Indicate compile mode in the benchmark results (#32990)

Signed-off-by: Huy Do <huydhn@gmail.com>
This commit is contained in:
Huy Do
2026-01-30 12:34:36 -08:00
committed by GitHub
parent c3a9752b0c
commit 9ca66ecc10
2 changed files with 42 additions and 3 deletions

View File

@@ -393,6 +393,11 @@ run_serving_tests() {
fi
fi
# save the compilation mode and optimization level on the serving results
# whenever they are set
compilation_config_mode=$(echo "$server_params" | jq -r '."compilation_config.mode" // empty')
optimization_level=$(echo "$server_params" | jq -r '.optimization_level // empty')
# iterate over different QPS
for qps in $qps_list; do
# remove the surrounding single quote from qps
@@ -406,15 +411,15 @@ run_serving_tests() {
for max_concurrency in $max_concurrency_list; do
new_test_name=$test_name"_qps_"$qps"_concurrency_"$max_concurrency
echo " new test name $new_test_name"
# pass the tensor parallel size to the client so that it can be displayed
# on the benchmark dashboard
# pass the tensor parallel size, the compilation mode, and the optimization
# level to the client so that they can be used on the benchmark dashboard
client_command="vllm bench serve \
--save-result \
--result-dir $RESULTS_FOLDER \
--result-filename ${new_test_name}.json \
--request-rate $qps \
--max-concurrency $max_concurrency \
--metadata "tensor_parallel_size=$tp" \
--metadata tensor_parallel_size=$tp compilation_config.mode=$compilation_config_mode optimization_level=$optimization_level \
$client_args $client_remote_args "
echo "Running test case $test_name with qps $qps"