20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[CI][CPU]refactor CPU tests to allow to bind with different cores (#10222)

Browse Source 
Signed-off-by: Yuan Zhou <yuan.zhou@intel.com>
This commit is contained in:
Yuan 2024-11-12 18:07:32 +08:00 committed by GitHub
parent 3a28f18b0b
commit d201d41973
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 11 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
.buildkite/run-cpu-test.sh
View File

@ -4,9 +4,13 @@
# It serves a sanity check for compilation and basic model usage.
set -ex
# allow to bind to different cores
CORE_RANGE=${CORE_RANGE:-48-95}
NUMA_NODE=${NUMA_NODE:-1}
# Try building the docker image
numactl -C 48-95 -N 1 docker build -t cpu-test -f Dockerfile.cpu .
numactl -C 48-95 -N 1 docker build --build-arg VLLM_CPU_DISABLE_AVX512="true" -t cpu-test-avx2 -f Dockerfile.cpu .
numactl -C $CORE_RANGE -N $NUMA_NODE docker build -t cpu-test -f Dockerfile.cpu .
numactl -C $CORE_RANGE -N $NUMA_NODE docker build --build-arg VLLM_CPU_DISABLE_AVX512="true" -t cpu-test-avx2 -f Dockerfile.cpu .
# Setup cleanup
remove_docker_container() { docker rm -f cpu-test cpu-test-avx2 || true; }
@ -14,10 +18,10 @@ trap remove_docker_container EXIT
remove_docker_container
# Run the image, setting --shm-size=4g for tensor parallel.
docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --cpuset-cpus=48-95 \
--cpuset-mems=1 --privileged=true --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --shm-size=4g --name cpu-test cpu-test
docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --cpuset-cpus=48-95 \
--cpuset-mems=1 --privileged=true --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --shm-size=4g --name cpu-test-avx2 cpu-test-avx2
docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --cpuset-cpus=$CORE_RANGE \
--cpuset-mems=$NUMA_NODE --privileged=true --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --shm-size=4g --name cpu-test cpu-test
docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --cpuset-cpus=$CORE_RANGE \
--cpuset-mems=$NUMA_NODE --privileged=true --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --shm-size=4g --name cpu-test-avx2 cpu-test-avx2
function cpu_tests() {
set -e
@ -57,7 +61,7 @@ function cpu_tests() {
docker exec cpu-test bash -c "
set -e
export VLLM_CPU_KVCACHE_SPACE=10
export VLLM_CPU_OMP_THREADS_BIND=48-92
export VLLM_CPU_OMP_THREADS_BIND=$CORE_RANGE
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 \