vllm/.buildkite/test-pipeline.yaml
shiyi.c_98 d10f8e1d43
[Experimental] Prefix Caching Support (#1669)
Co-authored-by: DouHappy <2278958187@qq.com>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
2024-01-17 16:32:10 -08:00

49 lines
1.2 KiB
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: Benchmarks
working_dir: "/vllm-workspace/.buildkite"
commands:
- pip install aiohttp
- bash run-benchmarks.sh