Thanks. How can we test it?

Seem there is no such test for different backend, should we write a Mixin for different attention backend, like AttentionBackendTesterMixin?

Or maybe a standalone reproducer that passes on this PR branch and fails on main?

Or maybe a standalone reproducer that passes on this PR branch and fails on main?

can be verified in #14114

I guess what I am more worried about is whether this PR is breaking existing functionalities and other supported pipelines.

Hi @zhtmike, thanks for the PR! It does not appear to link an issue it fixes. If this PR addresses an existing issue, please add a closing keyword (e.g. Fixes #1234) to the PR description so the issue is linked. See the contribution guide for more details. If this PR intentionally does not fix a tracked issue, a maintainer can add the no-issue-needed label to silence this reminder.

I guess what I am more worried about is whether this PR is breaking existing functionalities and other supported pipelines.

I agree with this. The attention backend lacks test coverage, so it is better to protect it with test cases.

The current fix is for the _flash_3_varlen_hub backend only. It can now correctly handle non-mask, contiguous mask, and non-contiguous mask cases. In my view, it should be safe.

I have also updated the PR content according to the GitHub Action review. Thanks.

Let's introduce a test suite for this and add that to concerned models then.

Sorry, I just realized that there is already an AttentionBackendTesterMixin in the latest main branch. We don’t need to introduce a new suite.

I have added an extra TestQwenImageTransformerAttentionBackend to guard against the error. The local test has passed. (The main branch will this test will fail)

I have also tested with TestFluxTransformerAttentionBackend, it also passed.

Thanks!