vLLM/.buildkite/intel_jobs/lora_intel.yaml

group: LoRA Intel
depends_on:
  - image-build-xpu
steps:
- label: ":intel: (BMG) LoRA Runtime + Utils"
  key: lora-runtime-utils
  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/lora
    - tests/lora
  commands:
    - >-
      bash .buildkite/scripts/hardware_ci/run-intel-test.sh
      'cd tests &&
      export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
      pytest -v -s lora/test_layers.py &&
      pytest -v -s lora/test_lora_checkpoints.py &&
      pytest -v -s lora/test_lora_functions.py &&
      pytest -v -s lora/test_lora_huggingface.py &&
      pytest -v -s lora/test_lora_manager.py &&
      pytest -v -s lora/test_lora_utils.py &&
      pytest -v -s lora/test_peft_helper.py &&
      pytest -v -s lora/test_resolver.py &&
      pytest -v -s lora/test_utils.py &&
      pytest -v -s lora/test_worker.py'

- label: ":intel: (BMG) LoRA Fused/MoE Kernels"
  key: lora-fused-moe-kernels
  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/lora
    - tests/lora
  commands:
    - >-
      bash .buildkite/scripts/hardware_ci/run-intel-test.sh
      'cd tests &&
      export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
      pytest -v -s lora/test_fused_moe_lora_kernel.py && 
      pytest -v -s lora/test_moe_lora_align_sum.py --deselect="tests/lora/test_moe_lora_align_sum.py::test_moe_lora_align_block_size_mixed_base_and_lora[1]"'

- label: ":intel: (BMG) LoRA Punica Kernels"
  key: lora-punica-kernels
  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/lora
    - tests/lora
  commands:
    - >-
      bash .buildkite/scripts/hardware_ci/run-intel-test.sh
      'cd tests &&
      export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
      set -o pipefail &&
      pytest -v -s lora/test_punica_ops.py::test_kernels &&
      pytest -v -s lora/test_punica_ops.py::test_kernels_hidden_size &&
      pytest -v -s lora/test_punica_ops.py::test_add_lora_fused_moe_early_exit'

- label: ":intel: (BMG) LoRA Punica FP8/XPU Ops"
  key: lora-punica-fp8-xpu-ops
  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"
  source_file_dependencies:
    - vllm/lora
    - tests/lora
  commands:
    - >-
      bash .buildkite/scripts/hardware_ci/run-intel-test.sh
      'cd tests &&
      export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
      pytest -v -s lora/test_punica_ops_fp8.py &&
      pytest -v -s lora/test_punica_xpu_ops.py'

- label: ":intel: (BMG) LoRA Models"
  key: lora-models
  timeout_in_minutes: 45
  device: intel_gpu
  agent_tags:
    label: production
    gpu: 2+
    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/lora
    - tests/lora
  commands:
    - >-
      bash .buildkite/scripts/hardware_ci/run-intel-test.sh
      'cd tests &&
      export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
      pytest -v -s lora/test_quant_model.py --deselect="tests/lora/test_quant_model.py::test_quant_model_lora[model0]" --deselect="tests/lora/test_quant_model.py::test_quant_model_lora[model1]" --deselect="tests/lora/test_quant_model.py::test_quant_model_tp_equality[model0]" &&
      pytest -v -s lora/test_transformers_model.py &&
      pytest -v -s lora/test_chatglm3_tp.py &&
      pytest -v -s lora/test_llama_tp.py::test_llama_lora'

- label: ":intel: (BMG) LoRA Multimodal"
  key: lora-multimodal
  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/lora
    - tests/lora
  commands:
    - >-
      bash .buildkite/scripts/hardware_ci/run-intel-test.sh
      'cd tests &&
      export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
      pytest -v -s lora/test_whisper.py'

- label: ":intel: (BMG) LoRA Add + Multimodal"
  key: lora-add-multimodal
  timeout_in_minutes: 45
  device: intel_gpu
  agent_tags:
    label: production
    gpu: 2+
    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/lora
    - tests/lora
  commands:
    - >-
      bash .buildkite/scripts/hardware_ci/run-intel-test.sh
      'cd tests &&
      export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
      pytest -v -s lora/test_add_lora.py &&
      pytest -v -s lora/test_default_mm_loras.py &&
      pytest -s -v lora/test_minicpmv_tp.py'