vLLM/.buildkite/intel_jobs/models_multimodal_intel.yaml

group: Models - Multimodal Intel
depends_on:
  - image-build-xpu
steps:
- label: ":intel: (BMG) Multi-Modal Models (Standard) 1: qwen2"
  key: multi-modal-models-standard-1-qwen2
  timeout_in_minutes: 70
  device: intel_gpu
  agent_tags:
    label: production
    gpu: 1+
    mem: 16+
  no_plugin: true
  working_dir: "."
  env:
    REGISTRY: "public.ecr.aws/q9t5s3a7"
    REPO: "vllm-ci-test-repo"
    VLLM_TEST_DEVICE: "xpu"
  source_file_dependencies:
  - vllm/
  - tests/models/multimodal
  commands:
    - >-
      bash .buildkite/scripts/hardware_ci/run-intel-test.sh
      'cd tests &&
      pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "qwen2" &&
      pytest -v -s models/multimodal/generation/test_ultravox.py -m core_model'

- label: ":intel: (BMG) Multi-Modal Models (Standard) 2: qwen3 + gemma"
  key: multi-modal-models-standard-2-qwen3-gemma
  timeout_in_minutes: 90
  device: intel_gpu
  agent_tags:
    label: production
    gpu: 1+
    mem: 16+
  no_plugin: true
  working_dir: "."
  env:
    REGISTRY: "public.ecr.aws/q9t5s3a7"
    REPO: "vllm-ci-test-repo"
    VLLM_TEST_DEVICE: "xpu"
  source_file_dependencies:
  - vllm/
  - tests/models/multimodal
  commands:
    - >-
      bash .buildkite/scripts/hardware_ci/run-intel-test.sh
      'cd tests &&
      pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "qwen3 or gemma" &&
      pytest -v -s models/multimodal/generation/test_mm_prefix_lm.py -m core_model &&
      pytest -v -s models/multimodal/generation/test_qwen2_5_vl.py -m core_model'

- label: ":intel: (BMG) Multi-Modal Models (Standard) 3: llava + qwen2_vl"
  key: multi-modal-models-standard-3-llava-qwen2-vl
  timeout_in_minutes: 65
  device: intel_gpu
  agent_tags:
    label: production
    gpu: 1+
    mem: 24+
  no_plugin: true
  working_dir: "."
  env:
    REGISTRY: "public.ecr.aws/q9t5s3a7"
    REPO: "vllm-ci-test-repo"
    VLLM_TEST_DEVICE: "xpu"
  source_file_dependencies:
  - vllm/
  - tests/models/multimodal
  commands:
    - >-
      bash .buildkite/scripts/hardware_ci/run-intel-test.sh
      'cd tests &&
      pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "not qwen2 and not qwen3 and not gemma" &&
      pytest -v -s models/multimodal/generation/test_gemma_ragged_audio.py -m core_model
      pytest -v -s models/multimodal/generation/test_qwen2_vl.py -m core_model'

- label: ":intel: (BMG) Multi-Modal Models (Standard) 4: other + whisper"
  key: multi-modal-models-standard-4-other-whisper
  timeout_in_minutes: 45
  device: intel_gpu
  agent_tags:
    label: production
    gpu: 1+
    mem: 16+
  no_plugin: true
  working_dir: "."
  env:
    REGISTRY: "public.ecr.aws/q9t5s3a7"
    REPO: "vllm-ci-test-repo"
    VLLM_TEST_DEVICE: "xpu"
  source_file_dependencies:
  - vllm/
  - tests/models/multimodal
  commands:
    - >-
      bash .buildkite/scripts/hardware_ci/run-intel-test.sh
      'cd tests &&
      pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/generation/test_ultravox.py --ignore models/multimodal/generation/test_qwen2_5_vl.py --ignore models/multimodal/generation/test_qwen2_vl.py --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/generation/test_gemma_ragged_audio.py --ignore models/multimodal/generation/test_memory_leak.py --ignore models/multimodal/processing'

- label: ":intel: (BMG) Multi-Modal Processor" # 44min
  key: multi-modal-processor
  timeout_in_minutes: 60
  device: intel_gpu
  agent_tags:
    label: production
    gpu: 1+
    mem: 24+
  no_plugin: true
  working_dir: "."
  env:
    REGISTRY: "public.ecr.aws/q9t5s3a7"
    REPO: "vllm-ci-test-repo"
    VLLM_TEST_DEVICE: "xpu"
  source_file_dependencies:
  - vllm/
  - tests/models/multimodal
  - tests/models/registry.py
  commands:
    - >-
      bash .buildkite/scripts/hardware_ci/run-intel-test.sh
      'cd tests &&
      pytest -v -s models/multimodal/processing/test_tensor_schema.py
      --deselect="tests/models/multimodal/processing/test_tensor_schema.py::test_model_tensor_schema[deepseek-ai/DeepSeek-V4.1-Flash]"
      --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB'
  parallelism: 4

- label: ":intel: (BMG) Multi-Modal Models (Extended Generation 1)"
  key: multi-modal-models-extended-generation-1
  timeout_in_minutes: 60
  device: intel_gpu
  agent_tags:
    label: production
    gpu: 1+
    mem: 16+
  no_plugin: true
  working_dir: "."
  env:
    REGISTRY: "public.ecr.aws/q9t5s3a7"
    REPO: "vllm-ci-test-repo"
    VLLM_TEST_DEVICE: "xpu"
  optional: true
  source_file_dependencies:
  - vllm/
  - "!vllm/distributed/kv_transfer/"
  - tests/models/multimodal/generation
  - tests/models/multimodal/test_mapping.py
  commands:
    - >-
      bash .buildkite/scripts/hardware_ci/run-intel-test.sh
      'cd tests &&
      pytest -v -s models/multimodal/test_mapping.py'