biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI/Build][Doc] Move existing benchmark scripts in CI/document/example to vllm bench CLI (#21355)

Browse Source 
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
This commit is contained in:
Ye (Charlotte) Qi
2025-07-26 07:10:14 -07:00
committed by GitHub
parent 9094d11c5d
commit e7c4f9ee86
14 changed files with 101 additions and 86 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
.buildkite/scripts/hardware_ci/run-cpu-test.sh
View File

@@ -13,9 +13,9 @@ NUMA_NODE=${NUMA_NODE:-1}
export CMAKE_BUILD_PARALLEL_LEVEL=32
# Setup cleanup
remove_docker_container() {
set -e;
docker rm -f cpu-test-"$NUMA_NODE" cpu-test-"$NUMA_NODE"-avx2 || true;
remove_docker_container() {
set -e;
docker rm -f cpu-test-"$NUMA_NODE" cpu-test-"$NUMA_NODE"-avx2 || true;
}
trap remove_docker_container EXIT
remove_docker_container
@@ -69,7 +69,7 @@ function cpu_tests() {
docker exec cpu-test-"$NUMA_NODE" bash -c "
set -e
pytest -s -v \
tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_logprobs[False-10-32-neuralmagic/Llama-3.2-1B-quantized.w8a8]"
tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_logprobs[False-10-32-neuralmagic/Llama-3.2-1B-quantized.w8a8]"
# Note: disable it until supports V1
# Run AWQ test
@@ -83,7 +83,7 @@ function cpu_tests() {
set -e
VLLM_CPU_OMP_THREADS_BIND=$E2E_OMP_THREADS VLLM_CPU_SGL_KERNEL=1 vllm serve meta-llama/Llama-3.2-3B-Instruct -tp=2 -pp=2 &
timeout 600 bash -c "until curl localhost:8000/v1/models; do sleep 1; done" || exit 1
python3 benchmarks/benchmark_serving.py \
vllm bench serve \
--backend vllm \
--dataset-name random \
--model meta-llama/Llama-3.2-3B-Instruct \

6
.buildkite/scripts/run-benchmarks.sh
View File

@@ -11,10 +11,10 @@ cd "$(dirname "${BASH_SOURCE[0]}")/../.."
(which wget && which curl) || (apt-get update && apt-get install -y wget curl)
# run python-based benchmarks and upload the result to buildkite
python3 benchmarks/benchmark_latency.py --output-json latency_results.json 2>&1 | tee benchmark_latency.txt
vllm bench latency --output-json latency_results.json 2>&1 | tee benchmark_latency.txt
bench_latency_exit_code=$?
python3 benchmarks/benchmark_throughput.py --input-len 256 --output-len 256 --output-json throughput_results.json 2>&1 | tee benchmark_throughput.txt
vllm bench throughput --input-len 256 --output-len 256 --output-json throughput_results.json 2>&1 | tee benchmark_throughput.txt
bench_throughput_exit_code=$?
# run server-based benchmarks and upload the result to buildkite
@@ -24,7 +24,7 @@ wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/r
# wait for server to start, timeout after 600 seconds
timeout 600 bash -c 'until curl localhost:8000/v1/models; do sleep 1; done' || exit 1
python3 benchmarks/benchmark_serving.py \
vllm bench serve \
--backend vllm \
--dataset-name sharegpt \
--dataset-path ./ShareGPT_V3_unfiltered_cleaned_split.json \

2
.buildkite/scripts/tpu/run_bm.sh
View File

@@ -77,7 +77,7 @@ done
echo "run benchmark test..."
echo "logging to $BM_LOG"
echo
python benchmarks/benchmark_serving.py \
vllm bench serve \
--backend vllm \
--model $MODEL \
--dataset-name sonnet \