vllm/.buildkite/test-pipeline.yaml

# 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 script will be feed into Jinja template in `test-template.j2` to generate
# the final pipeline yaml file.

steps:
- label: Regression Test
  mirror_hardwares: [amd]
  command: pytest -v -s test_regression.py
  working_dir: "/vllm-workspace/tests" # optional

- label: AsyncEngine Test
  #mirror_hardwares: [amd]
  command: pytest -v -s async_engine

- label: Basic Correctness Test
  mirror_hardwares: [amd]
  commands:
  - VLLM_ATTENTION_BACKEND=XFORMERS pytest -v -s basic_correctness/test_basic_correctness.py
  - VLLM_ATTENTION_BACKEND=FLASH_ATTN pytest -v -s basic_correctness/test_basic_correctness.py
  - VLLM_ATTENTION_BACKEND=XFORMERS pytest -v -s basic_correctness/test_chunked_prefill.py
  - VLLM_ATTENTION_BACKEND=FLASH_ATTN pytest -v -s basic_correctness/test_chunked_prefill.py
  - VLLM_TEST_ENABLE_ARTIFICIAL_PREEMPT=1 pytest -v -s basic_correctness/test_preemption.py

- label: Core Test
  mirror_hardwares: [amd]
  command: pytest -v -s core

- label: Distributed Comm Ops Test
  #mirror_hardwares: [amd]
  command: pytest -v -s distributed/test_comm_ops.py
  working_dir: "/vllm-workspace/tests"
  num_gpus: 2

- label: Distributed Tests
  mirror_hardwares: [amd]
  working_dir: "/vllm-workspace/tests"
  num_gpus: 2
  commands:
  - pytest -v -s distributed/test_pynccl_library.py
  - TEST_DIST_MODEL=facebook/opt-125m DISTRIBUTED_EXECUTOR_BACKEND=ray pytest -v -s distributed/test_basic_distributed_correctness.py
  - TEST_DIST_MODEL=meta-llama/Llama-2-7b-hf DISTRIBUTED_EXECUTOR_BACKEND=ray pytest -v -s distributed/test_basic_distributed_correctness.py
  - TEST_DIST_MODEL=facebook/opt-125m DISTRIBUTED_EXECUTOR_BACKEND=ray pytest -v -s distributed/test_chunked_prefill_distributed.py
  - TEST_DIST_MODEL=meta-llama/Llama-2-7b-hf DISTRIBUTED_EXECUTOR_BACKEND=ray pytest -v -s distributed/test_chunked_prefill_distributed.py
  - TEST_DIST_MODEL=facebook/opt-125m DISTRIBUTED_EXECUTOR_BACKEND=mp pytest -v -s distributed/test_basic_distributed_correctness.py
  - TEST_DIST_MODEL=meta-llama/Llama-2-7b-hf DISTRIBUTED_EXECUTOR_BACKEND=mp pytest -v -s distributed/test_basic_distributed_correctness.py
  - TEST_DIST_MODEL=facebook/opt-125m DISTRIBUTED_EXECUTOR_BACKEND=mp pytest -v -s distributed/test_chunked_prefill_distributed.py
  - TEST_DIST_MODEL=meta-llama/Llama-2-7b-hf DISTRIBUTED_EXECUTOR_BACKEND=mp pytest -v -s distributed/test_chunked_prefill_distributed.py
  - pytest -v -s spec_decode/e2e/test_integration_dist.py 

- label: Distributed Tests (Multiple Groups)
  #mirror_hardwares: [amd]
  working_dir: "/vllm-workspace/tests"
  num_gpus: 4
  commands:
  - pytest -v -s distributed/test_pynccl.py

- label: Engine Test
  mirror_hardwares: [amd]
  command: pytest -v -s engine tokenization test_sequence.py test_config.py test_logger.py

- label: Entrypoints Test
  #mirror_hardwares: [amd]
  commands:
  # these tests have to be separated, because each one will allocate all posible GPU memory
  - pytest -v -s entrypoints --ignore=entrypoints/test_server_oot_registration.py
  - pytest -v -s entrypoints/test_server_oot_registration.py

- label: Examples Test
  working_dir: "/vllm-workspace/examples"
  mirror_hardwares: [amd]
  commands:
    # install aws cli for llava_example.py
    # install tensorizer for tensorize_vllm_model.py
    - pip install awscli tensorizer
    - python3 offline_inference.py
    - python3 offline_inference_with_prefix.py
    - python3 llm_engine_example.py
    - python3 llava_example.py
    - python3 tensorize_vllm_model.py --model facebook/opt-125m serialize --serialized-directory /tmp/ --suffix v1 && python3 tensorize_vllm_model.py --model facebook/opt-125m deserialize --path-to-tensors /tmp/vllm/facebook/opt-125m/v1/model.tensors

- label: Kernels Test %N
  #mirror_hardwares: [amd]
  command: pytest -v -s kernels --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
  parallelism: 4

- label: Models Test
  #mirror_hardwares: [amd]
  commands:
    - bash ../.buildkite/download-images.sh
    - pytest -v -s models --ignore=models/test_llava.py

- label: Llava Test
  mirror_hardwares: [amd]
  commands:
    - bash ../.buildkite/download-images.sh
    - pytest -v -s models/test_llava.py

- label: Prefix Caching Test
  mirror_hardwares: [amd]
  commands:
    - pytest -v -s prefix_caching

- label: Samplers Test
  #mirror_hardwares: [amd]
  command: pytest -v -s samplers

- label: LogitsProcessor Test
  mirror_hardwares: [amd]
  command: pytest -v -s test_logits_processor.py

- label: Worker Test
  mirror_hardwares: [amd]
  command: pytest -v -s worker

- label: Speculative decoding tests
  #mirror_hardwares: [amd]
  command: pytest -v -s spec_decode

- label: LoRA Test %N
  #mirror_hardwares: [amd]
  command: pytest -v -s lora --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --ignore=lora/test_long_context.py
  parallelism: 4

- label: LoRA Long Context (Distributed)
  #mirror_hardwares: [amd]
  num_gpus: 4
  # This test runs llama 13B, so it is required to run on 4 GPUs.
  commands:
    # Temporarily run this way because we cannot clean up GPU mem usage
    # for multi GPU tests.
    # TODO(sang): Fix it.
    - pytest -v -s lora/test_long_context.py::test_rotary_emb_replaced
    - pytest -v -s lora/test_long_context.py::test_batched_rope_kernel
    - pytest -v -s lora/test_long_context.py::test_self_consistency
    - pytest -v -s lora/test_long_context.py::test_quality
    - pytest -v -s lora/test_long_context.py::test_max_len

- label: Tensorizer Test
  #mirror_hardwares: [amd]
  command: apt-get install curl libsodium23 && pytest -v -s tensorizer_loader

- label: Metrics Test
  mirror_hardwares: [amd]
  command: pytest -v -s metrics

- label: Quantization Test
  #mirror_hardwares: [amd]
  command: pytest -v -s quantization

- label: Benchmarks
  working_dir: "/vllm-workspace/.buildkite"
  mirror_hardwares: [amd]
  commands:
  - pip install aiohttp
  - bash run-benchmarks.sh

- label: Documentation Build
  working_dir: "/vllm-workspace/test_docs/docs"
  no_gpu: True
  commands:
  - pip install -r requirements-docs.txt
  - SPHINXOPTS=\"-W\" make html