xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 07:15:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Reduce initialization time of auto_tune (#23682)

Browse Source 
Signed-off-by: Weida Hong <wdhongtw@google.com>
This commit is contained in:
Weida Hong 2025-09-24 01:34:58 +08:00 committed by GitHub
parent 100b630a60
commit 24e8222745
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
benchmarks/auto_tune/auto_tune.sh
View File

@ -103,10 +103,15 @@ start_server() {
VLLM_USE_V1=1 VLLM_SERVER_DEV_MODE=1 \
vllm serve "${common_args_array[@]}" > "$vllm_log" 2>&1 &
fi
local server_pid=$!
# wait for 10 minutes...
server_started=0
for i in {1..60}; do
# This line checks whether the server is still alive or not,
# 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)
STATUS_CODE=$(echo "$RESPONSE" | tail -n 1)
if [[ "$STATUS_CODE" -eq 200 ]]; then
@ -118,7 +123,7 @@ start_server() {
done
if (( ! server_started )); then
echo "server did not start within 10 minutes. Please check server log at $vllm_log".
echo "server did not start within 10 minutes or crashed. Please check server log at $vllm_log".
return 1
else
return 0