Skip to content

[https://nvbugs/6786555][fix] [https://nvbugs/6786567] Gate SM103 graph test on SM count #19280

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
HuiGao-NV merged 1 commit into from
Sep 17, 2026
+3 −1
Merged

[https://nvbugs/6786555][fix] [https://nvbugs/6786567] Gate SM103 graph test on SM count #19280

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
4 changes: 3 additions & 1 deletion tests/unittest/_torch/thop/parallel/test_gvr_selfsampling_topk.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -765,9 +765,11 @@ def test_selfsampling_route_sm103_large_batch_k2048_register_rung() -> None:

@pytest.mark.skipif(getSMVersion() != 103, reason="requires an SM103 GPU")
def test_selfsampling_sm103_b512_k2048_cuda_graph() -> None:
"""Exercise the B300-only register plan through warmup and graph replay."""
"""Exercise the 148-SM SM103 register plan through warmup and graph replay."""
rows, n, npad, top_k = 512, 4111, 4160, 2048
properties = torch.cuda.get_device_properties(torch.cuda.current_device())
if properties.multi_processor_count != 148:
pytest.skip("requires an SM103 GPU with 148 SMs")
plan = ss_host.route(
rows,
n,
Expand Down
Loading