diff --git a/.buildkite/test-merge.yml b/.buildkite/test-merge.yml index 51c4223f2..b2798c458 100644 --- a/.buildkite/test-merge.yml +++ b/.buildkite/test-merge.yml @@ -108,7 +108,10 @@ steps: depends_on: upload-merge-pipeline steps: - label: "Entrypoint Test with H100" - timeout_in_minutes: 60 + # The suite relaunches an OmniServer per test class (~30 model loads, + # incl. ten ~27.5 GiB Bagel loads); 60 min passed only ~1 in 3 runs + # even on main, and vLLM 0.25 weight loading needs ~10 min more. + timeout_in_minutes: 90 commands: - pytest -s -v tests/entrypoints/ -m "advanced_model and cuda and H100" --run-level "advanced_model" agents: @@ -146,7 +149,9 @@ steps: type: DirectoryOrCreate - label: "Entrypoint Test with L4" - timeout_in_minutes: 30 + # 30 min left no headroom for a cold image pull (~11 min for new base + # layers) plus per-class engine relaunches; main passed at 26/30. + timeout_in_minutes: 45 commands: - pytest -s -v tests/entrypoints/ -m "advanced_model and cuda and L4" --run-level "advanced_model" agents: