vLLM/.buildkite/intel_jobs/test-intel.yaml

group: Intel
steps:
  - label: ":docker: Build XPU image"
    soft_fail: true
    depends_on: []
    key: image-build-xpu
    commands:
      - bash -lc '.buildkite/image_build/image_build_xpu.sh "public.ecr.aws/q9t5s3a7" "vllm-ci-test-repo" "$BUILDKITE_COMMIT"'
    env:
      DOCKER_BUILDKIT: "1"
    retry:
      automatic:
        - exit_status: -1  # Agent was lost
          limit: 2
        - exit_status: -10  # Agent was lost
          limit: 2
  - label: ":intel: (BMG) Example Test"
    key: xpu-example-test
    depends_on:
      - image-build-xpu
    timeout_in_minutes: 70
    device: intel_gpu
    agent_tags:
      label: production
      gpu: 2+
      mem: 16+
    no_plugin: true
    env:
      REGISTRY: "public.ecr.aws/q9t5s3a7"
      REPO: "vllm-ci-test-repo"
    source_file_dependencies:
      - vllm/
      - .buildkite/intel_jobs/test-intel.yaml
    commands:
      - >-
        bash .buildkite/scripts/hardware_ci/run-intel-test.sh
        'python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager &&
        python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 -O3 -cc.cudagraph_mode=NONE &&
        python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend mp &&
        python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --attention-backend=TRITON_ATTN &&
        python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --quantization fp8_per_tensor &&
        python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --kv-cache-dtype fp8 &&
        python3 examples/basic/offline_inference/generate.py --model nvidia/Llama-3.1-8B-Instruct-FP8 --block-size 64 --enforce-eager --quantization modelopt --kv-cache-dtype fp8 --attention-backend TRITON_ATTN --max-model-len 4096 &&
        python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --block-size 64 --enforce-eager --max-model-len 8192 &&
        python3 examples/basic/offline_inference/generate.py --model TheBloke/TinyLlama-1.1B-Chat-v0.3-AWQ --block-size 64 --enforce-eager &&
        python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 &&
        python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 --enable-expert-parallel &&
        python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --max-model-len 8192 &&
        python3 examples/basic/offline_inference/generate.py --model INCModel/Qwen3-30B-A3B-Instruct-2507-MXFP4-LLMC -tp 2 --max-model-len 8192
        '
  - label: ":intel: (BMG) W8A8 FP8 Linear Examples"
    key: xpu-w8a8-fp8-linear-examples
    depends_on:
      - image-build-xpu
    timeout_in_minutes: 60
    device: intel_gpu
    agent_tags:
      label: production
      gpu: 1+
      mem: 16+
    no_plugin: true
    env:
      REGISTRY: "public.ecr.aws/q9t5s3a7"
      REPO: "vllm-ci-test-repo"
      VLLM_TEST_DEVICE: "xpu"
    source_file_dependencies:
      - vllm/
      - .buildkite/intel_jobs/test-intel.yaml
    commands:
      - >-
        bash .buildkite/scripts/hardware_ci/run-intel-test.sh
        'python3 examples/basic/offline_inference/generate.py --linear-backend xpu --model RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8 --enforce-eager --max-model-len 4096 &&
        python3 examples/basic/offline_inference/generate.py --linear-backend torch --model RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8 --enforce-eager --max-model-len 4096 &&
        python3 examples/basic/offline_inference/generate.py --linear-backend xpu --model neuralmagic/Llama-3.2-1B-Instruct-FP8-dynamic --enforce-eager --max-model-len 4096 &&
        python3 examples/basic/offline_inference/generate.py --linear-backend torch --model Qwen/Qwen3-4B-Instruct-2507-FP8 --enforce-eager --max-model-len 4096 &&
        python3 examples/basic/offline_inference/generate.py --linear-backend xpu --model meta-llama/Llama-3.2-1B-Instruct --quantization fp8_per_tensor --enforce-eager --max-model-len 4096 &&
        python3 examples/basic/offline_inference/generate.py --linear-backend torch --model meta-llama/Llama-3.2-1B-Instruct --quantization fp8_per_tensor --enforce-eager --max-model-len 4096
        '
  - label: ":intel: (BMG) V1 test"
    key: xpu-v1-test
    depends_on:
      - image-build-xpu
    timeout_in_minutes: 70
    device: intel_gpu
    agent_tags:
      label: production
      gpu: 1+
      mem: 16+
    no_plugin: true
    env:
      REGISTRY: "public.ecr.aws/q9t5s3a7"
      REPO: "vllm-ci-test-repo"
    source_file_dependencies:
      - vllm/
      - .buildkite/intel_jobs/test-intel.yaml
    commands:
      - >-
        bash .buildkite/scripts/hardware_ci/run-intel-test.sh
        'cd tests && pip install dpctl &&
        pytest -v -s v1/core --ignore=v1/core/test_reset_prefix_cache_e2e.py --ignore=v1/core/test_scheduler_e2e.py &&
        pytest -v -s v1/engine --ignore=v1/engine/test_output_processor.py --ignore=v1/engine/test_core_engine_actor_manager.py &&
        pytest -v -s v1/sample --ignore=v1/sample/test_logprobs.py --ignore=v1/sample/test_logprobs_e2e.py -k "not test_topk_only and not test_topp_only and not test_topk_and_topp" &&
        pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py --ignore=v1/worker/test_worker_memory_snapshot.py &&
        pytest -v -s v1/structured_output &&
        pytest -v -s v1/test_serial_utils.py &&
        pytest -v -s v1/e2e/general/test_correctness_sliding_window.py &&
        pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_speculators_eagle3.py --ignore=v1/spec_decode/test_acceptance_length.py --ignore=v1/spec_decode/test_speculators_correctness.py --deselect=tests/v1/spec_decode/test_mtp.py::test_glm_mtp_defers_lm_head &&
        pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_lmcache_integration.py --ignore=v1/kv_connector/unit/test_hf3fs_client.py --ignore=v1/kv_connector/unit/test_hf3fs_connector.py --ignore=v1/kv_connector/unit/test_hf3fs_metadata_server.py --ignore=v1/kv_connector/unit/test_offloading_connector.py --ignore=v1/kv_connector/unit/test_multi_connector.py --ignore=v1/kv_connector/unit/test_example_connector.py --deselect=tests/v1/kv_connector/unit/test_nixl_connector.py::test_abort_timeout_on_prefiller[ray]'
    parallelism: 2
  - label: ":intel: (BMG) Qwen3-30B + V1 KV Connector"
    key: xpu-qwen3-30b-v1-kv-connector
    depends_on:
      - image-build-xpu
    timeout_in_minutes: 90
    device: intel_gpu
    agent_tags:
      label: production
      gpu: 2+
      mem: 24+
    no_plugin: true
    env:
      REGISTRY: "public.ecr.aws/q9t5s3a7"
      REPO: "vllm-ci-test-repo"
    source_file_dependencies:
      - vllm/
      - .buildkite/intel_jobs/test-intel.yaml
    commands:
      - >-
        bash .buildkite/scripts/hardware_ci/run-intel-test.sh
        'cd tests &&
        pip install dpctl &&
        pytest -v -s v1/kv_connector/unit/test_multi_connector.py &&
        pytest -v -s v1/kv_connector/unit/test_example_connector.py &&
        cd .. &&
        VLLM_XPU_FUSED_MOE_USE_REF=1 python3 examples/basic/offline_inference/generate.py --model Qwen/Qwen3-30B-A3B-Instruct-2507-FP8 --enforce-eager -tp 2 --max-model-len 8192'
  - label: ":intel: (BMG) Server test"
    key: xpu-server-test
    depends_on:
      - image-build-xpu
    timeout_in_minutes: 45
    device: intel_gpu
    agent_tags:
      label: production
      gpu: 1+
      mem: 16+
    no_plugin: true
    env:
      REGISTRY: "public.ecr.aws/q9t5s3a7"
      REPO: "vllm-ci-test-repo"
    source_file_dependencies:
      - vllm/
      - .buildkite/intel_jobs/test-intel.yaml
    commands:
      - >-
        bash .buildkite/scripts/hardware_ci/run-intel-test.sh
        'cd tests &&
        pytest -v -s entrypoints/multimodal/openai/chat_completion/test_audio_in_video.py &&
        pytest -v -s benchmarks/test_serve_cli.py'
  - label: ":intel: (BMG) Quantization test"
    key: xpu-quantization-test
    depends_on:
      - image-build-xpu
    timeout_in_minutes: 30
    device: intel_gpu
    agent_tags:
      label: production
      gpu: 1+
      mem: 16+
    no_plugin: true
    env:
      REGISTRY: "public.ecr.aws/q9t5s3a7"
      REPO: "vllm-ci-test-repo"
    source_file_dependencies:
      - vllm/
      - .buildkite/intel_jobs/test-intel.yaml
    commands:
      - >-
        bash .buildkite/scripts/hardware_ci/run-intel-test.sh
        'cd tests &&
        pytest -v -s quantization/test_auto_round.py &&
        pytest -v -s quantization/test_online.py --deselect=tests/quantization/test_online.py::test_online_quantization_loads_real_weights --deselect="tests/quantization/test_online.py::test_online_quantization[False-requantization_mxfp8_ptcp_fp8]"'
  - label: ":intel: (BMG) Compressed tensors FP8 test"
    key: xpu-compressed-tensors-fp8-test
    depends_on:
      - image-build-xpu
    timeout_in_minutes: 60
    device: intel_gpu
    agent_tags:
      label: production
      gpu: 1+
      mem: 16+
    no_plugin: true
    env:
      REGISTRY: "public.ecr.aws/q9t5s3a7"
      REPO: "vllm-ci-test-repo"
      VLLM_TEST_DEVICE: "xpu"
    source_file_dependencies:
      - vllm/
      - tests/quantization/test_compressed_tensors.py
      - .buildkite/intel_jobs/test-intel.yaml
    commands:
      - >-
        bash .buildkite/scripts/hardware_ci/run-intel-test.sh
        'cd tests &&
        pytest -v -s quantization/test_compressed_tensors.py::test_compressed_tensors_fp8 &&
        pytest -v -s quantization/test_compressed_tensors.py::test_compressed_tensors_fp8_block_enabled'
  - label: ":intel: (BMG) Graph"
    key: xpu-graph
    depends_on:
      - image-build-xpu
    timeout_in_minutes: 60
    device: intel_gpu
    agent_tags:
      label: production
      gpu: 1+
      mem: 32+
    no_plugin: true
    env:
      REGISTRY: "public.ecr.aws/q9t5s3a7"
      REPO: "vllm-ci-test-repo"
      VLLM_TEST_DEVICE: "xpu"
    source_file_dependencies:
      - vllm/compilation/
      - vllm/config/compilation.py
      - vllm/platforms/xpu.py
      - vllm/v1/cudagraph_dispatcher.py
      - vllm/v1/worker/encoder_cudagraph.py
      - vllm/v1/worker/encoder_cudagraph_defs.py
      - vllm/v1/worker/xpu_model_runner.py
      - vllm/v1/worker/xpu_worker.py
      - tests/v1/cudagraph
      - .buildkite/intel_jobs/test-intel.yaml
    commands:
      - >-
        bash .buildkite/scripts/hardware_ci/run-intel-test.sh
        'cd tests &&
        pytest -v -s v1/cudagraph/test_cudagraph_dispatch.py &&
        pytest -v -s v1/cudagraph/test_cudagraph_mode.py &&
        pytest -v -s v1/cudagraph/test_breakable_cudagraph.py &&
        pytest -v -s v1/cudagraph/test_encoder_cudagraph.py'