diff --git a/tests/distributed/test_torchrun_example.py b/tests/distributed/test_torchrun_example.py index f415409d7..354009519 100644 --- a/tests/distributed/test_torchrun_example.py +++ b/tests/distributed/test_torchrun_example.py @@ -32,6 +32,9 @@ llm = LLM( gpu_memory_utilization=random.uniform(0.7, 0.9), swap_space=random.randint(1, 4), seed=0, + # FIXME(Isotr0py): async scheduling causes deadlock + # on torchrun with PP, need to investigate further. + async_scheduling=False, ) outputs = llm.generate(prompts, sampling_params) diff --git a/tests/distributed/test_torchrun_example_moe.py b/tests/distributed/test_torchrun_example_moe.py index 1aa7f1793..25f55a968 100644 --- a/tests/distributed/test_torchrun_example_moe.py +++ b/tests/distributed/test_torchrun_example_moe.py @@ -39,6 +39,9 @@ llm = LLM( gpu_memory_utilization=random.uniform(0.7, 0.9), swap_space=random.randint(1, 4), seed=0, + # FIXME(Isotr0py): async scheduling causes deadlock + # on torchrun with PP, need to investigate further. + async_scheduling=False, ) outputs = llm.generate(prompts, sampling_params)