[ROCm][CI] Expand single-GPU coverage on MI355 DPX (#57599)

Signed-off-by: Sheral Kumar <shekumar@amd.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Andreas Karatzas <andreas.karatzas@protonmail.com>
Co-authored-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Andreas Karatzas <andreas.karatzas@protonmail.com>

.buildkite/test_areas/basic_correctness.yaml

@@ -19,9 +19,9 @@ steps:
   - pytest -v -s basic_correctness/test_cpu_offload.py
   mirror:
     amd:
-      label: ":amd: (MI300) Basic Correctness"
+      label: ":amd: (MI355 DPX) Basic Correctness"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 60
       depends_on:
       - image-build-amd

.buildkite/test_areas/benchmarks.yaml

@@ -15,9 +15,9 @@ steps:
   - pytest -v -s benchmarks/
   mirror:
     amd:
-      label: ":amd: (MI300) Benchmarks CLI"
+      label: ":amd: (MI355 DPX) Benchmarks CLI"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 40
       depends_on:
       - image-build-amd

.buildkite/test_areas/compile.yaml

@@ -113,9 +113,9 @@ steps:
     - pytest -v -s tests/compile/fusions_e2e/test_tp1_quant.py -k "inductor_partition and not +rms_norm and +quant_fp8 and (qwen3 or deepseek)"
   mirror:
     amd:
-      label: ":amd: (MI355) Fusion E2E Quick"
+      label: ":amd: (MI355 DPX) Fusion E2E Quick"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       working_dir: "/vllm-workspace/"
       timeout_in_minutes: 30
       depends_on:
@@ -154,9 +154,9 @@ steps:
     - pytest -v -s tests/compile/fusions_e2e/test_tp1_quant.py -k "llama-3"
   mirror:
     amd:
-      label: ":amd: (MI355) Fusion E2E Config Sweep"
+      label: ":amd: (MI355 DPX) Fusion E2E Config Sweep"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       working_dir: "/vllm-workspace/"
       timeout_in_minutes: 40
       depends_on:

.buildkite/test_areas/cuda.yaml

@@ -19,9 +19,9 @@ steps:
     - pytest -v -s cuda/test_cuda_compatibility_path.py
   mirror:
     amd:
-      label: ":amd: (MI355) CUDA Platform"
+      label: ":amd: (MI355 DPX) CUDA Platform"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       working_dir: "/vllm-workspace/tests"
       timeout_in_minutes: 25
       depends_on:

.buildkite/test_areas/disaggregated.yaml

@@ -153,7 +153,7 @@ steps:
       label: ":amd: (MI300) Hybrid SSM NixlConnector PD accuracy"
       dind: false
       device: mi300_4
-      timeout_in_minutes: 60
+      timeout_in_minutes: 80
       depends_on:
         - image-build-amd
       source_file_dependencies:

.buildkite/test_areas/distributed.yaml

@@ -35,9 +35,9 @@ steps:
   - pytest -v -s distributed/test_sharded_rdt_trainer.py
   mirror:
     amd:
-      label: ":amd: (MI355) Sharded RDT Weight Transfer"
+      label: ":amd: (MI355 DPX) Sharded RDT Weight Transfer"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       num_devices: 1
       timeout_in_minutes: 45
       working_dir: /vllm-workspace/tests
@@ -224,7 +224,7 @@ steps:
       label: ":amd: (MI355) Distributed Torchrun + Examples"
       dind: false
       device: mi355_4
-      timeout_in_minutes: 45
+      timeout_in_minutes: 55
       depends_on:
       - image-build-amd
       source_file_dependencies:

.buildkite/test_areas/e2e_integration.yaml

@@ -132,9 +132,9 @@ steps:
   - bash .buildkite/scripts/scheduled_integration_test/deepseek_v2_lite_prefetch_offload.sh 0.25 200 8030
   mirror:
     amd:
-      label: ":amd: (MI355) DeepSeek V2-Lite Prefetch Offload Accuracy"
+      label: ":amd: (MI355 DPX) DeepSeek V2-Lite Prefetch Offload Accuracy"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       working_dir: "/vllm-workspace"
       timeout_in_minutes: 30
       depends_on:

.buildkite/test_areas/engine.yaml

@@ -29,9 +29,9 @@ steps:
   - pytest -v -s engine test_sequence.py test_config.py test_logger.py test_vllm_port.py jit_monitor/test_hooks.py jit_monitor/test_hooks_gpu.py
   mirror:
     amd:
-      label: ":amd: (MI300) Engine Core"
+      label: ":amd: (MI355 DPX) Engine Core"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 40
       depends_on:
       - image-build-amd
@@ -117,9 +117,9 @@ steps:
     - pytest -v -s v1/e2e/general/test_mamba_prefix_cache.py::test_mamba_prefix_cache_mrv2 v1/e2e/general/test_mamba_prefix_cache.py::test_mamba_prefix_cache_mrv2_async
   mirror:
     amd:
-      label: ":amd: (MI355) E2E Core Large Memory"
+      label: ":amd: (MI355 DPX) E2E Core Large Memory"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       num_devices: 1
       timeout_in_minutes: 65
       working_dir: /vllm-workspace/tests

.buildkite/test_areas/entrypoints.yaml

@@ -39,9 +39,9 @@ steps:
   - pytest -v -s entrypoints/launchers
   mirror:
     amd:
-      label: ":amd: (MI355) Entrypoints Unit"
+      label: ":amd: (MI355 DPX) Entrypoints Unit"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 50
       depends_on:
       - image-build-amd
@@ -64,9 +64,9 @@ steps:
   - pytest -v -s entrypoints/llm/offline_mode # Needs to avoid interference with other tests
   mirror:
     amd:
-      label: ":amd: (MI300) Entrypoints Integration (LLM)"
+      label: ":amd: (MI355 DPX) Entrypoints Integration (LLM)"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 90
       depends_on:
       - image-build-amd
@@ -89,9 +89,9 @@ steps:
   - pytest -v -s entrypoints/scale_out --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB
   mirror:
     amd:
-      label: ":amd: (MI300) Entrypoints Integration (API Server) %N"
+      label: ":amd: (MI355 DPX) Entrypoints Integration (API Server) %N"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 65
       depends_on:
       - image-build-amd
@@ -111,9 +111,9 @@ steps:
   - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/correctness
   mirror:
     amd:
-      label: ":amd: (MI300) Entrypoints Integration (OpenAI API completion)"
+      label: ":amd: (MI355 DPX) Entrypoints Integration (OpenAI API completion)"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 65
       depends_on:
       - image-build-amd
@@ -132,9 +132,9 @@ steps:
   - pytest -v -s entrypoints/openai/chat_completion
   mirror:
     amd:
-      label: ":amd: (MI300) Entrypoints Integration (OpenAI API chat_completion)"
+      label: ":amd: (MI355 DPX) Entrypoints Integration (OpenAI API chat_completion)"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 70
       depends_on:
       - image-build-amd
@@ -160,9 +160,9 @@ steps:
   - pytest -v -s entrypoints/cohere
   mirror:
     amd:
-      label: ":amd: (MI300) Entrypoints Integration (API Server Generate)"
+      label: ":amd: (MI355 DPX) Entrypoints Integration (API Server Generate)"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 65
       depends_on:
       - image-build-amd
@@ -180,9 +180,9 @@ steps:
   - pytest -v -s entrypoints/openai/responses
   mirror:
     amd:
-      label: ":amd: (MI355) Entrypoints Integration (Responses API)"
+      label: ":amd: (MI355 DPX) Entrypoints Integration (Responses API)"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 50
       depends_on:
       - image-build-amd
@@ -201,9 +201,9 @@ steps:
   - pytest -v -s entrypoints/speech_to_text
   mirror:
     amd:
-      label: ":amd: (MI355) Entrypoints Integration (Speech to Text)"
+      label: ":amd: (MI355 DPX) Entrypoints Integration (Speech to Text)"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 60
       working_dir: "/vllm-workspace/tests"
       depends_on:
@@ -223,9 +223,9 @@ steps:
   - pytest -v -s entrypoints/multimodal
   mirror:
     amd:
-      label: ":amd: (MI355) Entrypoints Integration (Multimodal)"
+      label: ":amd: (MI355 DPX) Entrypoints Integration (Multimodal)"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 55
       depends_on:
       - image-build-amd
@@ -244,9 +244,9 @@ steps:
   - pytest -v -s entrypoints/pooling
   mirror:
     amd:
-      label: ":amd: (MI355) Entrypoints Integration (Pooling)"
+      label: ":amd: (MI355 DPX) Entrypoints Integration (Pooling)"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 65
       working_dir: "/vllm-workspace/tests"
       depends_on:
@@ -263,9 +263,9 @@ steps:
   - pytest -s entrypoints/openai/correctness/
   mirror:
     amd:
-      label: ":amd: (MI300) OpenAI API Correctness"
+      label: ":amd: (MI355 DPX) OpenAI API Correctness"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 30
       depends_on:
       - image-build-amd

.buildkite/test_areas/expert_parallelism.yaml

@@ -16,9 +16,9 @@ steps:
   - pytest -v -s distributed/test_eplb_utils.py
   mirror:
     amd:
-      label: ":amd: (MI300) EPLB Algorithm"
+      label: ":amd: (MI355 DPX) EPLB Algorithm"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 30
       depends_on:
       - image-build-amd

.buildkite/test_areas/kernels.yaml

@@ -15,9 +15,9 @@ steps:
     - pytest -v -s tests/kernels/ir
   mirror:
     amd:
-      label: ":amd: (MI355) vLLM IR"
+      label: ":amd: (MI355 DPX) vLLM IR"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 50
       working_dir: "/vllm-workspace/"
       depends_on:
@@ -44,9 +44,9 @@ steps:
   parallelism: 3
   mirror:
     amd:
-      label: ":amd: (MI355) Core Operation Kernels Shard %N"
+      label: ":amd: (MI300) Core Operation Kernels Shard %N"
       dind: false
-      device: mi355_1
+      device: mi300_1
       timeout_in_minutes: 40
       working_dir: "/vllm-workspace/tests"
       depends_on:
@@ -113,9 +113,9 @@ steps:
     - pytest -v -s kernels/test_top_k_per_row.py
   mirror:
     amd:
-      label: ":amd: (MI355) DeepSeek V4 Fused Kernels"
+      label: ":amd: (MI355 DPX) DeepSeek V4 Fused Kernels"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       num_devices: 1
       timeout_in_minutes: 60
       working_dir: /vllm-workspace/tests
@@ -230,9 +230,9 @@ steps:
     - pytest -v -s kernels/attention/test_triton_unified_attention_diffkv.py
   mirror:
     amd:
-      label: ":amd: (MI355) Attention DiffKV Kernels"
+      label: ":amd: (MI355 DPX) Attention DiffKV Kernels"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       num_devices: 1
       timeout_in_minutes: 35
       working_dir: /vllm-workspace/tests
@@ -270,9 +270,9 @@ steps:
     - pytest -v -s kernels/attention/test_mla_cross_layer_kernel_equivalence.py
   mirror:
     amd:
-      label: ":amd: (MI355) MLA Kernels"
+      label: ":amd: (MI355 DPX) MLA Kernels"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       num_devices: 1
       timeout_in_minutes: 40
       working_dir: /vllm-workspace/
@@ -768,10 +768,66 @@ steps:
       - amd-smi
       - VLLM_ROCM_USE_AITER=1 VLLM_ROCM_USE_AITER_MOE=1 VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS=0 pytest -v -s kernels/moe/test_mori_moe.py
 
-- label: ":amd: (MI355) FP8 MoE Kernels"
+- label: ":amd: (MI355 DPX) Native Quantization Kernels"
+  key: amd-native-quantization-kernels-mi355
+  dind: false
+  device: mi355_dpx
+  num_devices: 1
+  timeout_in_minutes: 40
+  working_dir: /vllm-workspace/tests
+  depends_on:
+  - image-build-amd
+  source_file_dependencies:
+  - csrc/rocm/
+  - vllm/model_executor/layers/quantization/
+  - vllm/model_executor/kernels/linear/
+  - vllm/_aiter_ops.py
+  - vllm/_custom_ops.py
+  - vllm/platforms/rocm.py
+  - vllm/envs.py
+  - tests/kernels/quantization/test_rocm_mxfp4.py
+  - tests/kernels/quantization/test_rocm_mxfp8_linear.py
+  - tests/kernels/quantization/test_rocm_skinny_gemms.py
+  - tests/quantization/reference_mxfp4.py
+  - tests/kernels/quant_utils.py
+  - tests/kernels/utils.py
+  commands:
+  - pytest -v -s kernels/quantization/test_rocm_mxfp4.py
+  - pytest -v -s kernels/quantization/test_rocm_mxfp8_linear.py
+  - pytest -v -s kernels/quantization/test_rocm_skinny_gemms.py -k wvsplitkrc
+
+- label: ":amd: (MI355 DPX) FP4 and INT4 MoE Kernels"
+  key: amd-fp4-moe-kernels-mi355
+  dind: false
+  device: mi355_dpx
+  num_devices: 1
+  timeout_in_minutes: 40
+  working_dir: /vllm-workspace/tests
+  depends_on:
+  - image-build-amd
+  source_file_dependencies:
+  - csrc/moe/
+  - csrc/rocm/
+  - vllm/model_executor/layers/fused_moe/
+  - vllm/model_executor/layers/quantization/
+  - vllm/_aiter_ops.py
+  - vllm/platforms/rocm.py
+  - vllm/envs.py
+  - vllm/config/
+  - tests/kernels/moe/test_rocm_aiter_moe.py
+  - tests/kernels/moe/test_ocp_mx_moe.py
+  - tests/kernels/moe/test_flydsl_moe.py
+  - tests/kernels/moe/utils.py
+  - tests/kernels/utils.py
+  commands:
+  - pytest -v -s kernels/moe/test_rocm_aiter_moe.py -k 'mi350_mxfp4 or quant_scheme_support_matches_gfx950'
+  - pytest -v -s kernels/moe/test_ocp_mx_moe.py::test_rocm_mxfp4_moe_oracle -k AITER_MXFP4
+  - pytest -v -s kernels/moe/test_flydsl_moe.py
+
+- label: ":amd: (MI355 DPX) FP8 MoE Kernels"
   key: amd-fp8-moe-kernels-mi355
   dind: false
-  device: mi355_1
+  device: mi355_dpx
   num_devices: 1
   timeout_in_minutes: 40
   working_dir: /vllm-workspace/tests
@@ -798,10 +854,10 @@ 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: ":amd: (MI355) Kernels"
+- label: ":amd: (MI355 DPX) Kernels"
   key: amd-kernels-mi355
   dind: false
-  device: mi355_1
+  device: mi355_dpx
   num_devices: 1
   timeout_in_minutes: 25
   working_dir: /vllm-workspace/

.buildkite/test_areas/lm_eval.yaml

@@ -68,9 +68,9 @@ steps:
   - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-watermark.txt
   mirror:
     amd:
-      label: ":amd: (MI355) LM Eval Watermarking"
+      label: ":amd: (MI355 DPX) LM Eval Watermarking"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       num_devices: 1
       timeout_in_minutes: 45
       working_dir: /vllm-workspace/tests
@@ -146,6 +146,28 @@ steps:
   - vllm/model_executor/layers/quantization
   commands:
   - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt
+  mirror:
+    amd:
+      label: ":amd: (MI355 DPX) LM Eval Small Models"
+      dind: false
+      device: mi355_dpx
+      timeout_in_minutes: 45
+      working_dir: /vllm-workspace/tests
+      depends_on:
+      - image-build-amd
+      source_file_dependencies:
+      - csrc/
+      - tests/evals/gsm8k/
+      - vllm/model_executor/layers/quantization
+      - vllm/model_executor/kernels/linear/
+      - vllm/model_executor/models/
+      - vllm/model_executor/model_loader/
+      - vllm/v1/attention/backends/
+      - vllm/v1/attention/selector.py
+      - vllm/_aiter_ops.py
+      - vllm/platforms/rocm.py
+      commands:
+      - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-gfx950-small.txt
 
 - label: ":nvidia: (B200) LM Eval Small Models Distributed"
   key: lm-eval-small-models-distributed-2xb200
@@ -972,9 +994,9 @@ steps:
     - pytest -s -v evals/mrcr/test_mrcr_correctness.py --config-list-file=evals/mrcr/configs/models-small.txt
   mirror:
     amd:
-      label: ":amd: (MI355) MRCR Eval Small Models"
+      label: ":amd: (MI355 DPX) MRCR Eval Small Models"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 40
       depends_on:
       - image-build-amd

.buildkite/test_areas/lora.yaml

@@ -14,9 +14,9 @@ steps:
   parallelism: 4
   mirror:
     amd:
-      label: ":amd: (MI300) LoRA Shard %N"
+      label: ":amd: (MI355 DPX) LoRA Shard %N"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       working_dir: "/vllm-workspace/tests"
       timeout_in_minutes: 85
       source_file_dependencies:

.buildkite/test_areas/misc.yaml

@@ -29,9 +29,9 @@ steps:
     - pytest -v -s v1/sample
   mirror:
     amd:
-      label: ":amd: (MI300) V1 Sample"
+      label: ":amd: (MI355 DPX) V1 Sample"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 70
       depends_on:
       - image-build-amd
@@ -51,9 +51,9 @@ steps:
     - pytest -v -s v1/test_outputs.py
   mirror:
     amd:
-      label: ":amd: (MI300) V1 Logits + Oracle"
+      label: ":amd: (MI355 DPX) V1 Logits + Oracle"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 70
       depends_on:
       - image-build-amd
@@ -96,9 +96,9 @@ steps:
     - pytest -v -s -m 'not cpu_test' v1/core
   mirror:
     amd:
-      label: ":amd: (MI300) V1 Core"
+      label: ":amd: (MI355 DPX) V1 Core"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 60
       depends_on:
       - image-build-amd
@@ -116,9 +116,9 @@ steps:
     - pytest -v -s v1/streaming_input
   mirror:
     amd:
-      label: ":amd: (MI300) V1 Executor + Worker"
+      label: ":amd: (MI355 DPX) V1 Executor + Worker"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 60
       depends_on:
       - image-build-amd
@@ -135,9 +135,9 @@ steps:
     - pytest -v -s v1/simple_kv_offload
   mirror:
     amd:
-      label: ":amd: (MI300) V1 KV Offload"
+      label: ":amd: (MI355 DPX) V1 KV Offload"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 60
       depends_on:
       - image-build-amd
@@ -155,9 +155,9 @@ steps:
     - pytest -v -s -m 'not cpu_test' v1/ec_connector/unit --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB
   mirror:
     amd:
-      label: ":amd: (MI300) V1 KV Connectors Shard %N"
+      label: ":amd: (MI355 DPX) V1 KV Connectors Shard %N"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 60
       depends_on:
       - image-build-amd
@@ -182,9 +182,9 @@ steps:
     - pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine
   mirror:
     amd:
-      label: ":amd: (MI300) V1 Metrics + LM Eval"
+      label: ":amd: (MI355 DPX) V1 Metrics + LM Eval"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 65
       depends_on:
       - image-build-amd
@@ -239,9 +239,9 @@ steps:
     - pytest -v -s tests/v1/kv_connector/extract_hidden_states_integration
   mirror:
     amd:
-      label: ":amd: (MI355) Extract Hidden States Integration Single GPU"
+      label: ":amd: (MI355 DPX) Extract Hidden States Integration Single GPU"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       num_devices: 1
       timeout_in_minutes: 45
       working_dir: /vllm-workspace
@@ -328,9 +328,9 @@ steps:
   working_dir: "/vllm-workspace/tests" # optional
   mirror:
     amd:
-      label: ":amd: (MI355) Regression"
+      label: ":amd: (MI355 DPX) Regression"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 25
       depends_on:
       - image-build-amd
@@ -370,9 +370,9 @@ steps:
     - python3 features/speculative_decoding/spec_decode_offline.py --test --method eagle3 --num_spec_tokens 3 --dataset-name hf --dataset-path philschmid/mt-bench --num-prompts 80 --temp 0 --top-p 1.0 --top-k -1 --tp 1 --enable-chunked-prefill --max-model-len 1536
   mirror:
     amd:
-      label: ":amd: (MI300) Examples"
+      label: ":amd: (MI355 DPX) Examples"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 75
       source_file_dependencies:
       - vllm/entrypoints
@@ -472,9 +472,9 @@ steps:
   - pytest -v -s utils_
   mirror:
     amd:
-      label: ":amd: (MI355) Async Engine, Inputs, Utils, Worker"
+      label: ":amd: (MI355 DPX) Async Engine, Inputs, Utils, Worker"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 50
       depends_on:
       - image-build-amd
@@ -667,9 +667,9 @@ steps:
     - pytest -v -s v1/spec_decode/test_acceptance_length.py -m slow_test
   mirror:
     amd:
-      label: ":amd: (MI355) Acceptance Length (Large Models)"
+      label: ":amd: (MI355 DPX) Acceptance Length (Large Models)"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 45
       depends_on:
       - image-build-amd

.buildkite/test_areas/models_basic.yaml

@@ -16,9 +16,9 @@ steps:
     - pytest -v -s models/test_initialization.py::test_can_initialize_small_subset
   mirror:
     amd:
-      label: ":amd: (MI355) Basic Models (Initialization)"
+      label: ":amd: (MI355 DPX) Basic Models (Initialization)"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 30
       depends_on:
       - image-build-amd
@@ -39,9 +39,9 @@ steps:
   parallelism: 14
   mirror:
     amd:
-      label: ":amd: (MI355) Basic Models (Extra Initialization) Shard %N"
+      label: ":amd: (MI355 DPX) Basic Models (Extra Initialization) Shard %N"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 60
       parallelism: 10
       working_dir: "/vllm-workspace/tests"
@@ -70,9 +70,9 @@ steps:
     - pytest -v -s models/test_terratorch.py models/transformers/test_backend.py models/test_registry.py models/test_deepseek_v4_vl_rocm.py
   mirror:
     amd:
-      label: ":amd: (MI300) Basic Models (Other)"
+      label: ":amd: (MI355 DPX) Basic Models (Other)"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 65
       depends_on:
       - image-build-amd
@@ -138,9 +138,9 @@ steps:
     - pytest -v -s models/glm5next
   mirror:
     amd:
-      label: ":amd: (MI355) GLM5Next"
+      label: ":amd: (MI355 DPX) GLM5Next"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 35
       working_dir: "/vllm-workspace/tests"
       depends_on:
@@ -162,9 +162,9 @@ steps:
     - pytest -v -s models/qwen4_exp/test_hc_ops.py models/qwen4_exp/test_qsa_pre_indexer.py models/qwen4_exp/test_qsa_reference.py
   mirror:
     amd:
-      label: ":amd: (MI300) Qwen4 Exp"
+      label: ":amd: (MI355 DPX) Qwen4 Exp"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       depends_on:
       - image-build-amd
       commands:

.buildkite/test_areas/models_language.yaml

@@ -16,9 +16,9 @@ steps:
     - pytest -v -s models/language -m 'core_model and (not slow_test)'
   mirror:
     amd:
-      label: ":amd: (MI300) Language Models (Standard)"
+      label: ":amd: (MI355 DPX) Language Models (Standard)"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 60
       depends_on:
       - image-build-amd
@@ -40,9 +40,9 @@ steps:
   parallelism: 2
   mirror:
     amd:
-      label: ":amd: (MI300) Language Models (Extra Standard) Shard %N"
+      label: ":amd: (MI355 DPX) Language Models (Extra Standard) Shard %N"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 40
       depends_on:
       - image-build-amd
@@ -82,9 +82,9 @@ steps:
   parallelism: 2
   mirror:
     amd:
-      label: ":amd: (MI355) Language Models (Hybrid) Shard %N"
+      label: ":amd: (MI355 DPX) Language Models (Hybrid) Shard %N"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 65
       depends_on:
       - image-build-amd
@@ -113,9 +113,9 @@ steps:
     - pytest -v -s models/language/generation -m hybrid_model -k 'granite-4.0-tiny-preview'
   mirror:
     amd:
-      label: ":amd: (MI355) Granite Language Model Compatibility"
+      label: ":amd: (MI355 DPX) Granite Language Model Compatibility"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       num_devices: 1
       timeout_in_minutes: 80
       working_dir: /vllm-workspace/tests
@@ -151,9 +151,9 @@ steps:
     - pytest -v -s models/language/generation -m '(not core_model) and (not hybrid_model)'
   mirror:
     amd:
-      label: ":amd: (MI355) Language Models (Extended Generation)"
+      label: ":amd: (MI355 DPX) Language Models (Extended Generation)"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 95
       depends_on:
       - image-build-amd

.buildkite/test_areas/models_multimodal.yaml

@@ -15,9 +15,9 @@ steps:
     - pytest -v -s models/multimodal/generation/test_ultravox.py -m core_model
   mirror:
     amd:
-      label: ":amd: (MI300) Multimodal Models (Standard) 1: qwen2"
+      label: ":amd: (MI355 DPX) Multimodal Models (Standard) 1: qwen2"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 65
       depends_on:
       - image-build-amd
@@ -36,9 +36,9 @@ steps:
     - pytest -v -s models/multimodal/generation/test_qwen2_5_vl.py -m core_model
   mirror:
     amd:
-      label: ":amd: (MI300) Multimodal Models (Standard) 2: qwen3 + gemma"
+      label: ":amd: (MI355 DPX) Multimodal Models (Standard) 2: qwen3 + gemma"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 55
       depends_on:
       - image-build-amd
@@ -78,9 +78,9 @@ steps:
     - cd .. && VLLM_WORKER_MULTIPROC_METHOD=spawn pytest -v -s tests/models/multimodal/generation/test_whisper.py -m core_model  # Otherwise, mp_method="spawn" doesn't work
   mirror:
     amd:
-      label: ":amd: (MI355) Multimodal Models (Standard) 4: other + whisper"
+      label: ":amd: (MI355 DPX) Multimodal Models (Standard) 4: other + whisper"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 70
       depends_on:
       - image-build-amd
@@ -125,9 +125,9 @@ steps:
     - pytest -v -s models/multimodal/processing/test_tensor_schema.py --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB
   mirror:
     amd:
-      label: ":amd: (MI355) Multimodal Processor Shard %N"
+      label: ":amd: (MI355 DPX) Multimodal Processor Shard %N"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       parallelism: 4
       timeout_in_minutes: 115
       depends_on:
@@ -146,9 +146,9 @@ steps:
   - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-mm-small.txt --tp-size=1
   mirror:
     amd:
-      label: ":amd: (MI300) Multimodal Accuracy Eval (Small Models)"
+      label: ":amd: (MI355 DPX) Multimodal Accuracy Eval (Small Models)"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 35
       depends_on:
       - image-build-amd
@@ -212,9 +212,9 @@ steps:
     - pytest -v -s models/multimodal/generation/test_common.py -m 'split(group=0) and not core_model' --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB
   mirror:
     amd:
-      label: ":amd: (MI355) Multimodal Models (Extended Generation 2) Shard %N"
+      label: ":amd: (MI355 DPX) Multimodal Models (Extended Generation 2) Shard %N"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 100
       depends_on:
       - image-build-amd
@@ -231,9 +231,9 @@ steps:
     - pytest -v -s models/multimodal/generation/test_common.py -m 'split(group=1) and not core_model'
   mirror:
     amd:
-      label: ":amd: (MI355) Multimodal Models (Extended Generation 3)"
+      label: ":amd: (MI355 DPX) Multimodal Models (Extended Generation 3)"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 90
       depends_on:
       - image-build-amd

.buildkite/test_areas/plugins.yaml

@@ -78,9 +78,9 @@ steps:
     - pytest -v -s plugins_tests/gguf
   mirror:
     amd:
-      label: ":amd: (MI355) GGUF Plugin"
+      label: ":amd: (MI355 DPX) GGUF Plugin"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 45
       working_dir: "/vllm-workspace/tests"
       depends_on:

.buildkite/test_areas/pytorch.yaml

@@ -89,9 +89,9 @@ steps:
   - "find compile/h100/ -name 'test_*.py' -print0 | xargs -0 -n1 -I{} pytest -s -v '{}'"
   mirror:
     amd:
-      label: ":amd: (MI355) PyTorch Compilation H100 Cases"
+      label: ":amd: (MI355 DPX) PyTorch Compilation H100 Cases"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 45
       working_dir: "/vllm-workspace/tests"
       depends_on:
@@ -192,10 +192,14 @@ steps:
   - "find compile/fullgraph/ -name 'test_*.py' -not -name 'test_full_cudagraph.py' -print0 | xargs -0 -n1 -I{} pytest -s -v '{}'"
   mirror:
     amd:
-      label: ":amd: (MI355) PyTorch Fullgraph"
+      label: ":amd: (MI355 DPX) PyTorch Fullgraph"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 90
+      # Remove once the ROCm Triton pin includes triton-lang/triton#11567.
+      # Avoid overlapping LLVM codegen/LLD by disabling background precompilation.
+      env:
+        TORCHINDUCTOR_PRECOMPILATION_TIMEOUT_SECONDS: "0"
       depends_on:
       - image-build-amd
 

.buildkite/test_areas/quantization.yaml

@@ -22,9 +22,9 @@ steps:
   - VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s quantization/ --ignore quantization/test_blackwell_moe.py --ignore quantization/test_rocm_moe.py -k 'not test_compressed_tensors_w4a8_fp8' --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
   mirror:
     amd:
-      label: ":amd: (MI355) Quantization Shard %N"
+      label: ":amd: (MI300) Quantization Shard %N"
       dind: false
-      device: mi355_1
+      device: mi300_1
       timeout_in_minutes: 115
       working_dir: "/vllm-workspace/tests"
       depends_on:
@@ -116,9 +116,9 @@ steps:
     - pytest -v -s models/quantization
   mirror:
     amd:
-      label: ":amd: (MI355) Quantized Models"
+      label: ":amd: (MI355 DPX) Quantized Models"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 80
       working_dir: "/vllm-workspace/tests"
       depends_on:

.buildkite/test_areas/ray_compat.yaml

@@ -18,9 +18,9 @@ steps:
   - bash /vllm-workspace/.buildkite/scripts/check-ray-compatibility.sh
   mirror:
     amd:
-      label: ":amd: (MI355) Ray Dependency Compatibility Check"
+      label: ":amd: (MI355 DPX) Ray Dependency Compatibility Check"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 25
       working_dir: "/"
       depends_on:

.buildkite/test_areas/rust_frontend.yaml

@@ -43,9 +43,9 @@ steps:
   - pytest -v -s v1/sample/test_logprobs_e2e.py -k "test_prompt_logprobs_e2e_server"
   mirror:
     amd:
-      label: ":amd: (MI355) Rust Frontend OpenAI Coverage"
+      label: ":amd: (MI355 DPX) Rust Frontend OpenAI Coverage"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 35
       depends_on:
       - image-build-amd
@@ -98,9 +98,9 @@ steps:
   - pytest -v -s entrypoints/serve/tokenize/test_tokenization.py -k "not tokenizer_info"
   mirror:
     amd:
-      label: ":amd: (MI355) Rust Frontend Serve/Admin Coverage"
+      label: ":amd: (MI355 DPX) Rust Frontend Serve/Admin Coverage"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 30
       depends_on:
       - image-build-amd
@@ -133,9 +133,9 @@ steps:
   - pytest -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine
   mirror:
     amd:
-      label: ":amd: (MI355) Rust Frontend Core Correctness"
+      label: ":amd: (MI355 DPX) Rust Frontend Core Correctness"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 25
       depends_on:
       - image-build-amd
@@ -163,9 +163,9 @@ steps:
   - pytest -v -s tool_use --ignore=tool_use/mistral --models llama3.2 -k "not test_response_format_with_tool_choice_required and not test_parallel_tool_calls_false and not test_tool_call_and_choice"
   mirror:
     amd:
-      label: ":amd: (MI355) Rust Frontend Tool Use"
+      label: ":amd: (MI355 DPX) Rust Frontend Tool Use"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 30
       depends_on:
       - image-build-amd

.buildkite/test_areas/samplers.yaml

@@ -53,9 +53,9 @@ steps:
     - VLLM_USE_FLASHINFER_SAMPLER=1 pytest -v -s samplers/test_beam_search.py::test_beam_search_passes_multimodal_data
   mirror:
     amd:
-      label: ":amd: (MI355) Samplers Multimodal Beam Search"
+      label: ":amd: (MI355 DPX) Samplers Multimodal Beam Search"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       num_devices: 1
       timeout_in_minutes: 45
       working_dir: /vllm-workspace/tests

.buildkite/test_areas/spec_decode.yaml

@@ -44,9 +44,9 @@ steps:
     - pytest -v -s v1/e2e/spec_decode/eagle/ -k "deepseek_eagle or qwen3_eagle3"
   mirror:
     amd:
-      label: ":amd: (MI300) Spec Decode Eagle 1: DeepSeek + Qwen"
+      label: ":amd: (MI355 DPX) Spec Decode Eagle 1: DeepSeek + Qwen"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 60
       depends_on:
       - image-build-amd
@@ -71,9 +71,9 @@ steps:
     - pytest -v -s v1/e2e/spec_decode/eagle/ -k "not deepseek_eagle and not qwen3_eagle3"
   mirror:
     amd:
-      label: ":amd: (MI300) Spec Decode Eagle 2: Llama 3 + Qwen VL + Other"
+      label: ":amd: (MI355 DPX) Spec Decode Eagle 2: Llama 3 + Qwen VL + Other"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 60
       depends_on:
       - image-build-amd
@@ -157,9 +157,9 @@ steps:
     - python3 spec_decode/test_custom_proposer.py
   mirror:
     amd:
-      label: ":amd: (MI300) Spec Decode N-Gram + Suffix"
+      label: ":amd: (MI355 DPX) Spec Decode N-Gram + Suffix"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 35
       depends_on:
       - image-build-amd
@@ -185,9 +185,9 @@ steps:
     - pytest -v -s v1/e2e/spec_decode/draft_model/ --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB
   mirror:
     amd:
-      label: ":amd: (MI300) Spec Decode Draft Model Shard %N"
+      label: ":amd: (MI355 DPX) Spec Decode Draft Model Shard %N"
       dind: false
-      device: mi300_1
+      device: mi355_dpx
       timeout_in_minutes: 60
       parallelism: 2
       depends_on:
@@ -392,9 +392,9 @@ steps:
     - if [ "$$BUILDKITE_PARALLEL_JOB" = "2" ]; then pytest -v -s "v1/e2e/spec_decode/acceptance_rates/mtp_other/test_mtp.py::test_gemma4_mtp_acceptance_lengths[True]"; fi
   mirror:
     amd:
-      label: ":amd: (MI355) Spec Decode AL MTP + Other Acceptance Nightly"
+      label: ":amd: (MI355 DPX) Spec Decode AL MTP + Other Acceptance Nightly"
       dind: false
-      device: mi355_1
+      device: mi355_dpx
       timeout_in_minutes: 55
       depends_on:
       - image-build-amd