diff --git a/.buildkite/test_areas/expert_parallelism.yaml b/.buildkite/test_areas/expert_parallelism.yaml index 76f2835978..49e6f5e9d2 100644 --- a/.buildkite/test_areas/expert_parallelism.yaml +++ b/.buildkite/test_areas/expert_parallelism.yaml @@ -58,6 +58,8 @@ steps: - label: ":nvidia: (H100) Elastic EP Scaling" key: elastic-ep-scaling-test + # Nightly only: 4-GPU H100 pods wait behind smaller jobs on per-PR runs. + optional: true timeout_in_minutes: 40 device: h100 working_dir: "/vllm-workspace/tests" diff --git a/.buildkite/test_areas/lm_eval.yaml b/.buildkite/test_areas/lm_eval.yaml index c7d9c1777e..af0b419de9 100644 --- a/.buildkite/test_areas/lm_eval.yaml +++ b/.buildkite/test_areas/lm_eval.yaml @@ -1345,6 +1345,8 @@ steps: - label: ":nvidia: (H100) LM Eval KV-Offload Large" key: kv-offload-large + # Nightly only: 4-GPU H100 pods wait behind smaller jobs on per-PR runs. + optional: true timeout_in_minutes: 40 device: h100 num_devices: 4