Skip to content

[Misc] Fix misleading ROCm warning #19486

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 1 commit into from
Jun 11, 2025
Merged

[Misc] Fix misleading ROCm warning #19486

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
7 changes: 6 additions & 1 deletion vllm/attention/ops/triton_flash_attention.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,9 +25,14 @@
import torch

from vllm.platforms import current_platform
from vllm.platforms.rocm import on_gfx1x
from vllm.triton_utils import tl, triton

# Avoid misleading ROCm warning.
Copy link
Collaborator

Choose a reason for hiding this comment

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

nit: import on demand

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Because of this line, I didn't use the lazy import.

if current_platform.is_rocm():
from vllm.platforms.rocm import on_gfx1x
else:
on_gfx1x = lambda *args, **kwargs: False

torch_dtype: tl.constexpr = torch.float16


Expand Down