diff --git a/.buildkite/test-amd.yaml b/.buildkite/test-amd.yaml
index eeb685e9892..09d8a33cc3f 100644
--- a/.buildkite/test-amd.yaml
+++ b/.buildkite/test-amd.yaml
@@ -771,7 +771,7 @@ steps:
 
 #-----------------------------------------------------------  mi300 · cuda  ------------------------------------------------------------#
 
-- label: Platform Tests (CUDA) # TBD
+- label: Platform Tests # TBD
   timeout_in_minutes: 180
   mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
   agent_pool: mi300_1
@@ -831,7 +831,7 @@ steps:
   - pytest -v -s distributed/test_eplb_execute.py
   - pytest -v -s distributed/test_eplb_spec_decode.py
 
-- label: Distributed Tests (2xH100-2xMI250) # TBD
+- label: Distributed Tests (2xH100-2xMI300) # TBD
   timeout_in_minutes: 180
   mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
   agent_pool: mi300_2
@@ -843,13 +843,19 @@ steps:
   - vllm/model_executor/layers/fused_moe/
   - vllm/v1/attention/backends/
   - vllm/v1/attention/selector.py
+  - tests/v1/distributed/test_dbo.py
   - tests/distributed/test_context_parallel.py
   - examples/features/data_parallel/data_parallel_offline.py
   - vllm/_aiter_ops.py
   - vllm/platforms/rocm.py
   commands:
   - pytest -v -s tests/distributed/test_context_parallel.py
+  - VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 examples/rl/rlhf_async_new_apis.py
+  - VLLM_LOGGING_LEVEL=DEBUG python3 examples/features/data_parallel/data_parallel_offline.py --model=Qwen/Qwen1.5-MoE-A2.7B -tp=1 -dp=2 --max-model-len=2048 --all2all-backend=deepep_high_throughput
   - VLLM_LOGGING_LEVEL=DEBUG python3 examples/features/data_parallel/data_parallel_offline.py --model=Qwen/Qwen1.5-MoE-A2.7B -tp=1 -dp=2 --max-model-len=2048 --all2all-backend=allgather_reducescatter --disable-nccl-for-dp-synchronization
+  - pytest -v -s tests/v1/distributed/test_dbo.py
+  - VLLM_ALLOW_INSECURE_SERIALIZATION=1 pytest -v -s tests/distributed/test_weight_transfer.py
+  - pytest -v -s tests/distributed/test_packed_tensor.py
 
 - label: Distributed Tests (4xA100-4xMI300) # TBD
   timeout_in_minutes: 180
@@ -2195,26 +2201,6 @@ steps:
   - TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_external_lb_dp.py
   - DP_SIZE=2 pytest -v -s entrypoints/openai/test_multi_api_servers.py
 
-- label: Distributed Tests (2xH100-2xMI300) # TBD
-  timeout_in_minutes: 180
-  mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
-  agent_pool: mi300_2
-  num_gpus: 2
-  working_dir: "/vllm-workspace/"
-  source_file_dependencies:
-  - vllm/distributed/
-  - vllm/v1/distributed/
-  - vllm/model_executor/layers/fused_moe/
-  - tests/v1/distributed/test_dbo.py
-  - vllm/_aiter_ops.py
-  - vllm/platforms/rocm.py
-  commands:
-  - VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 examples/rl/rlhf_async_new_apis.py
-  - VLLM_LOGGING_LEVEL=DEBUG python3 examples/features/data_parallel/data_parallel_offline.py --model=Qwen/Qwen1.5-MoE-A2.7B -tp=1 -dp=2 --max-model-len=2048 --all2all-backend=deepep_high_throughput
-  - pytest -v -s tests/v1/distributed/test_dbo.py
-  - VLLM_ALLOW_INSECURE_SERIALIZATION=1 pytest -v -s tests/distributed/test_weight_transfer.py
-  - pytest -v -s tests/distributed/test_packed_tensor.py
-
 - label: Metrics, Tracing (2 GPUs) # TBD
   timeout_in_minutes: 20
   mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
diff --git a/.buildkite/test_areas/cuda.yaml b/.buildkite/test_areas/cuda.yaml
index b56e635bea6..956c76cf05f 100644
--- a/.buildkite/test_areas/cuda.yaml
+++ b/.buildkite/test_areas/cuda.yaml
@@ -2,8 +2,8 @@ group: CUDA
 depends_on: 
   - image-build
 steps:
-- label: Platform Tests (CUDA)
-  key: platform-tests-cuda
+- label: Platform Tests
+  key: platform-tests
   timeout_in_minutes: 15
   device: h200_18gb
   source_file_dependencies:
diff --git a/.buildkite/test_areas/distributed.yaml b/.buildkite/test_areas/distributed.yaml
index b880fadf356..5ff4b24b744 100644
--- a/.buildkite/test_areas/distributed.yaml
+++ b/.buildkite/test_areas/distributed.yaml
@@ -174,8 +174,8 @@ steps:
   # test multi-node TP with multiproc executor (simulated on single node)
   - pytest -v -s distributed/test_multiproc_executor.py::test_multiproc_executor_multi_node
 
-- label: Distributed Tests (8 GPUs)(H100)
-  key: distributed-tests-8-gpus-h100
+- label: Distributed Tests (8xH100)
+  key: distributed-tests-8xh100
   timeout_in_minutes: 10
   device: h100
   num_devices: 8
@@ -195,8 +195,8 @@ steps:
   # test with torchrun tp=2 and dp=4 with ep
   - torchrun --nproc-per-node=8 ../examples/features/torchrun/torchrun_dp_example_offline.py --tp-size=2 --pp-size=1 --dp-size=4 --enable-ep
 
-- label: Distributed Tests (4 GPUs)(A100)
-  key: distributed-tests-4-gpus-a100
+- label: Distributed Tests (4xA100)
+  key: distributed-tests-4xa100
   device: a100
   optional: true
   num_devices: 4
@@ -211,7 +211,7 @@ steps:
   - pytest -v -s -x lora/test_mixtral.py
 
 - label: Distributed Tests (2xH100-2xMI300)
-  key: distributed-tests-2-gpus-h100
+  key: distributed-tests-2xh100-2xmi300
   timeout_in_minutes: 15
   device: h100
   optional: true
@@ -237,8 +237,8 @@ steps:
       - VLLM_ALLOW_INSECURE_SERIALIZATION=1 pytest -v -s tests/distributed/test_weight_transfer.py
       - pytest -v -s tests/distributed/test_packed_tensor.py
 
-- label: Distributed Tests (2 GPUs)(B200)
-  key: distributed-tests-2-gpus-b200
+- label: Distributed Tests (2xB200)
+  key: distributed-tests-2xb200
   device: b200-k8s
   optional: true
   working_dir: "/vllm-workspace/"
diff --git a/.buildkite/test_areas/e2e_integration.yaml b/.buildkite/test_areas/e2e_integration.yaml
index 88039a33960..3f87e3958d0 100644
--- a/.buildkite/test_areas/e2e_integration.yaml
+++ b/.buildkite/test_areas/e2e_integration.yaml
@@ -2,8 +2,8 @@ group: E2E Integration
 depends_on: 
   - image-build
 steps:
-- label: DeepSeek V2-Lite Sync EPLB Accuracy
-  key: deepseek-v2-lite-sync-eplb-accuracy
+- label: DeepSeek V2-Lite Sync EPLB Accuracy (4xH100)
+  key: deepseek-v2-lite-sync-eplb-accuracy-4xh100
   timeout_in_minutes: 60
   device: h100
   optional: true
@@ -12,8 +12,8 @@ steps:
   commands:
   - bash .buildkite/scripts/scheduled_integration_test/deepseek_v2_lite_ep_eplb.sh 0.25 200 8010
 
-- label: Qwen3-30B-A3B-FP8-block Sync EPLB Accuracy
-  key: qwen3-30b-a3b-fp8-block-sync-eplb-accuracy
+- label: Qwen3-30B-A3B-FP8-block Sync EPLB Accuracy (4xH100)
+  key: qwen3-30b-a3b-fp8-block-sync-eplb-accuracy-4xh100
   timeout_in_minutes: 60
   device: h100
   optional: true
@@ -22,8 +22,8 @@ steps:
   commands:
   - bash .buildkite/scripts/scheduled_integration_test/qwen30b_a3b_fp8_block_ep_eplb.sh 0.8 200 8020
 
-- label: Qwen3-30B-A3B-FP8-block Sync EPLB Accuracy (B200)
-  key: qwen3-30b-a3b-fp8-block-sync-eplb-accuracy-b200
+- label: Qwen3-30B-A3B-FP8-block Sync EPLB Accuracy (2xB200)
+  key: qwen3-30b-a3b-fp8-block-sync-eplb-accuracy-2xb200
   timeout_in_minutes: 60
   device: b200-k8s
   optional: true
diff --git a/.buildkite/test_areas/kernels.yaml b/.buildkite/test_areas/kernels.yaml
index c5341a0f518..10c132da095 100644
--- a/.buildkite/test_areas/kernels.yaml
+++ b/.buildkite/test_areas/kernels.yaml
@@ -274,8 +274,8 @@ steps:
     - pytest -v -s kernels/helion/
 
  
-- label: Kernels FP8 MoE Test (1 H100)
-  key: kernels-fp8-moe-test-1-h100
+- label: Kernels FP8 MoE Test (1xH100)
+  key: kernels-fp8-moe-test-1xh100
   timeout_in_minutes: 90
   device: h100
   num_devices: 1
@@ -291,8 +291,8 @@ steps:
     - pytest -v -s kernels/moe/test_triton_moe_no_act_mul.py
     - pytest -v -s kernels/moe/test_triton_moe_ptpc_fp8.py
 
-- label: Kernels FP8 MoE Test (2 H100s)
-  key: kernels-fp8-moe-test-2-h100s
+- label: Kernels FP8 MoE Test (2xH100)
+  key: kernels-fp8-moe-test-2xh100
   timeout_in_minutes: 90
   device: h100
   num_devices: 2
diff --git a/.buildkite/test_areas/lm_eval.yaml b/.buildkite/test_areas/lm_eval.yaml
index a64edbd1c4f..d5c4b6957ab 100644
--- a/.buildkite/test_areas/lm_eval.yaml
+++ b/.buildkite/test_areas/lm_eval.yaml
@@ -28,7 +28,8 @@ steps:
       - vllm/_aiter_ops.py
       - vllm/platforms/rocm.py
 
-# - label: LM Eval Large Models (4 GPUs)(A100)
+# - label: LM Eval Large Models (4xA100)
+#   key: lm-eval-large-models-4xa100
 #   device: a100
 #   optional: true
 #   num_devices: 4
@@ -40,8 +41,8 @@ steps:
 #   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
 #   - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-large.txt --tp-size=4
 
-- label: LM Eval Large Models (4 GPUs)(H100)
-  key: lm-eval-large-models-4-gpus-h100
+- label: LM Eval Large Models (4xH100)
+  key: lm-eval-large-models-4xh100
   device: h100
   optional: true
   num_devices: 4
@@ -53,8 +54,8 @@ steps:
     - export VLLM_USE_DEEP_GEMM=0  # We found Triton is faster than DeepGEMM for H100
     - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-large-hopper.txt --tp-size=4
 
-- label: LM Eval Small Models (B200)
-  key: lm-eval-small-models-b200
+- label: LM Eval Small Models (2xB200)
+  key: lm-eval-small-models-2xb200
   timeout_in_minutes: 120
   device: b200-k8s
   optional: true
@@ -64,8 +65,8 @@ steps:
   commands:
   - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt
 
-- label: LM Eval Large Models (B200, EP)
-  key: lm-eval-large-models-b200-ep
+- label: LM Eval Large Models EP (2xB200)
+  key: lm-eval-large-models-ep-2xb200
   timeout_in_minutes: 120
   device: b200-k8s
   optional: true
@@ -76,8 +77,8 @@ steps:
   commands:
   - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell-ep.txt
 
-- label: LM Eval Qwen3.5 Models (B200)
-  key: lm-eval-qwen3-5-models-b200
+- label: LM Eval Qwen3.5 Models (2xB200)
+  key: lm-eval-qwen3-5-models-2xb200
   timeout_in_minutes: 120
   device: b200-k8s
   optional: true
@@ -93,8 +94,8 @@ steps:
   commands:
   - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-qwen35-blackwell.txt
 
-- label: LM Eval Large Models (H200)
-  key: lm-eval-large-models-h200
+- label: LM Eval Large Models (8xH200)
+  key: lm-eval-large-models-8xh200
   timeout_in_minutes: 60
   device: h200
   optional: true
@@ -192,8 +193,8 @@ steps:
   commands:
   - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/models-turboquant.txt
 
-- label: GPQA Eval (GPT-OSS) (H100)
-  key: gpqa-eval-gpt-oss-h100
+- label: GPQA Eval (GPT-OSS) (2xH100)
+  key: gpqa-eval-gpt-oss-2xh100
   timeout_in_minutes: 120
   device: h100
   optional: true
@@ -206,8 +207,8 @@ steps:
     - uv pip install --system 'gpt-oss[eval]==0.0.5'
     - pytest -s -v evals/gpt_oss/test_gpqa_correctness.py --config-list-file=configs/models-h100.txt
 
-- label: GPQA Eval (GPT-OSS) (B200)
-  key: gpqa-eval-gpt-oss-b200
+- label: GPQA Eval (GPT-OSS) (2xB200)
+  key: gpqa-eval-gpt-oss-2xb200
   timeout_in_minutes: 120
   device: b200-k8s
   optional: true