[ROCm][CI] Preparing gfx90a mirroring (#36210)

Signed-off-by: Andreas Karatzas <akaratza@amd.com>

.buildkite/hardware_tests/amd.yaml

@@ -10,7 +10,7 @@ steps:
       docker build
       --build-arg max_jobs=16
       --build-arg REMOTE_VLLM=1
-      --build-arg ARG_PYTORCH_ROCM_ARCH='gfx942;gfx950'
+      --build-arg ARG_PYTORCH_ROCM_ARCH='gfx90a;gfx942;gfx950'
       --build-arg VLLM_BRANCH=$BUILDKITE_COMMIT
       --tag "rocm/vllm-ci:${BUILDKITE_COMMIT}"
       -f docker/Dockerfile.rocm

.buildkite/test-amd.yaml

@@ -33,6 +33,1335 @@
 #   Note that all steps execute in parallel.
 
 steps:
+
+
+#####################################################################################################################################
+#                                                                                                                                   #
+#  MI250 test definitions ( currently the test set is completely mirrored // TBD which tests are to be routed there ultimately)     #
+#                                                                                                                                   #
+#####################################################################################################################################
+
+- label: Pytorch Nightly Dependency Override Check # 2min
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+  - requirements/nightly_torch_test.txt
+  commands:
+  - bash standalone_tests/pytorch_nightly_dependency.sh
+
+- label: Async Engine, Inputs, Utils, Worker Test # 10min
+  timeout_in_minutes: 15
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+  - vllm/
+  - tests/detokenizer
+  - tests/multimodal
+  - tests/utils_
+  commands:
+  - pytest -v -s detokenizer
+  - pytest -v -s -m 'not cpu_test' multimodal
+  - pytest -v -s utils_
+
+- label: Async Engine, Inputs, Utils, Worker, Config Test (CPU) # 20min
+  timeout_in_minutes: 30
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+  - vllm/
+  - tests/test_inputs.py
+  - tests/test_outputs.py
+  - tests/test_pooling_params.py
+  - tests/multimodal
+  - tests/renderers
+  - tests/standalone_tests/lazy_imports.py
+  - tests/tokenizers_
+  - tests/tool_parsers
+  - tests/transformers_utils
+  - tests/config
+  no_gpu: true
+  commands:
+  - python3 standalone_tests/lazy_imports.py
+  - pytest -v -s test_inputs.py
+  - pytest -v -s test_outputs.py
+  - pytest -v -s test_pooling_params.py
+  - pytest -v -s -m 'cpu_test' multimodal
+  - pytest -v -s renderers
+  - pytest -v -s tokenizers_
+  - pytest -v -s tool_parsers
+  - pytest -v -s transformers_utils
+  - pytest -v -s config
+
+- label: Python-only Installation Test # 10min
+  timeout_in_minutes: 20
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+  - tests/standalone_tests/python_only_compile.sh
+  - setup.py
+  commands:
+  - bash standalone_tests/python_only_compile.sh
+
+- label: Basic Correctness Test # 20min
+  timeout_in_minutes: 30
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  fast_check: true
+  torch_nightly: true
+  source_file_dependencies:
+  - vllm/
+  - tests/basic_correctness/test_basic_correctness
+  - tests/basic_correctness/test_cpu_offload
+  - tests/basic_correctness/test_cumem.py
+  commands:
+  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+  - pytest -v -s basic_correctness/test_cumem.py
+  - pytest -v -s basic_correctness/test_basic_correctness.py
+  - pytest -v -s basic_correctness/test_cpu_offload.py
+
+- label: Entrypoints Unit Tests # 5min
+  timeout_in_minutes: 10
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  working_dir: "/vllm-workspace/tests"
+  fast_check: true
+  source_file_dependencies:
+  - vllm/entrypoints
+  - tests/entrypoints/
+  commands:
+  - pytest -v -s entrypoints/openai/tool_parsers
+  - pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/openai --ignore=entrypoints/rpc --ignore=entrypoints/instrumentator --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py  --ignore=entrypoints/pooling
+
+- label: Entrypoints Integration Test (LLM) # 30min
+  timeout_in_minutes: 40
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  fast_check: true
+  torch_nightly: true
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - vllm/
+  - tests/entrypoints/llm
+  - tests/entrypoints/offline_mode
+  commands:
+  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+  - pytest -v -s entrypoints/llm --ignore=entrypoints/llm/test_generate.py --ignore=entrypoints/llm/test_collective_rpc.py
+  - pytest -v -s entrypoints/llm/test_generate.py
+  - pytest -v -s entrypoints/offline_mode
+
+- label: Entrypoints Integration Test (API Server 1) # 100min
+  timeout_in_minutes: 130
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  working_dir: "/vllm-workspace/tests"
+  fast_check: true
+  torch_nightly: true
+  source_file_dependencies:
+  - vllm/
+  - tests/entrypoints/openai
+  - tests/entrypoints/test_chat_utils
+  commands:
+  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
+  - pytest -v -s entrypoints/test_chat_utils.py
+
+- label: Entrypoints Integration Test (API Server 2)
+  timeout_in_minutes: 50
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  working_dir: "/vllm-workspace/tests"
+  fast_check: true
+  torch_nightly: true
+  source_file_dependencies:
+  - vllm/
+  - tests/entrypoints/rpc
+  - tests/entrypoints/instrumentator
+  - tests/tool_use
+  commands:
+  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+  - pytest -v -s entrypoints/instrumentator
+  - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/rpc
+  - pytest -v -s tool_use
+
+- label: Entrypoints Integration Test (Pooling)
+  timeout_in_minutes: 50
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  fast_check: true
+  torch_nightly: true
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - vllm/
+  - tests/entrypoints/pooling
+  commands:
+  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+  - pytest -v -s entrypoints/pooling
+
+- label: Entrypoints Integration Test (Responses API)
+  timeout_in_minutes: 50
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  working_dir: "/vllm-workspace/tests"
+  fast_check: true
+  torch_nightly: true
+  source_file_dependencies:
+  - vllm/
+  - tests/entrypoints/openai/responses
+  commands:
+  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+  - pytest -v -s entrypoints/openai/responses
+
+- label: Distributed Tests (4 GPUs) # 35min
+  timeout_in_minutes: 50
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_4
+  optional: true
+  num_gpus: 4
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - vllm/distributed/
+  - tests/distributed/test_utils
+  - tests/distributed/test_pynccl
+  - tests/distributed/test_events
+  - tests/compile/fullgraph/test_basic_correctness.py
+  - examples/offline_inference/rlhf.py
+  - examples/offline_inference/rlhf_colocate.py
+  - examples/offline_inference/new_weight_syncing/
+  - tests/examples/offline_inference/data_parallel.py
+  - tests/v1/distributed
+  - tests/v1/engine/test_engine_core_client.py
+  - tests/distributed/test_symm_mem_allreduce.py
+  commands:
+  - export TORCH_NCCL_BLOCKING_WAIT=1
+  - torchrun --nproc-per-node=4 distributed/test_torchrun_example.py
+  - PP_SIZE=2 torchrun --nproc-per-node=4 distributed/test_torchrun_example.py
+  - TP_SIZE=4 torchrun --nproc-per-node=4 distributed/test_torchrun_example_moe.py
+  - PP_SIZE=2 TP_SIZE=2 torchrun --nproc-per-node=4 distributed/test_torchrun_example_moe.py
+  - DP_SIZE=4 ENABLE_EP=1 torchrun --nproc-per-node=4 distributed/test_torchrun_example_moe.py
+  - TP_SIZE=2 DP_SIZE=2 ENABLE_EP=1 torchrun --nproc-per-node=4 distributed/test_torchrun_example_moe.py
+  - python3 ../examples/offline_inference/data_parallel.py --enforce-eager
+  - TP_SIZE=2 DP_SIZE=2 pytest -v -s v1/distributed/test_async_llm_dp.py
+  - TP_SIZE=2 DP_SIZE=2 pytest -v -s v1/distributed/test_eagle_dp.py
+  - TP_SIZE=2 DP_SIZE=2 pytest -v -s v1/distributed/test_external_lb_dp.py
+  - TP_SIZE=1 DP_SIZE=4 pytest -v -s v1/distributed/test_internal_lb_dp.py
+  - TP_SIZE=1 DP_SIZE=4 pytest -v -s v1/distributed/test_hybrid_lb_dp.py
+  - pytest -v -s v1/engine/test_engine_core_client.py::test_kv_cache_events_dp
+  - pytest -v -s distributed/test_utils.py
+  - pytest -v -s compile/fullgraph/test_basic_correctness.py
+  - pytest -v -s distributed/test_pynccl.py
+  - pytest -v -s distributed/test_events.py
+  - pytest -v -s distributed/test_symm_mem_allreduce.py
+  - pushd ../examples/offline_inference
+  - VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 rlhf.py
+  - VLLM_ALLOW_INSECURE_SERIALIZATION=1 RAY_DEDUP_LOGS=0 python3 rlhf_colocate.py
+  - popd
+  - pushd ../examples/offline_inference/new_weight_syncing
+  - VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 rlhf_nccl.py
+  - VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 rlhf_ipc.py
+  - VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 rlhf_async_new_apis.py
+  - popd
+
+- label: Distributed Tests (8 GPUs) # 4min
+  timeout_in_minutes: 10
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_8
+  optional: true
+  num_gpus: 8
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - examples/offline_inference/torchrun_dp_example.py
+  - vllm/config/parallel.py
+  - vllm/distributed/
+  - vllm/v1/engine/llm_engine.py
+  - vllm/v1/executor/uniproc_executor.py
+  - vllm/v1/worker/gpu_worker.py
+  commands:
+  - export TORCH_NCCL_BLOCKING_WAIT=1
+  - torchrun --nproc-per-node=8 ../examples/offline_inference/torchrun_dp_example.py --tp-size=2 --pp-size=1 --dp-size=4 --enable-ep
+
+- label: EPLB Algorithm Test # 5min
+  timeout_in_minutes: 15
+  mirror_hardwares: [amdexperimental, amdproduction, amdtentative, amdgfx90a]
+  agent_pool: mi250_1
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - vllm/distributed/eplb
+  - tests/distributed/test_eplb_algo.py
+  commands:
+  - pytest -v -s distributed/test_eplb_algo.py
+
+- label: EPLB Execution Test # 10min
+  timeout_in_minutes: 20
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_4
+  num_gpus: 4
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - vllm/distributed/eplb
+  - tests/distributed/test_eplb_execute.py
+  commands:
+  - pytest -v -s distributed/test_eplb_execute.py
+  - pytest -v -s distributed/test_eplb_spec_decode.py
+
+- label: Metrics, Tracing Test # 12min
+  timeout_in_minutes: 20
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_2
+  num_gpus: 2
+  source_file_dependencies:
+  - vllm/
+  - tests/v1/tracing
+  commands:
+  - "pip install \
+      'opentelemetry-sdk>=1.26.0' \
+      'opentelemetry-api>=1.26.0' \
+      'opentelemetry-exporter-otlp>=1.26.0' \
+      'opentelemetry-semantic-conventions-ai>=0.4.1'"
+  - pytest -v -s v1/tracing
+
+- label: Regression Test # 7min
+  timeout_in_minutes: 20
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - vllm/
+  - tests/test_regression
+  commands:
+  - pip install modelscope
+  - pytest -v -s test_regression.py
+
+- label: Engine Test # 9min
+  timeout_in_minutes: 15
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+  - vllm/
+  - tests/engine
+  - tests/test_sequence
+  - tests/test_config
+  - tests/test_logger
+  - tests/test_vllm_port
+  commands:
+  - pytest -v -s engine test_sequence.py test_config.py test_logger.py test_vllm_port.py
+
+- label: V1 Test e2e + engine # 65min
+  timeout_in_minutes: 90
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  source_file_dependencies:
+    - vllm/
+    - tests/v1
+  commands:
+    - pytest -v -s v1/e2e
+    - pytest -v -s v1/engine
+
+- label: V1 Test e2e (2 GPUs) # 65min
+  timeout_in_minutes: 90
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_2
+  optional: true
+  source_file_dependencies:
+    - vllm/
+    - tests/v1
+  commands:
+    - pytest -v -s v1/e2e/test_spec_decode.py -k "tensor_parallelism"
+
+- label: V1 Test e2e (4 GPUs) # 65min
+  timeout_in_minutes: 90
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_4
+  optional: true
+  source_file_dependencies:
+    - vllm/
+    - tests/v1
+  commands:
+    - pytest -v -s v1/e2e/test_spec_decode.py -k "eagle_correctness_heavy"
+
+- label: V1 Test entrypoints # 35min
+  timeout_in_minutes: 50
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+    - vllm/
+    - tests/v1
+  commands:
+    - pytest -v -s v1/entrypoints
+
+- label: V1 Test others # 42min
+  timeout_in_minutes: 60
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  source_file_dependencies:
+    - vllm/
+    - tests/v1
+  commands:
+    - uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt
+    - pytest -v -s -m 'not cpu_test' v1/core
+    - pytest -v -s v1/executor
+    - pytest -v -s v1/kv_offload
+    - pytest -v -s v1/sample
+    - pytest -v -s v1/logits_processors
+    - pytest -v -s v1/worker
+    - pytest -v -s v1/spec_decode
+    - pytest -v -s -m 'not cpu_test' v1/kv_connector/unit
+    - pytest -v -s -m 'not cpu_test' v1/metrics
+    - pytest -v -s v1/test_oracle.py
+    - pytest -v -s v1/test_request.py
+    - pytest -v -s v1/test_outputs.py
+    - pip install -U git+https://github.com/robertgshaw2-redhat/lm-evaluation-harness.git@streaming-api
+    - pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine
+
+- label: V1 Test attention (H100) # 10min
+  timeout_in_minutes: 30
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  source_file_dependencies:
+    - vllm/config/attention.py
+    - vllm/model_executor/layers/attention
+    - vllm/v1/attention
+    - tests/v1/attention
+  commands:
+    - pytest -v -s v1/attention
+
+- label: Batch Invariance Tests (H100) # 10min
+  timeout_in_minutes: 25
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+    - vllm/v1/attention
+    - vllm/model_executor/layers
+    - tests/v1/determinism/
+  commands:
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - pip install pytest-timeout pytest-forked
+    - pytest -v -s v1/determinism/test_batch_invariance.py
+    - pytest -v -s v1/determinism/test_rms_norm_batch_invariant.py
+
+- label: V1 Test others (CPU) # 5 mins
+  timeout_in_minutes: 15
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  no_gpu: true
+  source_file_dependencies:
+    - vllm/
+    - tests/v1
+  commands:
+    - pytest -v -s -m 'cpu_test' v1/core
+    - pytest -v -s v1/structured_output
+    - pytest -v -s v1/test_serial_utils.py
+    - pytest -v -s -m 'cpu_test' v1/kv_connector/unit
+    - pytest -v -s -m 'cpu_test' v1/metrics
+
+
+- label: Examples Test # 30min
+  timeout_in_minutes: 45
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  working_dir: "/vllm-workspace/examples"
+  source_file_dependencies:
+  - vllm/entrypoints
+  - vllm/multimodal
+  - examples/
+  commands:
+    - pip install tensorizer
+    - python3 offline_inference/basic/chat.py
+    - python3 offline_inference/basic/generate.py --model facebook/opt-125m
+    - python3 offline_inference/basic/generate.py --model meta-llama/Llama-2-13b-chat-hf --cpu-offload-gb 10
+    - python3 offline_inference/basic/classify.py
+    - python3 offline_inference/basic/embed.py
+    - python3 offline_inference/basic/score.py
+    - python3 offline_inference/audio_language.py --seed 0
+    - python3 offline_inference/vision_language.py --seed 0
+    - python3 offline_inference/vision_language_multi_image.py --seed 0
+    - python3 offline_inference/encoder_decoder_multimodal.py --model-type whisper --seed 0
+    - python3 pooling/embed/vision_embedding_offline.py --seed 0
+    - python3 offline_inference/prefix_caching.py
+    - python3 offline_inference/llm_engine_example.py
+    - python3 others/tensorize_vllm_model.py --model facebook/opt-125m serialize --serialized-directory /tmp/ --suffix v1 && python3 others/tensorize_vllm_model.py --model facebook/opt-125m deserialize --path-to-tensors /tmp/vllm/facebook/opt-125m/v1/model.tensors
+    - python3 offline_inference/spec_decode.py --test --method eagle --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 2048
+    - python3 offline_inference/spec_decode.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
+
+- label: Platform Tests (CUDA) # 4min
+  timeout_in_minutes: 15
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+  - vllm/
+  - tests/cuda
+  commands:
+    - pytest -v -s cuda/test_cuda_context.py
+    - pytest -v -s cuda/test_platform_no_cuda_init.py
+
+- label: Samplers Test # 56min
+  timeout_in_minutes: 75
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  source_file_dependencies:
+  - vllm/model_executor/layers
+  - vllm/sampling_metadata.py
+  - tests/samplers
+  - tests/conftest.py
+  commands:
+    - pytest -v -s samplers
+
+- label: LoRA Test %N # 20min
+  timeout_in_minutes: 30
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  parallelism: 4
+  source_file_dependencies:
+  - vllm/lora
+  - tests/lora
+  commands:
+    - pytest -v -s lora \
+      --shard-id=$$BUILDKITE_PARALLEL_JOB \
+      --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT \
+      --ignore=lora/test_chatglm3_tp.py \
+      --ignore=lora/test_llama_tp.py \
+      --ignore=lora/test_llm_with_multi_loras.py \
+      --ignore=lora/test_olmoe_tp.py \
+      --ignore=lora/test_deepseekv2_tp.py \
+      --ignore=lora/test_gptoss_tp.py \
+      --ignore=lora/test_qwen3moe_tp.py
+
+- label: PyTorch Compilation Unit Tests # 15min
+  timeout_in_minutes: 30
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  torch_nightly: true
+  source_file_dependencies:
+    - vllm/
+    - tests/compile
+  commands:
+  - "find compile/ -maxdepth 1 -name 'test_*.py' -exec pytest -s -v {} \\\\;"
+
+- label: PyTorch Compilation Passes Unit Tests
+  timeout_in_minutes: 20
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+    - vllm/
+    - tests/compile/passes
+  commands:
+  - "find compile/passes -maxdepth 1 -name 'test_*.py' -exec pytest -s -v {} \\\\;"
+
+- label: PyTorch Fullgraph Smoke Test # 15min
+  timeout_in_minutes: 30
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  torch_nightly: true
+  source_file_dependencies:
+  - vllm/
+  - tests/compile
+  commands:
+  - "find compile/fullgraph/ -name 'test_*.py' -not -name 'test_full_graph.py' -exec pytest -s -v {} \\\\;"
+
+- label: PyTorch Fullgraph Test # 27min
+  timeout_in_minutes: 40
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  torch_nightly: true
+  source_file_dependencies:
+  - vllm/
+  - tests/compile
+  commands:
+  - pytest -v -s compile/fullgraph/test_full_graph.py -k 'not test_fp8_kv_scale_compile'
+
+- label: Cudagraph test # 15min
+  timeout_in_minutes: 20
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+  - tests/v1/cudagraph
+  - vllm/v1/cudagraph_dispatcher.py
+  - vllm/config/compilation.py
+  - vllm/compilation
+  commands:
+    - pytest -v -s v1/cudagraph/test_cudagraph_dispatch.py
+    - pytest -v -s v1/cudagraph/test_cudagraph_mode.py
+
+- label: Kernels Core Operation Test # 48min
+  timeout_in_minutes: 75
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+  - csrc/
+  - tests/kernels/core
+  - tests/kernels/test_top_k_per_row.py
+  commands:
+    - pytest -v -s kernels/core kernels/test_top_k_per_row.py
+
+- label: Kernels Attention Test %N # 23min
+  timeout_in_minutes: 35
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  parallelism: 2
+  source_file_dependencies:
+  - csrc/attention/
+  - vllm/v1/attention
+  - vllm/model_executor/layers/attention
+  - tests/kernels/attention
+  commands:
+    - pytest -v -s kernels/attention --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
+
+- label: Kernels Quantization Test %N # 64min
+  timeout_in_minutes: 90
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  parallelism: 2
+  source_file_dependencies:
+  - csrc/quantization/
+  - vllm/model_executor/layers/quantization
+  - tests/kernels/quantization
+  commands:
+    - pytest -v -s kernels/quantization --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
+
+- label: Kernels MoE Test %N # 40min
+  timeout_in_minutes: 60
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  parallelism: 2
+  source_file_dependencies:
+  - csrc/quantization/cutlass_w8a8/moe/
+  - csrc/moe/
+  - tests/kernels/moe
+  - vllm/model_executor/layers/fused_moe/
+  - vllm/distributed/device_communicators/
+  - vllm/envs.py
+  - vllm/config
+  commands:
+    - pytest -v -s kernels/moe --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
+
+- label: Kernels Mamba Test # 31min
+  timeout_in_minutes: 45
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+  - csrc/mamba/
+  - tests/kernels/mamba
+  - vllm/model_executor/layers/mamba/ops
+  commands:
+    - pytest -v -s kernels/mamba
+
+- label: Kernels Helion Test # 20min
+  timeout_in_minutes: 30
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+  - vllm/utils/import_utils.py
+  - tests/kernels/helion/
+  commands:
+    - pip install helion
+    - pytest -v -s kernels/helion/
+
+- label: Model Executor Test # 23min
+  timeout_in_minutes: 35
+  torch_nightly: true
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+  - vllm/engine/arg_utils.py
+  - vllm/config/model.py
+  - vllm/model_executor
+  - tests/model_executor
+  - tests/entrypoints/openai/test_tensorizer_entrypoint.py
+  commands:
+    - apt-get update && apt-get install -y curl libsodium23
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - pytest -v -s model_executor
+    - pytest -v -s entrypoints/openai/test_tensorizer_entrypoint.py
+
+- label: Benchmarks # 11min
+  timeout_in_minutes: 20
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  working_dir: "/vllm-workspace/.buildkite"
+  source_file_dependencies:
+  - benchmarks/
+  commands:
+  - bash scripts/run-benchmarks.sh
+
+- label: Benchmarks CLI Test # 7min
+  timeout_in_minutes: 20
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+  - vllm/
+  - tests/benchmarks/
+  commands:
+  - pytest -v -s benchmarks/
+
+- label: Quantization Test # 70min
+  timeout_in_minutes: 90
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+  - csrc/
+  - vllm/model_executor/layers/quantization
+  - tests/quantization
+  commands:
+  - uv pip install --system torchao==0.14.1
+  - uv pip install --system conch-triton-kernels
+  - VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s quantization/ --ignore quantization/test_blackwell_moe.py
+
+- label: LM Eval Small Models # 53min
+  timeout_in_minutes: 75
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  source_file_dependencies:
+  - csrc/
+  - vllm/model_executor/layers/quantization
+  autorun_on_main: true
+  commands:
+  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt
+
+- label: OpenAI API correctness # 10min
+  timeout_in_minutes: 15
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+  - csrc/
+  - vllm/entrypoints/openai/
+  - vllm/model_executor/models/whisper.py
+  - tools/
+  commands:
+  - bash ../tools/install_torchcodec_rocm.sh || exit 1
+  - pytest -s entrypoints/openai/correctness/
+
+- label: Basic Models Tests (Initialization) # 15min
+  timeout_in_minutes: 45
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  torch_nightly: true
+  source_file_dependencies:
+  - vllm/
+  - tests/models/test_initialization.py
+  commands:
+    - pytest -v -s models/test_initialization.py::test_can_initialize_small_subset
+
+- label: Basic Models Tests (Extra Initialization) %N # 15min
+  timeout_in_minutes: 45
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  torch_nightly: true
+  parallelism: 2
+  source_file_dependencies:
+  - vllm/model_executor/models/
+  - vllm/transformers_utils/
+  - tests/models/test_initialization.py
+  commands:
+    - pytest -v -s models/test_initialization.py \
+             -k 'not test_can_initialize_small_subset' \
+             --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT \
+             --shard-id=$$BUILDKITE_PARALLEL_JOB
+
+- label: Basic Models Tests (Other) # 15min
+  timeout_in_minutes: 45
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  torch_nightly: true
+  source_file_dependencies:
+  - vllm/
+  - tests/models/test_terratorch.py
+  - tests/models/test_transformers.py
+  - tests/models/test_registry.py
+  commands:
+    - pytest -v -s models/test_terratorch.py models/test_transformers.py models/test_registry.py
+
+- label: Basic Models Test (Other CPU) # 5min
+  timeout_in_minutes: 10
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  torch_nightly: true
+  no_gpu: true
+  source_file_dependencies:
+  - vllm/
+  - tests/models/test_utils.py
+  - tests/models/test_vision.py
+  commands:
+    - pytest -v -s models/test_utils.py models/test_vision.py
+
+- label: Language Models Tests (Standard) # 18min
+  timeout_in_minutes: 25
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  torch_nightly: true
+  source_file_dependencies:
+  - vllm/
+  - tests/models/language
+  commands:
+    - pip freeze | grep -E 'torch'
+    - pytest -v -s models/language -m 'core_model and (not slow_test)'
+
+- label: Language Models Tests (Extra Standard) %N # 27min
+  timeout_in_minutes: 45
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  torch_nightly: true
+  parallelism: 2
+  source_file_dependencies:
+  - vllm/model_executor/models/
+  - tests/models/language/pooling/test_embedding.py
+  - tests/models/language/generation/test_common.py
+  - tests/models/language/pooling/test_classification.py
+  commands:
+    - pip freeze | grep -E 'torch'
+    - export TORCH_NCCL_BLOCKING_WAIT=1
+    - pytest -v -s models/language -m 'core_model and slow_test' \
+             --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT \
+             --shard-id=$$BUILDKITE_PARALLEL_JOB
+
+- label: Language Models Tests (Hybrid) %N # 50min
+  timeout_in_minutes: 75
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  torch_nightly: true
+  parallelism: 2
+  source_file_dependencies:
+  - vllm/
+  - tests/models/language/generation
+  commands:
+    - uv pip install --system --no-build-isolation 'git+https://github.com/AndreasKaratzas/mamba@fix-rocm-7.0-warp-size-constexpr'
+    - uv pip install --system --no-build-isolation 'git+https://github.com/Dao-AILab/causal-conv1d@v1.5.2'
+    - pytest -v -s models/language/generation \
+                   -m hybrid_model \
+                   --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT \
+                   --shard-id=$$BUILDKITE_PARALLEL_JOB
+
+- label: Language Models Test (Extended Generation) # 80min
+  timeout_in_minutes: 110
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  source_file_dependencies:
+  - vllm/
+  - tests/models/language/generation
+  commands:
+    - uv pip install --system --no-build-isolation 'git+https://github.com/AndreasKaratzas/mamba@fix-rocm-7.0-warp-size-constexpr'
+    - uv pip install --system --no-build-isolation 'git+https://github.com/Dao-AILab/causal-conv1d@v1.5.2'
+    - pytest -v -s models/language/generation -m '(not core_model) and (not hybrid_model)'
+
+- label: Language Models Test (PPL) # 80min
+  timeout_in_minutes: 110
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  source_file_dependencies:
+  - vllm/
+  - tests/models/language/generation_ppl_test
+  commands:
+    - pytest -v -s models/language/generation_ppl_test
+
+- label: Language Models Test (Extended Pooling)  # 36min
+  timeout_in_minutes: 50
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  source_file_dependencies:
+  - vllm/
+  - tests/models/language/pooling
+  commands:
+    - pytest -v -s models/language/pooling -m 'not core_model'
+
+- label: Language Models Test (MTEB) # 80min
+  timeout_in_minutes: 110
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  source_file_dependencies:
+  - vllm/
+  - tests/models/language/pooling_mteb_test
+  commands:
+    - pytest -v -s models/language/pooling_mteb_test
+
+- label: Multi-Modal Processor Test (CPU) # 15min
+  timeout_in_minutes: 60
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  no_gpu: true
+  source_file_dependencies:
+  - vllm/
+  - tests/models/multimodal
+  - tests/models/registry.py
+  commands:
+    - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
+    - pytest -v -s models/multimodal/processing --ignore models/multimodal/processing/test_tensor_schema.py
+
+- label: Multi-Modal Processor Test # 44min
+  timeout_in_minutes: 60
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+  - vllm/
+  - tests/models/multimodal
+  - tests/models/registry.py
+  commands:
+    - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
+    - pytest -v -s models/multimodal/processing
+
+- label: Multi-Modal Models Test (Standard) # 60min
+  timeout_in_minutes: 100
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  torch_nightly: true
+  source_file_dependencies:
+  - vllm/
+  - tests/models/multimodal
+  commands:
+    - export MIOPEN_DEBUG_CONV_DIRECT=0
+    - export MIOPEN_DEBUG_CONV_GEMM=0
+    - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
+    - pip freeze | grep -E 'torch'
+    - pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/processing --ignore models/multimodal/pooling/test_prithvi_mae.py
+    - pytest -v -s models/multimodal/pooling/test_prithvi_mae.py -m core_model
+    - 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
+
+- label: Multi-Modal Accuracy Eval (Small Models) # 5min
+  timeout_in_minutes: 10
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  working_dir: "/vllm-workspace/.buildkite/lm-eval-harness"
+  source_file_dependencies:
+  - vllm/multimodal/
+  - vllm/inputs/
+  - vllm/v1/core/
+  commands:
+  - export MIOPEN_DEBUG_CONV_DIRECT=0
+  - export MIOPEN_DEBUG_CONV_GEMM=0
+  - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-mm-small.txt
+
+- label: Multi-Modal Models Test (Extended) 1 # 60min
+  timeout_in_minutes: 120
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  source_file_dependencies:
+  - vllm/
+  - tests/models/multimodal
+  commands:
+    - export MIOPEN_DEBUG_CONV_DIRECT=0
+    - export MIOPEN_DEBUG_CONV_GEMM=0
+    - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
+    - pytest -v -s models/multimodal -m 'not core_model' --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/processing
+
+- label: Multi-Modal Models Test (Extended) 2 #60min
+  timeout_in_minutes: 120
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  source_file_dependencies:
+  - vllm/
+  - tests/models/multimodal
+  commands:
+    - export MIOPEN_DEBUG_CONV_DIRECT=0
+    - export MIOPEN_DEBUG_CONV_GEMM=0
+    - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
+    - pytest -v -s models/multimodal/generation/test_common.py -m 'split(group=0) and not core_model'
+
+- label: Multi-Modal Models Test (Extended) 3 # 75min
+  timeout_in_minutes: 150
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  optional: true
+  source_file_dependencies:
+  - vllm/
+  - tests/models/multimodal
+  commands:
+    - export MIOPEN_DEBUG_CONV_DIRECT=0
+    - export MIOPEN_DEBUG_CONV_GEMM=0
+    - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
+    - pytest -v -s models/multimodal/generation/test_common.py -m 'split(group=1) and not core_model'
+
+- label: Quantized Models Test # 45 min
+  timeout_in_minutes: 60
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+  - vllm/model_executor/layers/quantization
+  - tests/models/quantization
+  commands:
+    - pytest -v -s models/quantization
+
+- label: Transformers Nightly Models Test # 60 min
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  working_dir: "/vllm-workspace/"
+  optional: true
+  commands:
+    - pip install --upgrade git+https://github.com/huggingface/transformers
+    - pytest -v -s tests/models/test_initialization.py -k 'not (Gemma3 or ModernBert or Qwen2_5_VL or Qwen2_5vl or Qwen2VL or TransformersMultiModalEmbeddingModel or TransformersMultiModalForSequenceClassification or Ultravox or Phi4Multimodal or LlavaNextVideo or MiniCPMO or Lfm2Moe or PaliGemma or RobertaForSequenceClassification or Ovis2_5 or Fuyu or DeepseekOCR or KimiVL)'
+    - pytest -v -s tests/models/test_transformers.py
+    - pytest -v -s tests/models/multimodal/test_mapping.py -k 'not (Gemma3 or Qwen2VL or Qwen2_5_VL)'
+    - python3 examples/offline_inference/basic/chat.py
+    - VLLM_WORKER_MULTIPROC_METHOD=spawn python3 examples/offline_inference/audio_language.py --model-type whisper
+
+- label: Distributed Comm Ops Test # 7min
+  timeout_in_minutes: 20
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_2
+  num_gpus: 2
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - vllm/distributed
+  - tests/distributed
+  commands:
+  - pytest -v -s distributed/test_comm_ops.py
+  - pytest -v -s distributed/test_shm_broadcast.py
+  - pytest -v -s distributed/test_shm_buffer.py
+  - pytest -v -s distributed/test_shm_storage.py
+
+- label: 2 Node Tests (4 GPUs in total) # 16min
+  timeout_in_minutes: 30
+  mirror_hardwares: [amdexperimental, amdproduction, amdmultinode, amdgfx90a]
+  agent_pool: mi250_4
+  optional: true
+  num_gpus: 2
+  num_nodes: 2
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - vllm/distributed/
+  - vllm/engine/
+  - vllm/executor/
+  - vllm/model_executor/models/
+  - tests/distributed/
+  - tests/examples/offline_inference/data_parallel.py
+  commands:
+  - # the following commands are for the first node, with ip 192.168.10.10 (ray environment already set up)  | grep 'Same node test passed'   | grep 'Node count test passed'
+    - VLLM_TEST_SAME_HOST=0 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_same_node.py 
+    - NUM_NODES=2 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_node_count.py 
+    - python3 ../examples/offline_inference/data_parallel.py -dp=2 -tp=1 --dp-num-nodes=2 --dp-node-rank=0 --dp-master-addr=192.168.10.10 --dp-master-port=12345 --enforce-eager --trust-remote-code
+    - VLLM_MULTI_NODE=1 pytest -v -s distributed/test_multi_node_assignment.py
+    - VLLM_MULTI_NODE=1 pytest -v -s distributed/test_pipeline_parallel.py
+  - # the following commands are for the second node, with ip 192.168.10.11 (ray environment already set up)
+    - VLLM_TEST_SAME_HOST=0 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_same_node.py 
+    - NUM_NODES=2 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_node_count.py 
+    - python3 ../examples/offline_inference/data_parallel.py -dp=2 -tp=1 --dp-num-nodes=2 --dp-node-rank=1 --dp-master-addr=192.168.10.10 --dp-master-port=12345 --enforce-eager --trust-remote-code
+
+- label: Distributed Tests (2 GPUs) # 68min
+  timeout_in_minutes: 90
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_2
+  optional: true
+  num_gpus: 2
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - vllm/compilation/
+  - vllm/distributed/
+  - vllm/engine/
+  - vllm/executor/
+  - vllm/worker/worker_base.py
+  - vllm/v1/engine/
+  - vllm/v1/worker/
+  - tests/compile/fullgraph/test_basic_correctness.py
+  - tests/compile/test_wrapper.py
+  - tests/distributed/
+  - tests/entrypoints/llm/test_collective_rpc.py
+  - tests/v1/distributed
+  - tests/v1/entrypoints/openai/test_multi_api_servers.py
+  - tests/v1/shutdown
+  - tests/v1/worker/test_worker_memory_snapshot.py
+  - examples/offline_inference/new_weight_syncing/
+  commands:
+  - export TORCH_NCCL_BLOCKING_WAIT=1
+  - TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_async_llm_dp.py
+  - TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_eagle_dp.py
+  - TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_external_lb_dp.py
+  - DP_SIZE=2 pytest -v -s v1/entrypoints/openai/test_multi_api_servers.py
+  - pytest -v -s entrypoints/llm/test_collective_rpc.py
+  - pytest -v -s ./compile/fullgraph/test_basic_correctness.py
+  - pytest -v -s ./compile/test_wrapper.py
+  - VLLM_TEST_SAME_HOST=1 torchrun --nproc-per-node=4 distributed/test_same_node.py | grep 'Same node test passed'
+  - VLLM_TEST_SAME_HOST=1 VLLM_TEST_WITH_DEFAULT_DEVICE_SET=1 torchrun --nproc-per-node=4 distributed/test_same_node.py | grep 'Same node test passed'
+  - CUDA_VISIBLE_DEVICES=0,1 pytest -v -s v1/shutdown
+  - pytest -v -s v1/worker/test_worker_memory_snapshot.py
+
+- label: Distributed Model Tests (2 GPUs) # 37min
+  timeout_in_minutes: 50
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_2
+  optional: true
+  num_gpus: 2
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - vllm/model_executor/model_loader/sharded_state_loader.py
+  - vllm/model_executor/models/
+  - tests/basic_correctness/
+  - tests/model_executor/model_loader/test_sharded_state_loader.py
+  - tests/models/
+  commands:
+  - TARGET_TEST_SUITE=L4 pytest basic_correctness/ -v -s -m 'distributed(num_gpus=2)'
+  - CUDA_VISIBLE_DEVICES=0,1 pytest -v -s model_executor/model_loader/test_sharded_state_loader.py
+  - pytest models/test_transformers.py -v -s -m 'distributed(num_gpus=2)'
+  - pytest models/language -v -s -m 'distributed(num_gpus=2)'
+  - pytest models/multimodal -v -s -m 'distributed(num_gpus=2)' --ignore models/multimodal/generation/test_whisper.py
+  - VLLM_WORKER_MULTIPROC_METHOD=spawn pytest models/multimodal/generation/test_whisper.py -v -s -m 'distributed(num_gpus=2)'
+
+- label: Plugin Tests (2 GPUs) # 40min
+  timeout_in_minutes: 60
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_2
+  num_gpus: 2
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - vllm/plugins/
+  - tests/plugins/
+  commands:
+  # begin platform plugin and general plugin tests, all the code in-between runs on dummy platform
+  - pip install -e ./plugins/vllm_add_dummy_platform
+  - pytest -v -s plugins_tests/test_platform_plugins.py
+  - pip uninstall vllm_add_dummy_platform -y
+  # end platform plugin tests
+  # begin io_processor plugins test, all the code in between uses the prithvi_io_processor plugin
+  - pip install -e ./plugins/prithvi_io_processor_plugin
+  - pytest -v -s plugins_tests/test_io_processor_plugins.py
+  - pip uninstall prithvi_io_processor_plugin -y
+  # test bge_m3_sparse io_processor plugin
+  - pip install -e ./plugins/bge_m3_sparse_plugin
+  - pytest -v -s plugins_tests/test_bge_m3_sparse_io_processor_plugins.py
+  - pip uninstall bge_m3_sparse_plugin -y
+  # end io_processor plugins test
+  # begin stat_logger plugins test
+  - pip install -e ./plugins/vllm_add_dummy_stat_logger
+  - pytest -v -s plugins_tests/test_stats_logger_plugins.py
+  - pip uninstall dummy_stat_logger -y
+  # end stat_logger plugins test
+  # other tests continue here:
+  - pytest -v -s plugins_tests/test_scheduler_plugins.py
+  - pip install -e ./plugins/vllm_add_dummy_model
+  - pytest -v -s distributed/test_distributed_oot.py
+  - pytest -v -s entrypoints/openai/test_oot_registration.py
+  - pytest -v -s models/test_oot_registration.py
+  - pytest -v -s plugins/lora_resolvers
+
+- label: Pipeline + Context Parallelism Test # 45min
+  timeout_in_minutes: 60
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_4
+  num_gpus: 4
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - vllm/distributed/
+  - vllm/engine/
+  - vllm/executor/
+  - vllm/model_executor/models/
+  - tests/distributed/
+  commands:
+  - pytest -v -s distributed/test_pp_cudagraph.py
+  - pytest -v -s distributed/test_pipeline_parallel.py
+
+- label: LoRA TP Test (Distributed) # 17 min
+  timeout_in_minutes: 30
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_4
+  num_gpus: 4
+  source_file_dependencies:
+  - vllm/lora
+  - tests/lora
+  commands:
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - pytest -v -s -x lora/test_chatglm3_tp.py
+    - pytest -v -s -x lora/test_llama_tp.py
+    - pytest -v -s -x lora/test_llm_with_multi_loras.py
+    - pytest -v -s -x lora/test_olmoe_tp.py
+
+- label: Weight Loading Multiple GPU Test  # 33min
+  timeout_in_minutes: 45
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_2
+  num_gpus: 2
+  optional: true
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - vllm/
+  - tests/weight_loading
+  commands:
+    - bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models-amd.txt
+
+- label: Weight Loading Multiple GPU Test - Large Models # optional
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_2
+  num_gpus: 2
+  optional: true
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+  - vllm/
+  - tests/weight_loading
+  commands:
+    - bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models-large-amd.txt
+
+- label: NixlConnector PD accuracy tests (Distributed) # 30min
+  timeout_in_minutes: 30
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_4
+  num_gpus: 4
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+    - vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py
+    - tests/v1/kv_connector/nixl_integration/
+  commands:
+    - uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt
+    - ROCM_ATTN=1 bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
+
+- label: DP EP NixlConnector PD accuracy tests (Distributed) # 15min
+  timeout_in_minutes: 15
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_4
+  num_gpus: 4
+  working_dir: "/vllm-workspace/tests"
+  source_file_dependencies:
+    - vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py
+    - tests/v1/kv_connector/nixl_integration/
+  commands:
+    - uv pip install --system -r /vllm-workspace/requirements/kv_connectors_rocm.txt
+    - DP_EP=1 ROCM_ATTN=1 bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
+
+- label: Distributed Tests (A100) # 68min
+  timeout_in_minutes: 90
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_4
+  optional: true
+  num_gpus: 4
+  source_file_dependencies:
+  - vllm/
+  commands:
+  - export TORCH_NCCL_BLOCKING_WAIT=1
+  - pytest -v -s distributed/test_custom_all_reduce.py
+  - torchrun --nproc_per_node=2 distributed/test_ca_buffer_sharing.py
+  - TARGET_TEST_SUITE=A100 pytest basic_correctness/ -v -s -m 'distributed(num_gpus=2)'
+  - pytest -v -s -x lora/test_mixtral.py
+
+- label: LM Eval Large Models # 80min
+  timeout_in_minutes: 110
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_4
+  optional: true
+  num_gpus: 4
+  working_dir: "/vllm-workspace/.buildkite/lm-eval-harness"
+  source_file_dependencies:
+  - csrc/
+  - vllm/model_executor/layers/quantization
+  commands:
+  - 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 (H100) # 80min
+  timeout_in_minutes: 110
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_4
+  optional: true
+  num_gpus: 4
+  working_dir: "/vllm-workspace/.buildkite/lm-eval-harness"
+  source_file_dependencies:
+  - csrc/
+  - vllm/model_executor/layers/quantization
+  commands:
+    - export VLLM_USE_DEEP_GEMM=0 
+    - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-large-rocm.txt --tp-size=4
+
+- label: Distributed Tests (H200) # 68min
+  timeout_in_minutes: 90
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_2
+  optional: true
+  num_gpus: 2
+  working_dir: "/vllm-workspace/"
+  commands:
+    - VLLM_TEST_CLEAN_GPU_MEMORY=1 pytest -v -s tests/compile/passes/distributed/test_async_tp.py
+    - pytest -v -s tests/compile/passes/distributed/test_sequence_parallelism.py
+    - pytest -v -s tests/distributed/test_context_parallel.py
+    - HIP_VISIBLE_DEVICES=0,1 VLLM_LOGGING_LEVEL=DEBUG python3 examples/offline_inference/data_parallel.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
+
+- label: LM Eval Small Models (1 Card) # 15min
+  timeout_in_minutes: 20
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_1
+  source_file_dependencies:
+  - csrc/
+  - vllm/model_executor/layers/quantization
+  commands:
+  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt
+
+- label: LM Eval Large Models (4 Card) # 80min
+  timeout_in_minutes: 110
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_4
+  optional: true
+  num_gpus: 4
+  working_dir: "/vllm-workspace/.buildkite/lm-eval-harness"
+  source_file_dependencies:
+  - csrc/
+  - vllm/model_executor/layers/quantization
+  commands:
+  - 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: ROCm LM Eval Large Models (8 Card) # 80min
+  timeout_in_minutes: 110
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_8
+  num_gpus: 8
+  working_dir: "/vllm-workspace/.buildkite/lm-eval-harness"
+  commands:
+  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+  - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-large-rocm.txt --tp-size=8
+
+- label: ROCm GPT-OSS Eval # 80min
+  timeout_in_minutes: 60
+  working_dir: "/vllm-workspace/"
+  agent_pool: mi250_1
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  optional: true
+  source_file_dependencies:
+  - tests/evals/gpt_oss
+  - vllm/model_executor/models/gpt_oss.py
+  - vllm/model_executor/layers/quantization/mxfp4.py
+  - vllm/v1/attention/backends/flashinfer.py
+  commands:
+    - uv pip install --system 'gpt-oss[eval]==0.0.5'
+    - VLLM_ROCM_USE_AITER_MHA=0 VLLM_ROCM_USE_AITER=1 VLLM_USE_AITER_UNIFIED_ATTENTION=1 pytest -s -v tests/evals/gpt_oss/test_gpqa_correctness.py --model openai/gpt-oss-20b --metric 0.58
+
+- label: DeepSeek V2-Lite Accuracy # 70min
+  timeout_in_minutes: 60
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_4
+  optional: true
+  num_gpus: 4
+  working_dir: "/vllm-workspace"
+  commands:
+  - bash .buildkite/scripts/scheduled_integration_test/deepseek_v2_lite_ep_eplb.sh 0.25 200 8010
+
+- label: Qwen3-Next-80B-A3B-Instruct MTP Async EPLB Accuracy # 70min
+  timeout_in_minutes: 60
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx90a]
+  agent_pool: mi250_4
+  optional: true
+  num_gpus: 4
+  working_dir: "/vllm-workspace"
+  commands:
+  - bash .buildkite/scripts/scheduled_integration_test/qwen3_next_mtp_async_eplb.sh 0.8 1319 8040
+
+
+###################################################
+#                                                 #
+#  MI325 test definitions                         #
+#                                                 #
+###################################################
+
+
 ##### fast check tests  #####
 
 - label: Pytorch Nightly Dependency Override Check # 2min