xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-24 15:35:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Benchmarks] auto_tune.sh: Use hostname variable for server requests (#30529)

Browse Source 
Signed-off-by: Kevin Musgrave <kevin.musgrave@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Kevin Musgrave 2025-12-15 17:00:29 -05:00 committed by GitHub
parent 60dbf7d8f1
commit c01d589813
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 11 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
benchmarks/auto_tune/auto_tune.sh
View File

@ -18,6 +18,11 @@ MIN_CACHE_HIT_PCT=${MIN_CACHE_HIT_PCT:-0}
MAX_LATENCY_ALLOWED_MS=${MAX_LATENCY_ALLOWED_MS:-100000000000}
NUM_SEQS_LIST=${NUM_SEQS_LIST:-"128 256"}
NUM_BATCHED_TOKENS_LIST=${NUM_BATCHED_TOKENS_LIST:-"512 1024 2048 4096"}
HOSTNAME=$(hostname)
if [[ -z "$HOSTNAME" ]]; then
echo "Error: Failed to determine hostname." >&2
exit 1
fi
LOG_FOLDER="$BASE/auto-benchmark/$TAG"
RESULT="$LOG_FOLDER/result.txt"
@ -82,6 +87,7 @@ start_server() {
"$MODEL"
"--disable-log-requests"
"--port" "8004"
"--host" "$HOSTNAME"
"--gpu-memory-utilization" "$gpu_memory_utilization"
"--max-num-seqs" "$max_num_seqs"
"--max-num-batched-tokens" "$max_num_batched_tokens"
@ -113,7 +119,7 @@ start_server() {
# since that we should always have permission to send signal to the server process.
kill -0 $server_pid 2> /dev/null || break
RESPONSE=$(curl -s -X GET "http://0.0.0.0:8004/health" -w "%{http_code}" -o /dev/stdout)
RESPONSE=$(curl -s -X GET "http://${HOSTNAME}:8004/health" -w "%{http_code}" -o /dev/stdout)
STATUS_CODE=$(echo "$RESPONSE" | tail -n 1)
if [[ "$STATUS_CODE" -eq 200 ]]; then
server_started=1
@ -173,6 +179,7 @@ run_benchmark() {
--goodput e2el:$MAX_LATENCY_ALLOWED_MS \
--num-prompts 1000 \
--random-prefix-len $prefix_len \
--host "$HOSTNAME" \
--port 8004 &> "$bm_log"
throughput=$(grep "Request throughput (req/s):" "$bm_log" | sed 's/[^0-9.]//g')
e2el=$(grep "P99 E2EL (ms):" "$bm_log" | awk '{print $NF}')
@ -188,7 +195,7 @@ run_benchmark() {
request_rate=$((${throughput%.*} + 1))
while ((request_rate > 0)); do
# clear prefix cache
curl -X POST http://0.0.0.0:8004/reset_prefix_cache
curl -X POST http://${HOSTNAME}:8004/reset_prefix_cache
sleep 5
bm_log="$LOG_FOLDER/bm_log_${max_num_seqs}_${max_num_batched_tokens}_requestrate_${request_rate}.txt"
vllm bench serve \
@ -204,6 +211,7 @@ run_benchmark() {
--goodput e2el:$MAX_LATENCY_ALLOWED_MS \
--num-prompts 100 \
--random-prefix-len $prefix_len \
--host "$HOSTNAME" \
--port 8004 &> "$bm_log"
throughput=$(grep "Request throughput (req/s):" "$bm_log" | sed 's/[^0-9.]//g')
e2el=$(grep "P99 E2EL (ms):" "$bm_log" | awk '{print $NF}')
@ -304,6 +312,7 @@ if (( $(echo "$best_throughput > 0" | bc -l) )); then
--goodput e2el:$MAX_LATENCY_ALLOWED_MS \
--num-prompts 100 \
--random-prefix-len $prefix_len \
--host "$HOSTNAME" \
--port 8004 \
--profile &> "$bm_log"
else