diff --git a/.buildkite/test_areas/models_language.yaml b/.buildkite/test_areas/models_language.yaml index be9f6927b3..94c16ba118 100644 --- a/.buildkite/test_areas/models_language.yaml +++ b/.buildkite/test_areas/models_language.yaml @@ -210,7 +210,10 @@ steps: - "!vllm/distributed/kv_transfer/" - tests/models/language/pooling commands: - - pytest -v -s models/language/pooling -m 'not core_model' + # Per-test timeout: a hung test fails with a stack dump instead of holding + # the job until Buildkite cancels it, which also blocks the full run's + # coverage collection. A whole shard takes 12-21 minutes. + - pytest -v -s models/language/pooling -m 'not core_model' --timeout=900 --timeout-method=thread mirror: amd: parallelism: 4