[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:
parent
b039cbbce3
commit
b75bce1008
@ -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
|
||||||
|
Loading…
x
Reference in New Issue
Block a user