vLLM/.buildkite/test_areas/models_basic.yaml

group: Models - Basic
depends_on:
  - image-build
steps:
- label: ":nvidia: (H200 MIG 18GB) Basic Models (Initialization)"
  key: basic-models-tests-initialization
  timeout_in_minutes: 25
  device: h200_18gb
  source_file_dependencies:
  - vllm/
  - "!vllm/distributed/kv_transfer/"
  - 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
  mirror:
    amd:
      label: ":amd: (MI355 DPX) Basic Models (Initialization)"
      dind: false
      device: mi355_dpx
      timeout_in_minutes: 30
      depends_on:
      - image-build-amd

- label: ":nvidia: (H200 MIG 35GB) Basic Models (Extra Initialization) Shard %N"
  device: h200_35gb
  key: basic-models-tests-extra-initialization
  timeout_in_minutes: 30
  source_file_dependencies:
  - vllm/model_executor/models/
  - 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: 14
  mirror:
    amd:
      label: ":amd: (MI355 DPX) Basic Models (Extra Initialization) Shard %N"
      dind: false
      device: mi355_dpx
      timeout_in_minutes: 60
      parallelism: 10
      working_dir: "/vllm-workspace/tests"
      depends_on:
      - image-build-amd
      source_file_dependencies:
      - vllm/model_executor/models/
      - vllm/model_executor/layers/
      - tests/models/test_initialization.py
      - tests/models/registry.py
      - vllm/_aiter_ops.py
      - vllm/platforms/rocm.py

- label: ":nvidia: (H200 MIG 35GB) Basic Models (Other)"
  device: h200_35gb
  key: basic-models-tests-other
  automatic_shard: true
  timeout_in_minutes: 38
  source_file_dependencies:
  - vllm/
  - "!vllm/distributed/kv_transfer/"
  - tests/models/test_terratorch.py
  - tests/models/transformers/test_backend.py
  - tests/models/test_registry.py
  - tests/models/test_deepseek_v4_vl_rocm.py
  - tests/models/test_deepseek_v41_decoder_replay_layers.py
  - tests/models/test_deepseek_v41_replay_batch.py
  - tests/models/test_deepseek_v41_pcp.py
  - tests/models/transformers/test_layer_registry_e2e.py
  - tests/models/test_deepseek_v41_replay_start.py
  - tests/models/test_deepseek_v4_vl_stream_weights.py
  commands:
    - pytest -v -s models/test_terratorch.py models/transformers/test_backend.py models/test_registry.py models/test_deepseek_v4_vl_rocm.py models/transformers/test_layer_registry_e2e.py models/test_deepseek_v41_replay_start.py models/test_deepseek_v41_decoder_replay_layers.py models/test_deepseek_v41_replay_batch.py models/test_deepseek_v41_pcp.py models/test_deepseek_v4_vl_stream_weights.py
  mirror:
    amd:
      label: ":amd: (MI355) Basic Models (Other)"
      dind: false
      device: mi355_1
      timeout_in_minutes: 65
      depends_on:
      - image-build-amd
      source_file_dependencies:
      - vllm/models/deepseek_v4/
      - vllm/models/deepseek_v41/
      - tests/models/test_deepseek_v4_vl_rocm.py
      - tests/models/test_hyv4_rocm.py
      - tests/models/transformers/test_layer_registry_e2e.py
      - tests/models/test_deepseek_v41_replay_start.py
      - tests/models/test_deepseek_v41_decoder_replay_layers.py
      - tests/models/test_deepseek_v41_replay_batch.py
      - tests/models/test_deepseek_v41_amd_replay_forward.py
      - tests/models/test_deepseek_v4_dspark_rocm.py
      - tests/models/test_deepseek_v4_rocm_wo_a.py
      - tests/models/test_deepseek_v4_rocm_compressor_gemm_fusion.py
      - tests/models/test_dsv41_mono_decode.py
      commands:
      - pytest -v -s models/test_terratorch.py models/transformers/test_backend.py models/test_registry.py models/test_deepseek_v4_vl_rocm.py models/transformers/test_layer_registry_e2e.py models/test_deepseek_v41_replay_start.py models/test_deepseek_v41_decoder_replay_layers.py models/test_deepseek_v41_replay_batch.py models/test_deepseek_v41_amd_replay_forward.py models/test_deepseek_v4_dspark_rocm.py models/test_deepseek_v4_rocm_wo_a.py models/test_deepseek_v4_rocm_compressor_gemm_fusion.py models/test_dsv41_mono_decode.py
      - VLLM_ROCM_USE_AITER=1 pytest -v -s models/test_hyv4_rocm.py -m 'not distributed'

- label: ":nvidia: (B200) Inkling"
  key: inkling-unit-tests-b200
  timeout_in_minutes: 40
  device: b200-k8s
  source_file_dependencies:
  - vllm/models/inkling/
  - vllm/cute_utils/
  - cmake/external_projects/tml_fa4.cmake
  - tests/models/inkling/
  commands:
    # FA4 kernel tests require SM100; the suite skips them elsewhere.
    - pytest -v -s models/inkling
  mirror:
    amd:
      label: ":amd: (MI355) Inkling"
      dind: false
      device: mi355_1
      timeout_in_minutes: 65
      working_dir: "/vllm-workspace/tests"
      depends_on:
      - image-build-amd
      source_file_dependencies:
      - vllm/models/inkling/
      - vllm/cute_utils/
      - cmake/external_projects/tml_fa4.cmake
      - tests/models/inkling/
      - vllm/platforms/rocm.py
      commands:
      - pytest -v -s models/inkling/rocm

- label: ":nvidia: (B200) Kimi K3"
  key: kimi-k3-unit-tests-b200
  timeout_in_minutes: 40
  device: b200-k8s
  source_file_dependencies:
  - vllm/models/kimi_k3/
  - csrc/kimi_k3/
  - tests/models/kimi_k3/
  - tests/kernels/attention/test_kimi_k3_mla_fused_epilogue.py
  commands:
    # The native NVIDIA Kimi K3 kernels require the SM100 family.
    - pytest -v -s models/kimi_k3 --ignore=models/kimi_k3/test_prefix_cache.py kernels/attention/test_kimi_k3_mla_fused_epilogue.py
  mirror:
    amd:
      label: ":amd: (MI355) Kimi K3"
      dind: false
      device: mi355_1
      num_devices: 1
      timeout_in_minutes: 60
      working_dir: "/vllm-workspace/tests"
      depends_on:
      - image-build-amd
      source_file_dependencies:
      - vllm/platforms/rocm.py
      commands:
      # The ROCm KDA/AttnRes kernels are gated on gfx950, so this has to be MI355.
      # The kernels/ file the NVIDIA job adds is CUDA-only (it imports
      # cuda.bindings.driver), so it is deliberately left out here.
      - pytest -v -s models/kimi_k3

- label: ":nvidia: (4xB200) Kimi K3 Prefix Cache"
  key: kimi-k3-prefix-cache-4xb200
  # Nightly only: 4-GPU B200 pods wait hours behind smaller jobs on per-PR runs.
  optional: true
  automatic_shard: true
  timeout_in_minutes: 75
  device: b200-k8s
  num_devices: 4
  source_file_dependencies:
  - vllm/models/kimi_k3/
  - vllm/v1/core/
  - vllm/distributed/kv_transfer/kv_connector/v1/nixl/
  - vllm/distributed/kv_transfer/kv_connector/v1/simple_cpu_offload_connector.py
  - vllm/distributed/kv_transfer/kv_connector/v1/mooncake/store/
  - vllm/distributed/mooncake_store.py
  - vllm/v1/simple_kv_offload/
  - vllm/v1/spec_decode/
  - vllm/model_executor/layers/mamba/
  - tests/models/kimi_k3/test_prefix_cache.py
  - .buildkite/scripts/install-kv-connectors.sh
  commands:
  - bash /vllm-workspace/.buildkite/scripts/install-kv-connectors.sh
  - pytest -v -s models/kimi_k3/test_prefix_cache.py

- label: ":nvidia: (H200) GLM5Next"
  key: glm5next-unit-tests
  timeout_in_minutes: 20
  device: h200_35gb
  source_file_dependencies:
  - vllm/models/glm5next/
  - tests/models/glm5next/
  commands:
    - pytest -v -s models/glm5next
  mirror:
    amd:
      label: ":amd: (MI355 DPX) GLM5Next"
      dind: false
      device: mi355_dpx
      timeout_in_minutes: 35
      working_dir: "/vllm-workspace/tests"
      depends_on:
      - image-build-amd
      source_file_dependencies:
      - vllm/platforms/rocm.py

- label: ":nvidia: (H200) Qwen4 Exp"
  key: qwen4-exp-unit-tests
  timeout_in_minutes: 40
  device: h200_35gb
  source_file_dependencies:
  - vllm/models/qwen4_exp/
  - vllm/config/compilation.py
  - vllm/v1/attention/backends/short_conv_attn.py
  - tests/models/qwen4_exp/
  commands:
    - pytest -v -s models/qwen4_exp/test_hc_ops.py models/qwen4_exp/test_qsa_prepare.py models/qwen4_exp/test_qsa_reference.py
    - pytest -v -s models/qwen4_exp/test_ple.py
  mirror:
    amd:
      label: ":amd: (MI355 DPX) Qwen4 Exp"
      dind: false
      device: mi355_dpx
      depends_on:
      - image-build-amd
      commands:
      - pytest -v -s models/qwen4_exp/test_qsa_amd.py models/qwen4_exp/test_qsa_prepare_amd.py
      # PLE and QSA import conflicting HC registrations in a shared process.
      - pytest -v -s models/qwen4_exp/test_ple.py

- label: ":computer: (CPU) Qwen4 Exp"
  key: qwen4-exp-unit-tests-cpu
  depends_on:
  - image-build-cpu
  timeout_in_minutes: 20
  device: cpu-small
  source_file_dependencies:
  - vllm/models/qwen4_exp/
  - vllm/config/compilation.py
  - vllm/v1/attention/backends/short_conv_attn.py
  - tests/models/qwen4_exp/
  commands:
    - pytest -v -s models/qwen4_exp/test_config.py models/qwen4_exp/test_ple.py

- label: ":computer: (CPU) Basic Models Other"
  key: basic-models-test-other-cpu
  depends_on:
  - image-build-cpu
  timeout_in_minutes: 30
  source_file_dependencies:
  - vllm/
  - "!vllm/distributed/kv_transfer/"
  - tests/models/test_utils.py
  - tests/models/test_vision.py
  - tests/models/test_adapters.py
  - tests/models/test_qwen3_5_mtp_config.py
  - tests/models/test_alice_ai.py
  - tests/models/test_alice_ai_config.py
  - tests/models/transformers/fusers/
  - tests/models/transformers/test_dynamic_rope.py
  - tests/model_executor/layers/test_activation.py
  - tests/models/test_language_model_cache_is_weak.py
  - tests/models/deepseek_v32/test_sequence_parallel.py
  - tests/models/test_deepseek_v4_fi_moe_ep.py
  - tests/models/test_dspark_mla.py
  - tests/models/transformers/test_layer_registry.py
  device: cpu-small
  commands:
    - pytest -v -s models/test_utils.py models/test_vision.py models/test_adapters.py models/test_qwen3_5_mtp_config.py models/transformers/fusers/ models/transformers/test_dynamic_rope.py model_executor/layers/test_activation.py models/test_language_model_cache_is_weak.py models/deepseek_v32/test_sequence_parallel.py models/test_deepseek_v4_fi_moe_ep.py models/test_dspark_mla.py models/transformers/test_layer_registry.py models/test_alice_ai.py models/test_alice_ai_config.py

- label: ':amd: (MI355) DeepSeek-V4.1 Mono Decode Numerics'
  key: dsv41-mono-decode-numerics-amd
  dind: false
  device: mi355_4
  num_devices: 4
  timeout_in_minutes: 40
  working_dir: /vllm-workspace/
  depends_on:
  - image-build-amd
  source_file_dependencies:
  - docker/Dockerfile.rocm_base
  - vllm/models/deepseek_v41/amd/
  - tests/models/test_dsv41_mono_numerics.py
  - tests/models/test_dsv41_mono_layers.py
  commands:
  - pytest -v -s tests/models/test_dsv41_mono_numerics.py
  - pytest -v -s tests/models/test_dsv41_mono_layers.py