Skip to content

Add L2 score mod distributed attention shape #3147

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
vcherepanov-nv wants to merge 1 commit into
base: main
Choose a base branch
from
+1 −0
Open

Add L2 score mod distributed attention shape #3147

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
1 change: 1 addition & 0 deletions tests/jax/test_distributed_fused_attn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -283,6 +283,7 @@ def test_cross_attn(
DISTRIBUTED_SCORE_MOD_DATA_SHAPES = {
"L0": [],
"L1": [(4, 16, 4, 64)],
"L2": [],

@greptile-apps greptile-apps Bot Jun 25, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

P1 L2 level resolves to zero test cases

"L2": [] is passed to pytest_parametrize_wrapper, which calls get_parameters_for_test_level and returns the empty list. That list is forwarded directly to pytest.mark.parametrize("data_shape", []). With an empty parametrize set, pytest either skips the test entirely or raises a collection error depending on the --empty-parameter-set-mark config, so when NVTE_JAX_UNITTEST_LEVEL=L2 is used in CI no TestDistributedScoreModSelfAttn cases will execute. The PR description says this change "fixes L2 tests", but the fix needs at least one concrete shape tuple — the same pattern used by DISTRIBUTED_SELF_ATTN_DATA_SHAPES where L2 carries [(32, 512, 12, 64)].

}


Expand Down
Loading