From eb6e3a16c3c6c6f2227320534a4f108c90618219 Mon Sep 17 00:00:00 2001 From: Fred Heinecke Date: Fri, 21 Aug 2026 17:56:31 -0500 Subject: [PATCH] Fix PyTorch EP tests sharing a single timeout Signed-off-by: Fred Heinecke --- tests/pytorch/distributed/test_ep.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tests/pytorch/distributed/test_ep.py b/tests/pytorch/distributed/test_ep.py index 81eef9a3c1..c37bdc4b77 100644 --- a/tests/pytorch/distributed/test_ep.py +++ b/tests/pytorch/distributed/test_ep.py @@ -19,13 +19,12 @@ def test_multi_process_ep(): """Launch the EP unit-test suite across all visible GPUs. - Short timeout so a hang on any rank surfaces fast rather than burning CI time. + The launcher applies its timeout independently to every torchrun pass. """ timeout_s = int(os.environ.get("NVTE_TEST_EP_TIMEOUT_S", "180")) proc = subprocess.run( ["bash", str(LAUNCHER)], env={**os.environ, "KEEP_EP_LOGS": "1", "TEST_TIMEOUT_S": str(timeout_s)}, - timeout=timeout_s + 30, check=False, ) assert proc.returncode == 0, f"EP test suite failed (rc={proc.returncode})"