[CI/Build] Adding timeout in CPU CI to avoid CPU test queue blocking (#6892)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk> Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Li, Jiang
GitHub
parent
127c07480e
commit
d7edca1dee
@ -17,30 +17,35 @@ source /etc/environment
|
||||
#docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --privileged=true --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --shm-size=4g --name cpu-test cpu-test
|
||||
docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --privileged=true --network host -e HF_TOKEN="$HF_TOKEN" --name cpu-test cpu-test
|
||||
|
||||
# Run basic model test
|
||||
docker exec cpu-test bash -c "
|
||||
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"
|
||||
function cpu_tests() {
|
||||
# Run basic model test
|
||||
docker exec cpu-test bash -c "
|
||||
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
|
||||
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 \
|
||||
--backend vllm \
|
||||
--dataset-name random \
|
||||
--model facebook/opt-125m \
|
||||
--num-prompts 20 \
|
||||
--endpoint /v1/completions \
|
||||
--tokenizer facebook/opt-125m"
|
||||
# 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 \
|
||||
--backend vllm \
|
||||
--dataset-name random \
|
||||
--model facebook/opt-125m \
|
||||
--num-prompts 20 \
|
||||
--endpoint /v1/completions \
|
||||
--tokenizer facebook/opt-125m"
|
||||
}
|
||||
|
||||
# All of CPU tests are expected to be finished less than 25 mins.
|
||||
export -f cpu_tests
|
||||
timeout 25m bash -c "cpu_tests"
|
||||
|
||||
@ -19,50 +19,55 @@ docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/hugg
|
||||
docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --cpuset-cpus=48-95 \
|
||||
--cpuset-mems=1 --privileged=true --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --shm-size=4g --name cpu-test-avx2 cpu-test-avx2
|
||||
|
||||
# offline inference
|
||||
docker exec cpu-test-avx2 bash -c "
|
||||
set -e
|
||||
python3 examples/offline_inference.py"
|
||||
function cpu_tests() {
|
||||
# offline inference
|
||||
docker exec cpu-test-avx2 bash -c "
|
||||
set -e
|
||||
python3 examples/offline_inference.py"
|
||||
|
||||
# Run basic model test
|
||||
docker exec cpu-test bash -c "
|
||||
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"
|
||||
# Run basic model test
|
||||
docker exec cpu-test bash -c "
|
||||
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
|
||||
pytest -v -s tests/models/decoder_only/audio_language -m cpu_model
|
||||
pytest -v -s tests/models/decoder_only/vision_language -m cpu_model"
|
||||
|
||||
# Run compressed-tensor test
|
||||
docker exec cpu-test bash -c "
|
||||
set -e
|
||||
pytest -s -v \
|
||||
tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_static_setup \
|
||||
tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_dynamic_per_token"
|
||||
# Run compressed-tensor test
|
||||
docker exec cpu-test bash -c "
|
||||
set -e
|
||||
pytest -s -v \
|
||||
tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_static_setup \
|
||||
tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_dynamic_per_token"
|
||||
|
||||
# Run AWQ test
|
||||
docker exec cpu-test bash -c "
|
||||
set -e
|
||||
pytest -s -v \
|
||||
tests/quantization/test_ipex_quant.py"
|
||||
# Run AWQ test
|
||||
docker exec cpu-test bash -c "
|
||||
set -e
|
||||
pytest -s -v \
|
||||
tests/quantization/test_ipex_quant.py"
|
||||
|
||||
# online inference
|
||||
docker exec cpu-test bash -c "
|
||||
set -e
|
||||
export VLLM_CPU_KVCACHE_SPACE=10
|
||||
export VLLM_CPU_OMP_THREADS_BIND=48-92
|
||||
python3 -m vllm.entrypoints.openai.api_server --model facebook/opt-125m --dtype half &
|
||||
timeout 600 bash -c 'until curl localhost:8000/v1/models; do sleep 1; done' || exit 1
|
||||
python3 benchmarks/benchmark_serving.py \
|
||||
--backend vllm \
|
||||
--dataset-name random \
|
||||
--model facebook/opt-125m \
|
||||
--num-prompts 20 \
|
||||
--endpoint /v1/completions \
|
||||
--tokenizer facebook/opt-125m"
|
||||
# online inference
|
||||
docker exec cpu-test bash -c "
|
||||
set -e
|
||||
export VLLM_CPU_KVCACHE_SPACE=10
|
||||
export VLLM_CPU_OMP_THREADS_BIND=48-92
|
||||
python3 -m vllm.entrypoints.openai.api_server --model facebook/opt-125m --dtype half &
|
||||
timeout 600 bash -c 'until curl localhost:8000/v1/models; do sleep 1; done' || exit 1
|
||||
python3 benchmarks/benchmark_serving.py \
|
||||
--backend vllm \
|
||||
--dataset-name random \
|
||||
--model facebook/opt-125m \
|
||||
--num-prompts 20 \
|
||||
--endpoint /v1/completions \
|
||||
--tokenizer facebook/opt-125m"
|
||||
}
|
||||
|
||||
# All of CPU tests are expected to be finished less than 25 mins.
|
||||
export -f cpu_tests
|
||||
timeout 25m bash -c "cpu_tests"
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user