[ci] Add grouped tests & mark tests to run by default for fastcheck pipeline (#6365)

Signed-off-by: kevin <kevin@anyscale.com>
This commit is contained in:
Kevin H. Luu 2024-07-12 09:58:38 -07:00 committed by GitHub
parent b039cbbce3
commit b75bce1008
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -7,8 +7,33 @@
steps: steps:
- label: Async Engine, Inputs, Utils, Worker Test
fast_check: true
fast_check_only: true
commands:
- pytest -v -s async_engine # Async Engine
- bash ../.buildkite/download-images.sh # Inputs
- pytest -v -s test_inputs.py
- pytest -v -s multimodal
- pytest -v -s test_utils.py # Utils
- pytest -v -s worker # Worker
- label: Tensorizer, Metrics, Tracing Test
fast_check: true
fast_check_only: true
commands:
- apt-get install curl libsodium23 && pytest -v -s tensorizer_loader # Tensorizer
- pytest -v -s metrics # Metrics
- "pip install \
opentelemetry-sdk \
opentelemetry-api \
opentelemetry-exporter-otlp \
opentelemetry-semantic-conventions-ai" # Tracing
- pytest -v -s tracing
- label: Regression Test - label: Regression Test
mirror_hardwares: [amd] mirror_hardwares: [amd]
fast_check: true
command: pytest -v -s test_regression.py command: pytest -v -s test_regression.py
working_dir: "/vllm-workspace/tests" # optional working_dir: "/vllm-workspace/tests" # optional
@ -18,6 +43,7 @@ steps:
- label: Basic Correctness Test - label: Basic Correctness Test
mirror_hardwares: [amd] mirror_hardwares: [amd]
fast_check: true
commands: commands:
- pip install https://github.com/flashinfer-ai/flashinfer/releases/download/v0.0.8/flashinfer-0.0.8+cu121torch2.3-cp310-cp310-linux_x86_64.whl - pip install https://github.com/flashinfer-ai/flashinfer/releases/download/v0.0.8/flashinfer-0.0.8+cu121torch2.3-cp310-cp310-linux_x86_64.whl
- VLLM_ATTENTION_BACKEND=XFORMERS pytest -v -s basic_correctness/test_basic_correctness.py - VLLM_ATTENTION_BACKEND=XFORMERS pytest -v -s basic_correctness/test_basic_correctness.py
@ -29,6 +55,7 @@ steps:
- label: Core Test - label: Core Test
mirror_hardwares: [amd] mirror_hardwares: [amd]
fast_check: true
commands: commands:
- pytest -v -s core - pytest -v -s core
- pytest -v -s distributed/test_parallel_state.py - pytest -v -s distributed/test_parallel_state.py
@ -68,6 +95,7 @@ steps:
#mirror_hardwares: [amd] #mirror_hardwares: [amd]
working_dir: "/vllm-workspace/tests" working_dir: "/vllm-workspace/tests"
num_gpus: 4 num_gpus: 4
fast_check: true
commands: commands:
- pytest -v -s distributed/test_pynccl.py - pytest -v -s distributed/test_pynccl.py
# We want to test that models which use 2 GPUs work with 4 GPUs, which is why we duplicate them here. # We want to test that models which use 2 GPUs work with 4 GPUs, which is why we duplicate them here.
@ -95,6 +123,7 @@ steps:
- pytest -v -s tokenization - pytest -v -s tokenization
- label: Entrypoints Test - label: Entrypoints Test
fast_check: true
mirror_hardwares: [amd] mirror_hardwares: [amd]
commands: commands:
@ -228,6 +257,7 @@ steps:
- label: Documentation Build - label: Documentation Build
working_dir: "/vllm-workspace/test_docs/docs" working_dir: "/vllm-workspace/test_docs/docs"
fast_check: true
no_gpu: True no_gpu: True
commands: commands:
- pip install -r requirements-docs.txt - pip install -r requirements-docs.txt