.tensor([1.0]).to(torch_device, self.torch_dtype),
}
Expand Down
Loading