diff --git a/.buildkite/test_areas/cuda.yaml b/.buildkite/test_areas/cuda.yaml index 45b3dc768e..b3bfa9f097 100644 --- a/.buildkite/test_areas/cuda.yaml +++ b/.buildkite/test_areas/cuda.yaml @@ -33,6 +33,7 @@ steps: - label: ":nvidia: (H200 MIG 18GB) CUDAGraph" device: h200_18gb key: cudagraph + automatic_shard: true timeout_in_minutes: 45 source_file_dependencies: - tests/v1/cudagraph diff --git a/.buildkite/test_areas/engine.yaml b/.buildkite/test_areas/engine.yaml index 29aec98b07..26485e0a17 100644 --- a/.buildkite/test_areas/engine.yaml +++ b/.buildkite/test_areas/engine.yaml @@ -38,6 +38,7 @@ steps: - label: ":nvidia: (L4) V1 Engine" key: engine-1-gpu + automatic_shard: true device: l4 num_devices: 1 timeout_in_minutes: 45 diff --git a/.buildkite/test_areas/lm_eval.yaml b/.buildkite/test_areas/lm_eval.yaml index 49eea0b78f..0660795105 100644 --- a/.buildkite/test_areas/lm_eval.yaml +++ b/.buildkite/test_areas/lm_eval.yaml @@ -5,6 +5,7 @@ steps: - label: ":nvidia: (H200 MIG 35GB) LM Eval Small Models" device: h200_35gb key: lm-eval-small-models + automatic_shard: true timeout_in_minutes: 45 source_file_dependencies: - csrc/ diff --git a/.buildkite/test_areas/misc.yaml b/.buildkite/test_areas/misc.yaml index 52ff1d65b3..9763b2ce7d 100644 --- a/.buildkite/test_areas/misc.yaml +++ b/.buildkite/test_areas/misc.yaml @@ -4,6 +4,7 @@ depends_on: steps: - label: ":nvidia: (H200 MIG 18GB) V1 Sample" key: v1-sample + automatic_shard: true timeout_in_minutes: 45 device: h200_18gb source_file_dependencies: &v1-sample-logits-deps diff --git a/.buildkite/test_areas/quantization.yaml b/.buildkite/test_areas/quantization.yaml index 429b01f273..55cef9fbd3 100644 --- a/.buildkite/test_areas/quantization.yaml +++ b/.buildkite/test_areas/quantization.yaml @@ -80,6 +80,7 @@ steps: - label: ":nvidia: (B200) Quantized MoE" key: quantized-moe-test-b200 + automatic_shard: true timeout_in_minutes: 120 working_dir: "/vllm-workspace/" device: b200-k8s