frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI][CPU] adding numa node number as container name suffix (#10441)

Browse Source 
Signed-off-by: Yuan Zhou <yuan.zhou@intel.com>
This commit is contained in:
Yuan
2024-11-19 21:16:43 +08:00
committed by GitHub
parent 25f9c78961
commit b4614656b8
1 changed files with 8 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
.buildkite/run-cpu-test.sh
View File

@ -13,26 +13,26 @@ numactl -C "$CORE_RANGE" -N "$NUMA_NODE" docker build -t cpu-test -f Dockerfile.
numactl -C "$CORE_RANGE" -N "$NUMA_NODE" docker build --build-arg VLLM_CPU_DISABLE_AVX512="true" -t cpu-test-avx2 -f Dockerfile.cpu .
# Setup cleanup
remove_docker_container() { docker rm -f cpu-test cpu-test-avx2 || true; }
remove_docker_container() { docker rm -f cpu-test-"$NUMA_NODE" cpu-test-avx2-"$NUMA_NODE" || true; }
trap remove_docker_container EXIT
remove_docker_container
# Run the image, setting --shm-size=4g for tensor parallel.
docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --cpuset-cpus="$CORE_RANGE" \
--cpuset-mems="$NUMA_NODE" --privileged=true --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --shm-size=4g --name cpu-test cpu-test
--cpuset-mems="$NUMA_NODE" --privileged=true --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --shm-size=4g --name cpu-test-"$NUMA_NODE" cpu-test
docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --cpuset-cpus="$CORE_RANGE" \
--cpuset-mems="$NUMA_NODE" --privileged=true --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --shm-size=4g --name cpu-test-avx2 cpu-test-avx2
--cpuset-mems="$NUMA_NODE" --privileged=true --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --shm-size=4g --name cpu-test-avx2-"$NUMA_NODE" cpu-test-avx2
function cpu_tests() {
set -e
# offline inference
docker exec cpu-test-avx2 bash -c "
docker exec cpu-test-avx2-"$NUMA_NODE" bash -c "
set -e
python3 examples/offline_inference.py"
# Run basic model test
docker exec cpu-test bash -c "
docker exec cpu-test-"$NUMA_NODE" bash -c "
set -e
pip install pytest pytest-asyncio \
decord einops librosa peft Pillow sentence-transformers soundfile \
@ -45,20 +45,20 @@ function cpu_tests() {
pytest -v -s tests/models/decoder_only/vision_language -m cpu_model"
# Run compressed-tensor test
docker exec cpu-test bash -c "
docker exec cpu-test-"$NUMA_NODE" bash -c "
set -e
pytest -s -v \
tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_static_setup \
tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_dynamic_per_token"
# Run AWQ test
docker exec cpu-test bash -c "
docker exec cpu-test-"$NUMA_NODE" bash -c "
set -e
pytest -s -v \
tests/quantization/test_ipex_quant.py"
# online inference
docker exec cpu-test bash -c "
docker exec cpu-test-"$NUMA_NODE" bash -c "
set -e
export VLLM_CPU_KVCACHE_SPACE=10
export VLLM_CPU_OMP_THREADS_BIND=$1