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

Signed-off-by: Yuan Zhou <yuan.zhou@intel.com>

.buildkite/run-cpu-test.sh

@@ -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 \