[CI Failure][NIGHTLY FIRE DRILL]: Distributed Tests (2 GPUS)

[robertgshaw2-redhat]

Name of failing test

tests/v1/test_async_llm_dp.py::test_load

Basic information

• Flaky test
• Can reproduce locally
• Caused by external libraries (e.g. bug in transformers)

🧪 Describe the failing test

the test is hanging

potential fix: #22744

📝 History of failing test

https://buildkite.com/vllm/ci/builds/26788#0198a196-b39c-46cd-b8fc-e0072e5b63a7

CC List.

cc @zifeitong