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

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
+9 -9
View File
@@ -1,6 +1,6 @@
#!/bin/bash
# This script aims to tune the best server parameter combinations to maximize throughput for given requirement.
# This script aims to tune the best server parameter combinations to maximize throughput for given requirement.
# See details in README (benchmarks/auto_tune/README.md).
TAG=$(date +"%Y_%m_%d_%H_%M")
@@ -56,7 +56,7 @@ start_server() {
local max_num_batched_tokens=$3
local vllm_log=$4
local profile_dir=$5
pkill -f vllm
VLLM_USE_V1=1 VLLM_SERVER_DEV_MODE=1 VLLM_TORCH_PROFILER_DIR=$profile_dir vllm serve $MODEL \
@@ -73,9 +73,9 @@ start_server() {
# wait for 10 minutes...
server_started=0
for i in {1..60}; do
for i in {1..60}; do
RESPONSE=$(curl -s -X GET "http://0.0.0.0:8004/health" -w "%{http_code}" -o /dev/stdout)
STATUS_CODE=$(echo "$RESPONSE" | tail -n 1)
STATUS_CODE=$(echo "$RESPONSE" | tail -n 1)
if [[ "$STATUS_CODE" -eq 200 ]]; then
server_started=1
break
@@ -98,10 +98,10 @@ update_best_profile() {
selected_profile_file=
if [[ "$SYSTEM" == "TPU" ]]; then
selected_profile_file="${sorted_paths[$profile_index]}/*.xplane.pb"
fi
fi
if [[ "$SYSTEM" == "GPU" ]]; then
selected_profile_file="${sorted_paths[$profile_index]}"
fi
fi
rm -f $PROFILE_PATH/*
cp $selected_profile_file $PROFILE_PATH
}
@@ -129,14 +129,14 @@ run_benchmark() {
echo "server started."
fi
echo
echo "run benchmark test..."
meet_latency_requirement=0
# get a basic qps by using request-rate inf
bm_log="$LOG_FOLDER/bm_log_${max_num_seqs}_${max_num_batched_tokens}_requestrate_inf.txt"
prefix_len=$(( INPUT_LEN * MIN_CACHE_HIT_PCT / 100 ))
adjusted_input_len=$(( INPUT_LEN - prefix_len ))
python3 benchmarks/benchmark_serving.py \
vllm bench serve \
--backend vllm \
--model $MODEL \
--dataset-name random \
@@ -169,7 +169,7 @@ adjusted_input_len=$(( INPUT_LEN - prefix_len ))
curl -X POST http://0.0.0.0:8004/reset_prefix_cache
sleep 5
bm_log="$LOG_FOLDER/bm_log_${max_num_seqs}_${max_num_batched_tokens}_requestrate_${request_rate}.txt"
python3 benchmarks/benchmark_serving.py \
vllm bench serve \
--backend vllm \
--model $MODEL \
--dataset-name random \