diff --git a/.buildkite/test-pipeline.yaml b/.buildkite/test-pipeline.yaml
index ecbf1a878..b0a7ba8aa 100644
--- a/.buildkite/test-pipeline.yaml
+++ b/.buildkite/test-pipeline.yaml
@@ -1,1524 +1,8 @@
-# In this file, you can add more tests to run either by adding a new step or
-# adding a new command to an existing step. See different options here for examples.
+# This file has been deprecated as of Feb 18, 2026. The content has already been migrated to:
 
-# This script will be feed into Jinja template in `test-template-aws.j2` at
-# https://github.com/vllm-project/buildkite-ci/blob/main/scripts/test-template-aws.j2
-# to generate the final pipeline yaml file.
+# .buildkite/test_areas for test jobs
+# .buildkite/image_build for image building jobs
+# .buildkite/hardware_tests for jobs running on other hardwares (Intel, Ascend NPU, Arm, etc..)
+# .buildkite/ci_config.yaml for configuration of CI pipeline
 
-# Documentation
-# label(str): the name of the test. emojis allowed.
-# fast_check(bool): whether to run this on each commit on the fastcheck pipeline.
-# torch_nightly(bool): whether to run this on vllm against the torch nightly pipeline.
-# fast_check_only(bool): run this test on the fastcheck pipeline only
-# optional(bool): never run this test by default (i.e. need to unblock manually) unless it's a scheduled nightly run.
-# soft_fail(bool): allow this step to fail without failing the entire pipeline (useful for flaky or experimental tests).
-# command(str): the single command to run for tests. incompatible with commands.
-# commands(list): the list of commands to run for the test. incompatible with command.
-# mirror_hardwares(list): the list of hardware to run the test on as well. currently only supports [amdexperimental]
-# gpu(str): override the GPU selection for the test. default is L4 GPUs. supports a100, b200, h200
-# num_gpus(int): override the number of GPUs for the test. defaults to 1 GPU. currently supports 2,4.
-# num_nodes(int): whether to simulate multi-node setup by launching multiple containers on one host,
-#     in this case, commands must be specified. the first command runs on the first host, the second
-#     command runs on the second host.
-# timeout_in_minutes(int): sets a timeout for the step in minutes. if not specified, uses the default timeout.
-# parallelism(int): number of parallel jobs to run for this step. enables test sharding using $$BUILDKITE_PARALLEL_JOB
-#     and $$BUILDKITE_PARALLEL_JOB_COUNT environment variables.
-# working_dir(str): specify the place where the command should execute, default to /vllm-workspace/tests
-# source_file_dependencies(list): the list of prefixes to opt-in the test for, if empty, the test will always run.
-# autorun_on_main (bool): default to false, if true, the test will run automatically when commit is pushed to main branch.
-
-# When adding a test
-# - If the test belongs to an existing group, add it there
-# - If the test is short, add to any existing step
-# - If the test takes more than 10min, then it is okay to create a new step.
-#   Note that all steps execute in parallel.
-
-steps:
-##### fast check tests  #####
-
-- label: Pytorch Nightly Dependency Override Check # 2min
-  # if this test fails, it means the nightly torch version is not compatible with some
-  # of the dependencies. Please check the error message and add the package to whitelist
-  # in /vllm/tools/pre_commit/generate_nightly_torch_test.py
-  soft_fail: true
-  source_file_dependencies:
-  - requirements/nightly_torch_test.txt
-  commands:
-  - bash standalone_tests/pytorch_nightly_dependency.sh
-
-- label: Async Engine, Inputs, Utils, Worker Test # 36min
-  timeout_in_minutes: 50
-  mirror_hardwares: [amdexperimental]
-  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
-  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]
-  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]
-  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
-  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/rpc --ignore=entrypoints/instrumentator --ignore=entrypoints/openai --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]
-  working_dir: "/vllm-workspace/tests"
-  fast_check: true
-  torch_nightly: true
-  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 # it needs a clean process
-  - pytest -v -s entrypoints/offline_mode # Needs to avoid interference with other tests
-
-- label: Entrypoints Integration Test (API Server 1) # 100min
-  timeout_in_minutes: 130
-  mirror_hardwares: [amdexperimental]
-  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/instrumentator --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]
-  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]
-  working_dir: "/vllm-workspace/tests"
-  fast_check: true
-  torch_nightly: true
-  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]
-  working_dir: "/vllm-workspace/tests"
-  fast_check: true
-  torch_nightly: true
-  source_file_dependencies:
-  - vllm/
-  - tests/entrypoints/openai/responses
-  commands:
-  - pytest -v -s entrypoints/openai/responses
-
-- label: Distributed Tests (4 GPUs) # 35min
-  timeout_in_minutes: 50
-  mirror_hardwares: [amdexperimental]
-  working_dir: "/vllm-workspace/tests"
-  num_gpus: 4
-  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:
-  # https://github.com/NVIDIA/nccl/issues/1838
-  - export NCCL_CUMEM_HOST_ENABLE=0
-  # test with torchrun tp=2 and external_dp=2
-  - torchrun --nproc-per-node=4 distributed/test_torchrun_example.py
-  # test with torchrun tp=2 and pp=2
-  - PP_SIZE=2 torchrun --nproc-per-node=4 distributed/test_torchrun_example.py
-  # test with torchrun tp=4 and dp=1
-  - TP_SIZE=4 torchrun --nproc-per-node=4 distributed/test_torchrun_example_moe.py
-  # test with torchrun tp=2, pp=2 and dp=1
-  - PP_SIZE=2 TP_SIZE=2 torchrun --nproc-per-node=4 distributed/test_torchrun_example_moe.py
-  # test with torchrun tp=1 and dp=4 with ep
-  - DP_SIZE=4 ENABLE_EP=1 torchrun --nproc-per-node=4 distributed/test_torchrun_example_moe.py
-  # test with torchrun tp=2 and dp=2 with ep
-  - TP_SIZE=2 DP_SIZE=2 ENABLE_EP=1 torchrun --nproc-per-node=4 distributed/test_torchrun_example_moe.py
-  # test with internal dp
-  - 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
-  # TODO: create a dedicated test section for multi-GPU example tests
-  # when we have multiple distributed example tests
-  # OLD rlhf examples
-  - 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
-  # NEW rlhf examples
-  - pushd ../examples/offline_inference/new_weight_syncing
-  - VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 rlhf.py
-  - VLLM_ALLOW_INSECURE_SERIALIZATION=1 python3 rlhf_async_new_apis.py
-  - popd
-
-- label: Distributed Tests (8 GPUs) # 4min
-  timeout_in_minutes: 10
-  gpu: h100
-  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:
-  # https://github.com/NVIDIA/nccl/issues/1838
-  - export NCCL_CUMEM_HOST_ENABLE=0
-  # test with torchrun tp=2 and dp=4 with ep
-  - 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
-  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
-  working_dir: "/vllm-workspace/tests"
-  num_gpus: 4
-  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]
-  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
-
-##### fast check tests  #####
-#####  1 GPU test  #####
-
-- label: Regression Test # 7min
-  timeout_in_minutes: 20
-  mirror_hardwares: [amdexperimental]
-  source_file_dependencies:
-  - vllm/
-  - tests/test_regression
-  commands:
-  - pip install modelscope
-  - pytest -v -s test_regression.py
-  working_dir: "/vllm-workspace/tests" # optional
-
-- label: Engine Test # 9min
-  timeout_in_minutes: 15
-  mirror_hardwares: [amdexperimental]
-  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 # 30min
-  timeout_in_minutes: 45
-  mirror_hardwares: [amdexperimental]
-  source_file_dependencies:
-    - vllm/
-    - tests/v1
-  commands:
-    # TODO: accuracy does not match, whether setting
-    # VLLM_USE_FLASHINFER_SAMPLER or not on H100.
-    - pytest -v -s v1/e2e
-    # Run this test standalone for now;
-    # need to untangle use (implicit) use of spawn/fork across the tests.
-    - pytest -v -s v1/engine/test_preprocess_error_handling.py
-    - pytest -v -s v1/engine --ignore v1/engine/test_preprocess_error_handling.py
-
-- label: V1 Test entrypoints # 35min
-  timeout_in_minutes: 50
-  mirror_hardwares: [amdexperimental]
-  source_file_dependencies:
-    - vllm/
-    - tests/v1
-  commands:
-    - pytest -v -s v1/entrypoints
-
-- label: V1 Test others # 42min
-  timeout_in_minutes: 60
-  mirror_hardwares: [amdexperimental]
-  source_file_dependencies:
-    - vllm/
-    - tests/v1
-  commands:
-    - uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt
-    # split the test to avoid interference
-    - 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 -m 'not slow_test' 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
-    # Integration test for streaming correctness (requires special branch).
-    - 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
-  gpu: h100
-  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
-  gpu: h100
-  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 attention (B200) # 10min
-  timeout_in_minutes: 30
-  gpu: b200
-  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: V1 Test others (CPU) # 5 mins
-  source_file_dependencies:
-    - vllm/
-    - tests/v1
-  no_gpu: true
-  commands:
-    # split the test to avoid interference
-    - 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]
-  working_dir: "/vllm-workspace/examples"
-  source_file_dependencies:
-  - vllm/entrypoints
-  - vllm/multimodal
-  - examples/
-  commands:
-    - pip install tensorizer # for tensorizer test
-    # for basic
-    - 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
-    # for multi-modal models
-    - 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
-    # for pooling models
-    - python3 pooling/embed/vision_embedding_offline.py --seed 0
-    # for features demo
-    - 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
-    # https://github.com/vllm-project/vllm/pull/26682 uses slightly more memory in PyTorch 2.9+ causing this test to OOM in 1xL4 GPU
-    - 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]
-  source_file_dependencies:
-  - vllm/
-  - tests/cuda
-  commands:
-    - pytest -v -s cuda/test_cuda_context.py
-
-- label: Samplers Test # 56min
-  timeout_in_minutes: 75
-  mirror_hardwares: [amdexperimental]
-  source_file_dependencies:
-  - vllm/model_executor/layers
-  - vllm/sampling_metadata.py
-  - tests/samplers
-  - tests/conftest.py
-  commands:
-    - pytest -v -s samplers
-    - VLLM_USE_FLASHINFER_SAMPLER=1 pytest -v -s samplers
-
-- label: LoRA Test %N # 20min each
-  timeout_in_minutes: 30
-  mirror_hardwares: [amdexperimental]
-  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
-
-  parallelism: 4
-
-- label: PyTorch Compilation Unit Tests # 15min
-  timeout_in_minutes: 30
-  mirror_hardwares: [amdexperimental]
-  torch_nightly: true
-  source_file_dependencies:
-    - vllm/
-    - tests/compile
-  commands:
-  # Run unit tests defined directly under compile/,
-  # not including subdirectories, which are usually heavier
-  # tests covered elsewhere.
-  # Use `find` to launch multiple instances of pytest so that
-  # they do not suffer from https://github.com/vllm-project/vllm/issues/28965
-  # However, find does not normally propagate error codes, so we combine it with xargs
-  # (using -0 for proper path handling)
-  - "find compile/ -maxdepth 1 -name 'test_*.py' -print0 | xargs -0 -n1 -I{} pytest -s -v '{}'"
-  - pytest -s -v compile/passes --ignore compile/passes/distributed
-
-- label: PyTorch Fullgraph Smoke Test # 15min
-  timeout_in_minutes: 30
-  mirror_hardwares: [amdexperimental]
-  torch_nightly: true
-  source_file_dependencies:
-  - vllm/
-  - tests/compile
-  commands:
-  # Run smoke tests under fullgraph directory, except test_full_graph.py
-  # as it is a heavy test that is covered in other steps.
-  # Use `find` to launch multiple instances of pytest so that
-  # they do not suffer from https://github.com/vllm-project/vllm/issues/28965
-  # However, find does not normally propagate error codes, so we combine it with xargs
-  # (using -0 for proper path handling)
-  - "find compile/fullgraph -maxdepth 1 -name 'test_*.py' -not -name 'test_full_graph.py' -print0 | xargs -0 -n1 -I{} pytest -s -v '{}'"
-
-- label: PyTorch Fullgraph Test # 27min
-  timeout_in_minutes: 40
-  mirror_hardwares: [amdexperimental]
-  torch_nightly: true
-  source_file_dependencies:
-  - vllm/
-  - tests/compile
-  commands:
-    # fp8 kv scales not supported on sm89, tested on Blackwell instead
-  - pytest -v -s compile/fullgraph/test_full_graph.py -k 'not test_fp8_kv_scale_compile'
-    # # Limit to no custom ops to reduce running time
-    # # Wrap with quotes to escape yaml and avoid starting -k string with a -
-    # - "pytest -v -s compile/distributed/test_fusions_e2e.py -k 'TRITON and not +quant_fp8 and not Llama-4'"
-    # Old E2E tests were removed in https://github.com/vllm-project/vllm/pull/33293
-    # in favor of new tests in fusions_e2e. We avoid replicating the new jobs in this file as it's deprecated.
-
-- label: Cudagraph test
-  timeout_in_minutes: 20
-  mirror_hardwares: [amdexperimental]
-  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]
-  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]
-  source_file_dependencies:
-  - csrc/attention/
-  - vllm/v1/attention
-    # TODO: remove this dependency (https://github.com/vllm-project/vllm/issues/32267)
-  - 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
-  parallelism: 2
-
-- label: Kernels Quantization Test %N # 64min
-  timeout_in_minutes: 90
-  mirror_hardwares: [amdexperimental]
-  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
-  parallelism: 2
-
-- label: Kernels MoE Test %N # 40min
-  timeout_in_minutes: 60
-  mirror_hardwares: [amdexperimental]
-  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
-  parallelism: 2
-
-- label: Kernels Mamba Test # 31min
-  timeout_in_minutes: 45
-  mirror_hardwares: [amdexperimental]
-  source_file_dependencies:
-  - csrc/mamba/
-  - tests/kernels/mamba
-  - vllm/model_executor/layers/mamba/ops
-  commands:
-    - pytest -v -s kernels/mamba
-
-- label: Kernels DeepGEMM Test (H100)
-  timeout_in_minutes: 45
-  gpu: h100
-  num_gpus: 1
-  source_file_dependencies:
-  - tools/install_deepgemm.sh
-  - vllm/utils/deep_gemm.py
-  - vllm/model_executor/layers/fused_moe
-  - vllm/model_executor/layers/quantization
-  - tests/kernels/quantization/test_block_fp8.py
-  - tests/kernels/moe/test_deepgemm.py
-  - tests/kernels/moe/test_batched_deepgemm.py
-  - tests/kernels/attention/test_deepgemm_attention.py
-  commands:
-    - pytest -v -s kernels/quantization/test_block_fp8.py -k deep_gemm
-    - pytest -v -s kernels/moe/test_deepgemm.py
-    - pytest -v -s kernels/moe/test_batched_deepgemm.py
-    - pytest -v -s kernels/attention/test_deepgemm_attention.py
-
-- label: Kernels Helion Test
-  timeout_in_minutes: 30
-  gpu: h100
-  source_file_dependencies:
-  - vllm/utils/import_utils.py
-  - tests/kernels/helion/
-  commands:
-    - pip install helion
-    - pytest -v -s kernels/helion/
-
-  
-- label: Kernels FP8 MoE Test (1 H100)
-  timeout_in_minutes: 90
-  gpu: h100
-  num_gpus: 1
-  optional: true
-  commands:
-    - pytest -v -s kernels/moe/test_cutlass_moe.py
-    - pytest -v -s kernels/moe/test_flashinfer.py
-    - pytest -v -s kernels/moe/test_gpt_oss_triton_kernels.py
-    - pytest -v -s kernels/moe/test_modular_oai_triton_moe.py
-    - pytest -v -s kernels/moe/test_moe.py
-    # - pytest -v -s kernels/moe/test_block_fp8.py - failing on main
-    - pytest -v -s kernels/moe/test_block_int8.py
-    - 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)
-  timeout_in_minutes: 90
-  gpu: h100
-  num_gpus: 2
-  optional: true
-  commands:
-    - pytest -v -s kernels/moe/test_deepep_deepgemm_moe.py
-    - pytest -v -s kernels/moe/test_deepep_moe.py
-    - pytest -v -s kernels/moe/test_pplx_cutlass_moe.py
-    # - pytest -v -s kernels/moe/test_pplx_moe.py - failing on main
-  
-- label: Kernels Fp4 MoE Test (B200)
-  timeout_in_minutes: 60
-  gpu: b200
-  num_gpus: 1
-  optional: true
-  commands:
-    - pytest -v -s kernels/moe/test_cutedsl_moe.py
-    - pytest -v -s kernels/moe/test_flashinfer_moe.py
-    - pytest -v -s kernels/moe/test_nvfp4_moe.py
-    - pytest -v -s kernels/moe/test_ocp_mx_moe.py
-
-
-- label: Model Executor Test # 23min
-  timeout_in_minutes: 35
-  torch_nightly: true
-  mirror_hardwares: [amdexperimental]
-  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]
-  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]
-  source_file_dependencies:
-  - vllm/
-  - tests/benchmarks/
-  commands:
-  - pytest -v -s benchmarks/
-
-- label: Quantization Test # 70min
-  timeout_in_minutes: 90
-  mirror_hardwares: [amdexperimental]
-  source_file_dependencies:
-  - csrc/
-  - vllm/model_executor/layers/quantization
-  - tests/quantization
-  commands:
-  # temporary install here since we need nightly, will move to requirements/test.in
-  # after torchao 0.12 release, and pin a working version of torchao nightly here
-
-  # since torchao nightly is only compatible with torch nightly currently
-  # https://github.com/pytorch/ao/issues/2919, we'll have to skip new torchao tests for now
-  # we can only upgrade after this is resolved
-  # TODO(jerryzh168): resolve the above comment
-  - uv pip install --system torchao==0.14.1 --index-url https://download.pytorch.org/whl/cu129
-  - 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]
-  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 # 22min
-  timeout_in_minutes: 30
-  mirror_hardwares: [amdexperimental]
-  source_file_dependencies:
-  - csrc/
-  - vllm/entrypoints/openai/
-  - vllm/model_executor/models/whisper.py
-  commands: # LMEval+Transcription WER check
-  - pytest -s entrypoints/openai/correctness/
-
-#####  models test  #####
-
-- label: Basic Models Tests (Initialization)
-  timeout_in_minutes: 45
-  mirror_hardwares: [amdexperimental]
-  torch_nightly: true
-  source_file_dependencies:
-  - vllm/
-  - tests/models/test_initialization.py
-  - tests/models/registry.py
-  commands:
-    # Run a subset of model initialization tests
-    - pytest -v -s models/test_initialization.py::test_can_initialize_small_subset
-
-- label: Basic Models Tests (Extra Initialization) %N
-  timeout_in_minutes: 45
-  mirror_hardwares: [amdexperimental]
-  torch_nightly: true
-  source_file_dependencies:
-  - vllm/model_executor/models/
-  - vllm/transformers_utils/
-  - tests/models/test_initialization.py
-  - tests/models/registry.py
-  commands:
-    # Only when vLLM model source is modified - test initialization of a large
-    # subset of supported models (the complement of the small subset in the above
-    # test.) Also run if model initialization test file is modified
-    - 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
-  parallelism: 2
-
-- label: Basic Models Tests (Other)
-  timeout_in_minutes: 45
-  mirror_hardwares: [amdexperimental]
-  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
-  torch_nightly: true
-  source_file_dependencies:
-  - vllm/
-  - tests/models/test_utils.py
-  - tests/models/test_vision.py
-  no_gpu: true
-  commands:
-    - pytest -v -s models/test_utils.py models/test_vision.py
-
-- label: Language Models Tests (Standard)
-  timeout_in_minutes: 25
-  mirror_hardwares: [amdexperimental]
-  torch_nightly: true
-  source_file_dependencies:
-  - vllm/
-  - tests/models/language
-  commands:
-    # Test standard language models, excluding a subset of slow tests
-    - pip freeze | grep -E 'torch'
-    - pytest -v -s models/language -m 'core_model and (not slow_test)'
-
-- label: Language Models Tests (Extra Standard) %N
-  timeout_in_minutes: 45
-  mirror_hardwares: [amdexperimental]
-  torch_nightly: true
-  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:
-    # Shard slow subset of standard language models tests. Only run when model
-    # source is modified, or when specified test files are modified
-    - pip freeze | grep -E 'torch'
-    - pytest -v -s models/language -m 'core_model and slow_test' \
-             --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT \
-             --shard-id=$$BUILDKITE_PARALLEL_JOB
-  parallelism: 2
-
-- label: Language Models Tests (Hybrid) %N
-  timeout_in_minutes: 75
-  mirror_hardwares: [amdexperimental]
-  torch_nightly: true
-  source_file_dependencies:
-  - vllm/
-  - tests/models/language/generation
-  commands:
-    # Install fast path packages for testing against transformers
-    # Note: also needed to run plamo2 model in vLLM
-    - uv pip install --system --no-build-isolation 'git+https://github.com/state-spaces/mamba@v2.3.0'
-    - uv pip install --system --no-build-isolation 'git+https://github.com/Dao-AILab/causal-conv1d@v1.5.2'
-    # Shard hybrid language model tests
-    - pytest -v -s models/language/generation \
-                   -m hybrid_model \
-                   --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT \
-                   --shard-id=$$BUILDKITE_PARALLEL_JOB
-  parallelism: 2
-
-- label: Language Models Test (Extended Generation) # 80min
-  timeout_in_minutes: 110
-  mirror_hardwares: [amdexperimental]
-  optional: true
-  source_file_dependencies:
-  - vllm/
-  - tests/models/language/generation
-  commands:
-    # Install fast path packages for testing against transformers
-    # Note: also needed to run plamo2 model in vLLM
-    - uv pip install --system --no-build-isolation 'git+https://github.com/state-spaces/mamba@v2.3.0'
-    - 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)
-  timeout_in_minutes: 110
-  mirror_hardwares: [amdexperimental]
-  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]
-  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)
-  timeout_in_minutes: 110
-  mirror_hardwares: [amdexperimental]
-  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)
-  timeout_in_minutes: 60
-  source_file_dependencies:
-  - vllm/
-  - tests/models/multimodal
-  no_gpu: true
-  commands:
-    - "pip install git+https://github.com/TIGER-AI-Lab/Mantis.git || echo 'Mantis installation skipped (decord not available on CPU-only environment)'"
-    - pytest -v -s models/multimodal/processing --ignore models/multimodal/processing/test_tensor_schema.py
-
-- label: Multi-Modal Processor Test
-  timeout_in_minutes: 60
-  source_file_dependencies:
-  - vllm/
-  - tests/models/multimodal
-  commands:
-    - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
-    - pytest -v -s models/multimodal/processing/test_tensor_schema.py
-
-- label: Multi-Modal Models Test (Standard) # 60min
-  timeout_in_minutes: 80
-  mirror_hardwares: [amdexperimental]
-  torch_nightly: true
-  source_file_dependencies:
-  - vllm/
-  - tests/models/multimodal
-  commands:
-    - 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
-    - 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) # 50min
-  timeout_in_minutes: 70
-  working_dir: "/vllm-workspace/.buildkite/lm-eval-harness"
-  source_file_dependencies:
-  - vllm/multimodal/
-  - vllm/inputs/
-  - vllm/v1/core/
-  commands:
-  - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-mm-small.txt --tp-size=1
-
-- label: Multi-Modal Models Test (Extended) 1
-  mirror_hardwares: [amdexperimental]
-  optional: true
-  source_file_dependencies:
-  - vllm/
-  - tests/models/multimodal
-  commands:
-    - 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
-  mirror_hardwares: [amdexperimental]
-  optional: true
-  source_file_dependencies:
-  - vllm/
-  - tests/models/multimodal
-  commands:
-    - 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
-  mirror_hardwares: [amdexperimental]
-  optional: true
-  source_file_dependencies:
-  - vllm/
-  - tests/models/multimodal
-  commands:
-    - 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]
-  source_file_dependencies:
-  - vllm/model_executor/layers/quantization
-  - tests/models/quantization
-  commands:
-    - pytest -v -s models/quantization
-
-# This test is used only in PR development phase to test individual models and should never run on main
-- label: Custom Models Test
-  mirror_hardwares: [amdexperimental]
-  optional: true
-  commands:
-    - echo 'Testing custom models...'
-    # PR authors can temporarily add commands below to test individual models
-    # e.g. pytest -v -s models/encoder_decoder/vision_language/test_mllama.py
-    # *To avoid merge conflicts, remember to REMOVE (not just comment out) them before merging the PR*
-
-- label: Transformers Nightly Models Test
-  working_dir: "/vllm-workspace/"
-  optional: true
-  soft_fail: true
-  commands:
-    - pip install --upgrade git+https://github.com/huggingface/transformers
-    - pytest -v -s tests/models/test_initialization.py
-    - pytest -v -s tests/models/test_transformers.py
-    - pytest -v -s tests/models/multimodal/processing/
-    - pytest -v -s tests/models/multimodal/test_mapping.py
-    - python3 examples/offline_inference/basic/chat.py
-    - python3 examples/offline_inference/vision_language.py --model-type qwen2_5_vl
-    # Whisper needs spawn method to avoid deadlock
-    - VLLM_WORKER_MULTIPROC_METHOD=spawn python3 examples/offline_inference/audio_language.py --model-type whisper
-
-- label: Blackwell Test # 23 min
-  timeout_in_minutes: 30
-  working_dir: "/vllm-workspace/"
-  gpu: b200
-  source_file_dependencies:
-  - csrc/quantization/fp4/
-  - csrc/attention/mla/
-  - csrc/quantization/cutlass_w8a8/moe/
-  - vllm/model_executor/layers/fused_moe/cutlass_moe.py
-  - vllm/model_executor/layers/fused_moe/flashinfer_cutlass_moe.py
-  - vllm/model_executor/layers/fused_moe/flashinfer_a2a_prepare_finalize.py
-  - vllm/model_executor/layers/quantization/utils/flashinfer_utils.py
-  - vllm/v1/attention/backends/flashinfer.py
-  - vllm/v1/attention/backends/mla/cutlass_mla.py
-  - vllm/v1/attention/backends/mla/flashinfer_mla.py
-  - vllm/v1/attention/selector.py
-  - vllm/platforms/cuda.py
-  commands:
-    - nvidia-smi
-    - python3 examples/offline_inference/basic/chat.py
-    # Attention
-    # num_heads2 broken by https://github.com/flashinfer-ai/flashinfer/issues/1353
-    - pytest -v -s tests/kernels/attention/test_attention_selector.py
-    - pytest -v -s tests/kernels/attention/test_flashinfer.py -k 'not num_heads2'
-    - pytest -v -s tests/kernels/attention/test_flashinfer_trtllm_attention.py
-    - pytest -v -s tests/kernels/attention/test_cutlass_mla_decode.py
-    - pytest -v -s tests/kernels/attention/test_flashinfer_mla_decode.py
-    # Quantization
-    - pytest -v -s tests/kernels/quantization/test_cutlass_scaled_mm.py -k 'fp8'
-    - pytest -v -s tests/kernels/quantization/test_nvfp4_quant.py
-    - pytest -v -s tests/kernels/quantization/test_silu_mul_nvfp4_quant.py
-    - pytest -v -s tests/kernels/quantization/test_nvfp4_scaled_mm.py
-    - pytest -v -s tests/kernels/quantization/test_flashinfer_scaled_mm.py
-    - pytest -v -s tests/kernels/quantization/test_flashinfer_nvfp4_scaled_mm.py
-    - pytest -v -s tests/kernels/quantization/test_nvfp4_qutlass.py
-    - pytest -v -s tests/kernels/quantization/test_mxfp4_qutlass.py
-    - pytest -v -s tests/kernels/moe/test_nvfp4_moe.py
-    - pytest -v -s tests/kernels/moe/test_ocp_mx_moe.py
-    - pytest -v -s tests/kernels/moe/test_flashinfer.py
-    - pytest -v -s tests/kernels/moe/test_cutedsl_moe.py
-    # e2e
-    - pytest -v -s tests/models/quantization/test_nvfp4.py
-
-- label: Blackwell Fusion and Compile Tests # 30 min
-  timeout_in_minutes: 40
-  working_dir: "/vllm-workspace/"
-  gpu: b200
-  source_file_dependencies:
-  - csrc/quantization/fp4/
-  - vllm/model_executor/layers/quantization/utils/flashinfer_utils.py
-  - vllm/v1/attention/backends/flashinfer.py
-  - vllm/v1/worker/
-  - vllm/v1/cudagraph_dispatcher.py
-  - vllm/compilation/
-  # can affect pattern matching
-  - vllm/model_executor/layers/layernorm.py
-  - vllm/model_executor/layers/activation.py
-  - vllm/model_executor/layers/quantization/input_quant_fp8.py
-  - tests/compile/test_fusion_attn.py
-  - tests/compile/test_silu_mul_quant_fusion.py
-  - tests/compile/passes/distributed/test_fusion_all_reduce.py
-  - tests/compile/fullgraph/test_full_graph.py
-  commands:
-    - nvidia-smi
-    - pytest -v -s tests/compile/test_fusion_attn.py
-    - pytest -v -s tests/compile/test_silu_mul_quant_fusion.py
-    # this runner has 2 GPUs available even though num_gpus=2 is not set
-    - pytest -v -s tests/compile/passes/distributed/test_fusion_all_reduce.py
-    #  # Limit to Inductor partition, no custom ops, and allreduce & attn fusion to reduce running time
-    #  # Wrap with quotes to escape yaml
-    #  - "pytest -v -s tests/compile/distributed/test_fusions_e2e.py::test_tp2_attn_quant_allreduce_rmsnorm -k 'True and not +quant_fp8 and not +rms_norm'"
-    # Old E2E tests were removed in https://github.com/vllm-project/vllm/pull/33293
-    # in favor of new tests in fusions_e2e. We avoid replicating the new jobs in this file as it's deprecated.
-
-    # test_fp8_kv_scale_compile requires FlashAttention (not supported on default L4/L40)
-    - pytest -v -s tests/compile/fullgraph/test_full_graph.py::test_fp8_kv_scale_compile
-
-- label: Blackwell GPT-OSS Eval
-  timeout_in_minutes: 60
-  working_dir: "/vllm-workspace/"
-  gpu: b200
-  optional: true # run on nightlies
-  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'
-    - pytest -s -v tests/evals/gpt_oss/test_gpqa_correctness.py --model openai/gpt-oss-20b --metric 0.58
-
-- label: Blackwell Quantized MoE Test
-  timeout_in_minutes: 60
-  working_dir: "/vllm-workspace/"
-  gpu: b200
-  source_file_dependencies:
-  - tests/quantization/test_blackwell_moe.py
-  - vllm/model_executor/models/deepseek_v2.py
-  - vllm/model_executor/models/gpt_oss.py
-  - vllm/model_executor/models/llama4.py
-  - vllm/model_executor/layers/fused_moe
-  - vllm/model_executor/layers/quantization/compressed_tensors
-  - vllm/model_executor/layers/quantization/modelopt.py
-  - vllm/model_executor/layers/quantization/mxfp4.py
-  - vllm/v1/attention/backends/flashinfer.py
-  commands:
-    - pytest -s -v tests/quantization/test_blackwell_moe.py
-
-- label: Blackwell LM Eval Small Models
-  timeout_in_minutes: 120
-  gpu: b200
-  optional: true # run on nightlies
-  source_file_dependencies:
-  - csrc/
-  - vllm/model_executor/layers/quantization
-  commands:
-  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt
-
-#####  1 GPU test  #####
-#####  multi gpus test  #####
-
-- label: Distributed Comm Ops Test # 7min
-  timeout_in_minutes: 20
-  mirror_hardwares: [amdexperimental]
-  working_dir: "/vllm-workspace/tests"
-  num_gpus: 2
-  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
-  - pytest -v -s distributed/test_packed_tensor.py
-  - pytest -v -s distributed/test_weight_transfer.py
-
-- label: 2 Node Tests (4 GPUs in total) # 16min
-  timeout_in_minutes: 30
-  mirror_hardwares: [amdexperimental]
-  working_dir: "/vllm-workspace/tests"
-  num_gpus: 2
-  num_nodes: 2
-  source_file_dependencies:
-  - vllm/distributed/
-  - vllm/engine/
-  - vllm/executor/
-  - vllm/model_executor/models/
-  - tests/distributed/
-  - tests/examples/offline_inference/data_parallel.py
-  - .buildkite/scripts/run-multi-node-test.sh
-  commands:
-  - # the following commands are for the first node, with ip 192.168.10.10 (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 | grep 'Same node test passed'
-    - NUM_NODES=2 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_node_count.py | grep 'Node count test passed'
-    - 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 | grep 'Same node test passed'
-    - NUM_NODES=2 torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=192.168.10.10 distributed/test_node_count.py | grep 'Node count test passed'
-    - 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]
-  working_dir: "/vllm-workspace/tests"
-  num_gpus: 2
-  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
-  commands:
-  # https://github.com/NVIDIA/nccl/issues/1838
-  - export NCCL_CUMEM_HOST_ENABLE=0
-  - 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'
-  - pytest -v -s distributed/test_sequence_parallel.py
-  - 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]
-  working_dir: "/vllm-workspace/tests"
-  num_gpus: 2
-  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
-  # Avoid importing model tests that cause CUDA reinitialization error
-  - 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]
-  working_dir: "/vllm-workspace/tests"
-  num_gpus: 2
-  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
-  # 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 # it needs a clean process
-  - pytest -v -s models/test_oot_registration.py # it needs a clean process
-  - pytest -v -s plugins/lora_resolvers # unit tests for lora resolver plugins
-
-- label: Pipeline + Context Parallelism Test # 45min
-  timeout_in_minutes: 60
-  mirror_hardwares: [amdexperimental]
-  working_dir: "/vllm-workspace/tests"
-  num_gpus: 4
-  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]
-  num_gpus: 4
-  source_file_dependencies:
-  - vllm/lora
-  - tests/lora
-  commands:
-    # FIXIT: find out which code initialize cuda before running the test
-    # before the fix, we need to use spawn to test it
-    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-    # Alot of these tests are on the edge of OOMing
-    - export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
-    # There is some Tensor Parallelism related processing logic in LoRA that
-    # requires multi-GPU testing for validation.
-    - 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
-    - pytest -v -s -x lora/test_gptoss_tp.py
-
-
-- label: Weight Loading Multiple GPU Test  # 33min
-  timeout_in_minutes: 45
-  mirror_hardwares: [amdexperimental]
-  working_dir: "/vllm-workspace/tests"
-  num_gpus: 2
-  optional: true
-  source_file_dependencies:
-  - vllm/
-  - tests/weight_loading
-  commands:
-    - bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models.txt
-
-- label: Weight Loading Multiple GPU Test - Large Models # optional
-  mirror_hardwares: [amdexperimental]
-  working_dir: "/vllm-workspace/tests"
-  num_gpus: 2
-  gpu: a100
-  optional: true
-  source_file_dependencies:
-  - vllm/
-  - tests/weight_loading
-  commands:
-    - bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models-large.txt
-
-- label: NixlConnector PD accuracy tests (Distributed) # 40min
-  timeout_in_minutes: 40
-  working_dir: "/vllm-workspace/tests"
-  num_gpus: 4
-  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.txt
-    - bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
-
-- label: DP EP NixlConnector PD accuracy tests (Distributed) # 15min
-  timeout_in_minutes: 15
-  working_dir: "/vllm-workspace/tests"
-  num_gpus: 4
-  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.txt
-    - DP_EP=1 bash v1/kv_connector/nixl_integration/config_sweep_accuracy_test.sh
-
-
-##### multi gpus test #####
-##### A100 test #####
-
-- label: Distributed Tests (A100) # optional
-  gpu: a100
-  optional: true
-  num_gpus: 4
-  source_file_dependencies:
-  - vllm/
-  commands:
-  # NOTE: don't test llama model here, it seems hf implementation is buggy
-  # see https://github.com/vllm-project/vllm/pull/5689 for details
-  - 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: Acceptance Length Test (Large Models) # optional
-  timeout_in_minutes: 120
-  gpu: h100
-  optional: true
-  num_gpus: 1
-  working_dir: "/vllm-workspace/tests"
-  source_file_dependencies:
-  - vllm/v1/spec_decode/
-  - vllm/model_executor/models/mlp_speculator.py
-  - tests/v1/spec_decode/test_acceptance_length.py
-  commands:
-    - export VLLM_ALLOW_INSECURE_SERIALIZATION=1
-    - pytest -v -s v1/spec_decode/test_acceptance_length.py -m slow_test
-
-- label: LM Eval Large Models # optional
-  gpu: a100
-  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
-
-##### H100 test #####
-- label: LM Eval Large Models (H100) # optional
-  gpu: h100
-  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  # 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: Sequence Parallel Tests (H100) # 60 min
-  timeout_in_minutes: 60
-  working_dir: "/vllm-workspace/"
-  gpu: h100
-  optional: true
-  num_gpus: 2
-  commands:
-    - export VLLM_TEST_CLEAN_GPU_MEMORY=1
-    # Run sequence parallel tests
-    - pytest -v -s tests/compile/correctness_e2e/test_sequence_parallel.py
-    - pytest -v -s tests/compile/passes/distributed/test_sequence_parallelism.py
-
-- label: Distributed Tests (H100) # optional
-  gpu: h100
-  optional: true
-  working_dir: "/vllm-workspace/"
-  num_gpus: 2
-  commands:
-    - VLLM_TEST_CLEAN_GPU_MEMORY=1 pytest -v -s tests/compile/passes/distributed/test_async_tp.py
-    - pytest -v -s tests/distributed/test_context_parallel.py
-    - VLLM_USE_DEEP_GEMM=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=deepep_high_throughput
-    - pytest -v -s tests/v1/distributed/test_dbo.py
-
-##### H200 test #####
-
-- label: LM Eval Large Models (H200) # optional
-  timeout_in_minutes: 60
-  gpu: h200
-  optional: true
-  num_gpus: 8
-  commands:
-    - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-h200.txt
-
-##### B200 test #####
-- label: Distributed Tests (B200) # optional
-  gpu: b200
-  optional: true
-  working_dir: "/vllm-workspace/"
-  num_gpus: 2
-  commands:
-    - pytest -v -s tests/distributed/test_context_parallel.py
-    - pytest -v -s tests/distributed/test_nccl_symm_mem_allreduce.py
-    - pytest -v -s tests/v1/distributed/test_dbo.py
-
-##### RL Integration Tests #####
-- label: Prime-RL Integration Test # 15min
-  timeout_in_minutes: 30
-  optional: true
-  soft_fail: true
-  num_gpus: 2
-  working_dir: "/vllm-workspace"
-  source_file_dependencies:
-  - vllm/
-  - .buildkite/scripts/run-prime-rl-test.sh
-  commands:
-    - nvidia-smi
-    - bash .buildkite/scripts/run-prime-rl-test.sh
-
-- label: DeepSeek V2-Lite Accuracy
-  timeout_in_minutes: 60
-  gpu: h100
-  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: Qwen3-30B-A3B-FP8-block Accuracy (H100)
-  timeout_in_minutes: 60
-  gpu: h100
-  optional: true
-  num_gpus: 4
-  working_dir: "/vllm-workspace"
-  commands:
-  - bash .buildkite/scripts/scheduled_integration_test/qwen30b_a3b_fp8_block_ep_eplb.sh 0.8 200 8020
-
-- label: Qwen3-30B-A3B-FP8-block Accuracy (B200)
-  timeout_in_minutes: 60
-  gpu: b200
-  optional: true
-  num_gpus: 2
-  working_dir: "/vllm-workspace"
-  commands:
-  - bash .buildkite/scripts/scheduled_integration_test/qwen30b_a3b_fp8_block_ep_eplb.sh 0.8 200 8020 2 1
-
-##### MoE Refactor (Temporary) Tests #####
-
-- label: MoE Refactor Integration Test (H100 - TEMPORARY) # optional
-  gpu: h100
-  optional: true
-  num_gpus: 2
-  commands:
-    - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/moe-refactor/config-h100.txt
-  
-- label: MoE Refactor Integration Test (B200 - TEMPORARY) # optional
-  gpu: b200
-  optional: true
-  num_gpus: 2
-  commands:
-    - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/moe-refactor/config-b200.txt
-
-- label: MoE Refactor Integration Test (B200 DP - TEMPORARY) # optional
-  gpu: b200
-  optional: true
-  num_gpus: 2
-  commands:
-    - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/moe-refactor-dp-ep/config-b200.txt
+# If you need to make changes to CI, please find the relevant file in these directories and make changes there.