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
  command: pytest -v -s test_regression.py
  working_dir: "/vllm-workspace/tests" # optional

- label: AsyncEngine Test
  command: pytest -v -s async_engine

- label: Distributed Test
  command: pytest -v -s test_comm_ops.py
  working_dir: "/vllm-workspace/tests/distributed"
  num_gpus: 2 # only support 1 or 2 for now.

- label: Engine Test
  command: pytest -v -s engine

- label: Entrypoints Test
  command: pytest -v -s entrypoints

- label: Kernels Test
  command: pytest -v -s kernels
  soft_fail: true

- label: Models Test
  commands:
    - pytest -v -s models --forked
  soft_fail: true

- label: Prefix Caching Test
  commands:
    - pytest -v -s prefix_caching

- label: Samplers Test
  command: pytest -v -s samplers --forked

- label: Worker Test
  command: pytest -v -s worker

- label: LoRA Test
  command: pytest -v -s lora

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