Skip to content

[XPU] Fix fp8 UT patch func #42584

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 3 commits into from
Dec 3, 2025
+3 −0
Merged

[XPU] Fix fp8 UT patch func #42584

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
fb088c7
[XPU] Fix fp8 UT patch
YangKai0616 Dec 3, 2025
6cec809
make style
YangKai0616 Dec 3, 2025
f410734
Merge branch 'main' into Fix-fp8-UT-XPU
MekkCyber Dec 3, 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
3 changes: 3 additions & 0 deletions tests/quantization/finegrained_fp8/test_fp8.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,9 @@ def _patch_no_accelerator():
stack.enter_context(patch("torch.cuda.is_available", return_value=False))
if hasattr(torch, "xpu"):
stack.enter_context(patch("torch.xpu.is_available", return_value=False))
stack.enter_context(
patch("transformers.quantizers.quantizer_finegrained_fp8.is_torch_xpu_available", return_value=False)
)
Comment on lines +49 to +51
Copy link
Contributor

@MekkCyber MekkCyber Dec 3, 2025

Choose a reason for hiding this comment

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

weird that we need to add it, but I guess it's fine

Copy link
Contributor Author

@YangKai0616 YangKai0616 Dec 3, 2025

Choose a reason for hiding this comment

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

It's because is_torch_xpu_available is used here. During the Setup phase, we called this func once via cls.quantized_model, and since it is decorated with @lru_cache, even if we enter _patch_no_accelerator, the value of is_torch_xpu_available read here is still True.

yield


Expand Down