diff --git a/.buildkite/test_areas/entrypoints.yaml b/.buildkite/test_areas/entrypoints.yaml
index 68c6243d47..34a190e810 100644
--- a/.buildkite/test_areas/entrypoints.yaml
+++ b/.buildkite/test_areas/entrypoints.yaml
@@ -231,6 +231,7 @@ steps:
 - label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (Pooling)"
   device: h200_35gb
   key: entrypoints-integration-pooling
+  automatic_shard: true
   timeout_in_minutes: 75
   working_dir: "/vllm-workspace/tests"
   source_file_dependencies:
diff --git a/.buildkite/test_areas/kernels.yaml b/.buildkite/test_areas/kernels.yaml
index d3c8f65790..e0d6c4ce40 100644
--- a/.buildkite/test_areas/kernels.yaml
+++ b/.buildkite/test_areas/kernels.yaml
@@ -504,6 +504,7 @@ steps:
 - label: ":nvidia: (H200 MIG 35GB) Mamba Kernels"
   device: h200_35gb
   key: kernels-mamba-test
+  automatic_shard: true
   timeout_in_minutes: 60
   source_file_dependencies:
   - csrc/mamba/
diff --git a/.buildkite/test_areas/quantization.yaml b/.buildkite/test_areas/quantization.yaml
index b49b4b92c7..429b01f273 100644
--- a/.buildkite/test_areas/quantization.yaml
+++ b/.buildkite/test_areas/quantization.yaml
@@ -127,6 +127,7 @@ steps:
 - label: ":nvidia: (H200 MIG 35GB) Quantized Models"
   device: h200_35gb
   key: quantized-models-test
+  automatic_shard: true
   timeout_in_minutes: 65
   env:
     VLLM_USE_V2_MODEL_RUNNER: "0"
diff --git a/.buildkite/test_areas/spec_decode.yaml b/.buildkite/test_areas/spec_decode.yaml
index 6882c24b37..d031d4fdea 100644
--- a/.buildkite/test_areas/spec_decode.yaml
+++ b/.buildkite/test_areas/spec_decode.yaml
@@ -5,6 +5,7 @@ steps:
 - label: ":nvidia: (H200 MIG 35GB) V1 Spec Decode"
   device: h200_35gb
   key: v1-spec-decode
+  automatic_shard: true
   timeout_in_minutes: 40
   source_file_dependencies:
     - vllm/config/