biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI/Build] Update CPU tests to include all "standard" tests (#5481)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2024-11-08 23:30:04 +08:00
committed by GitHub
parent 208ce622c7
commit b489fc3c91
14 changed files with 63 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
.buildkite/run-cpu-test-ppc64le.sh
View File

@@ -19,17 +19,22 @@ docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/hugg
# Run basic model test
docker exec cpu-test bash -c "
pip install pytest matplotlib einops transformers_stream_generator
pytest -v -s tests/models -m \"not vlm\" \
--ignore=tests/models/test_embedding.py \
--ignore=tests/models/test_oot_registration.py \
--ignore=tests/models/test_registry.py \
--ignore=tests/models/test_jamba.py \
--ignore=tests/models/test_mamba.py \
--ignore=tests/models/test_danube3_4b.py" # Mamba kernels and Danube3-4B on CPU is not supported
set -e
pip install pytest pytest-asyncio \
decord einops librosa peft Pillow sentence-transformers soundfile \
transformers_stream_generator matplotlib datamodel_code_generator
pip install torchvision --index-url https://download.pytorch.org/whl/cpu
# Embedding models are not supported for CPU yet
# pytest -v -s tests/models/embedding/language
pytest -v -s tests/models/encoder_decoder/language
pytest -v -s tests/models/decoder_only/language/test_models.py
# Chunked prefill not supported for CPU yet
# pytest -v -s tests/models/decoder_only/audio_language -m cpu_model
pytest -v -s tests/models/decoder_only/vision_language -m cpu_model"
# online inference
docker exec cpu-test bash -c "
set -e
python3 -m vllm.entrypoints.openai.api_server --model facebook/opt-125m &
timeout 600 bash -c 'until curl localhost:8000/v1/models; do sleep 1; done' || exit 1
python3 benchmarks/benchmark_serving.py \