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

Test sequential cpu offload for torchao quantization #10506

Merged
merged 3 commits into from
Jan 14, 2025
Merged

Test sequential cpu offload for torchao quantization #10506

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ad48117
test sequential cpu offload
a-r-r-o-w Jan 9, 2025
0e70d4f
Merge branch 'main' into torchao-test-sequential-cpu-offload
a-r-r-o-w Jan 9, 2025
5912aa9
Merge branch 'main' into torchao-test-sequential-cpu-offload
a-r-r-o-w Jan 11, 2025
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
12 changes: 12 additions & 0 deletions tests/quantization/torchao/test_torchao.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -476,6 +476,18 @@ def test_wrong_config(self):
with self.assertRaises(ValueError):
self.get_dummy_components(TorchAoConfig("int42"))

def test_sequential_cpu_offload(self):
r"""
A test that checks if inference runs as expected when sequential cpu offloading is enabled.
"""
quantization_config = TorchAoConfig("int8wo")
components = self.get_dummy_components(quantization_config)
pipe = FluxPipeline(**components)
pipe.enable_sequential_cpu_offload()

inputs = self.get_dummy_inputs(torch_device)
_ = pipe(**inputs)


# Slices for these tests have been obtained on our aws-g6e-xlarge-plus runners
@require_torch
Expand Down
Loading