xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-15 04:45:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI][CPU] adding build number to docker image name (#11788)

Browse Source 
Signed-off-by: Yuan Zhou <yuan.zhou@intel.com>
This commit is contained in:
Yuan 2025-01-07 15:28:01 +08:00 committed by GitHub
parent ce1917fcf2
commit 1e4ce295ae
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 11 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
.buildkite/run-cpu-test.sh
View File

@ -9,31 +9,31 @@ CORE_RANGE=${CORE_RANGE:-48-95}
NUMA_NODE=${NUMA_NODE:-1} NUMA_NODE=${NUMA_NODE:-1}
# Try building the docker image # Try building the docker image
numactl -C "$CORE_RANGE" -N "$NUMA_NODE" docker build -t cpu-test -f Dockerfile.cpu . numactl -C "$CORE_RANGE" -N "$NUMA_NODE" docker build -t cpu-test-"$BUILDKITE_BUILD_NUMBER" -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 . numactl -C "$CORE_RANGE" -N "$NUMA_NODE" docker build --build-arg VLLM_CPU_DISABLE_AVX512="true" -t cpu-test-"$BUILDKITE_BUILD_NUMBER"-avx2 -f Dockerfile.cpu .
# Setup cleanup # Setup cleanup
remove_docker_container() { docker rm -f cpu-test-"$NUMA_NODE" cpu-test-avx2-"$NUMA_NODE" || true; } remove_docker_container() { docker rm -f cpu-test-"$BUILDKITE_BUILD_NUMBER"-"$NUMA_NODE" cpu-test-"$BUILDKITE_BUILD_NUMBER"-avx2-"$NUMA_NODE" || true; }
trap remove_docker_container EXIT trap remove_docker_container EXIT
remove_docker_container remove_docker_container
# Run the image, setting --shm-size=4g for tensor parallel. # Run the image, setting --shm-size=4g for tensor parallel.
docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --cpuset-cpus="$CORE_RANGE" \ 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-"$NUMA_NODE" cpu-test --cpuset-mems="$NUMA_NODE" --privileged=true --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --shm-size=4g --name cpu-test-"$BUILDKITE_BUILD_NUMBER"-"$NUMA_NODE" cpu-test-"$BUILDKITE_BUILD_NUMBER"
docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --cpuset-cpus="$CORE_RANGE" \ 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-"$NUMA_NODE" cpu-test-avx2 --cpuset-mems="$NUMA_NODE" --privileged=true --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --shm-size=4g --name cpu-test-"$BUILDKITE_BUILD_NUMBER"-avx2-"$NUMA_NODE" cpu-test-"$BUILDKITE_BUILD_NUMBER"-avx2
function cpu_tests() { function cpu_tests() {
set -e set -e
export NUMA_NODE=$2 export NUMA_NODE=$2
# offline inference # offline inference
docker exec cpu-test-avx2-"$NUMA_NODE" bash -c " docker exec cpu-test-"$BUILDKITE_BUILD_NUMBER"-avx2-"$NUMA_NODE" bash -c "
set -e set -e
python3 examples/offline_inference.py" python3 examples/offline_inference.py"
# Run basic model test # Run basic model test
docker exec cpu-test-"$NUMA_NODE" bash -c " docker exec cpu-test-"$BUILDKITE_BUILD_NUMBER"-"$NUMA_NODE" bash -c "
set -e set -e
pip install pytest pytest-asyncio \ pip install pytest pytest-asyncio \
decord einops librosa peft Pillow sentence-transformers soundfile \ decord einops librosa peft Pillow sentence-transformers soundfile \
@ -46,26 +46,26 @@ function cpu_tests() {
pytest -v -s tests/models/decoder_only/vision_language -m cpu_model" pytest -v -s tests/models/decoder_only/vision_language -m cpu_model"
# Run compressed-tensor test # Run compressed-tensor test
docker exec cpu-test-"$NUMA_NODE" bash -c " docker exec cpu-test-"$BUILDKITE_BUILD_NUMBER"-"$NUMA_NODE" bash -c "
set -e set -e
pytest -s -v \ 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_static_setup \
tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_dynamic_per_token" tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_dynamic_per_token"
# Run AWQ test # Run AWQ test
docker exec cpu-test-"$NUMA_NODE" bash -c " docker exec cpu-test-"$BUILDKITE_BUILD_NUMBER"-"$NUMA_NODE" bash -c "
set -e set -e
pytest -s -v \ pytest -s -v \
tests/quantization/test_ipex_quant.py" tests/quantization/test_ipex_quant.py"
# Run chunked-prefill and prefix-cache test # Run chunked-prefill and prefix-cache test
docker exec cpu-test-"$NUMA_NODE" bash -c " docker exec cpu-test-"$BUILDKITE_BUILD_NUMBER"-"$NUMA_NODE" bash -c "
set -e set -e
pytest -s -v -k cpu_model \ pytest -s -v -k cpu_model \
tests/basic_correctness/test_chunked_prefill.py" tests/basic_correctness/test_chunked_prefill.py"
# online inference # online inference
docker exec cpu-test-"$NUMA_NODE" bash -c " docker exec cpu-test-"$BUILDKITE_BUILD_NUMBER"-"$NUMA_NODE" bash -c "
set -e set -e
export VLLM_CPU_KVCACHE_SPACE=10 export VLLM_CPU_KVCACHE_SPACE=10
export VLLM_CPU_OMP_THREADS_BIND=$1 export VLLM_CPU_OMP_THREADS_BIND=$1