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

Enable aarch64 CPU performance benchmarks (#26494)

Browse Source 
Signed-off-by: Ioana Ghiban <ioana.ghiban@arm.com>
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
Co-authored-by: Ioana Ghiban <ioana.ghiban@arm.com>
Co-authored-by: Fadi Arafeh <fadi.arafeh@arm.com>
This commit is contained in:
Li, Jiang
2025-12-19 20:16:18 +08:00
committed by GitHub
parent 455949675d
commit 420ba2dbb6
6 changed files with 213 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
.buildkite/performance-benchmarks/scripts/run-performance-benchmarks.sh Normal file → Executable file
View File

@@ -49,7 +49,11 @@ check_cpus() {
echo "Need at least 1 NUMA to run benchmarking."
exit 1
fi
declare -g gpu_type="cpu"
if [[ "$(uname -m)" == "aarch64" ]] || [[ "$(uname -m)" == "arm64" ]]; then
declare -g gpu_type="arm64-cpu"
else
declare -g gpu_type="cpu"
fi
echo "GPU type is $gpu_type"
}
@@ -207,8 +211,8 @@ run_latency_tests() {
# check if there is enough GPU to run the test
tp=$(echo "$latency_params" | jq -r '.tensor_parallel_size')
if [ "$ON_CPU" == "1" ]; then
pp=$(echo "$latency_params" | jq -r '.pipeline_parallel_size')
if [[ "$ON_CPU" == "1" ]]; then
pp=$(echo "$latency_params" | jq -r '.pipeline_parallel_size // 1')
world_size=$(($tp*$pp))
if [[ $numa_count -lt $world_size && -z "${REMOTE_HOST}" ]]; then
echo "Required world-size $world_size but only $numa_count NUMA nodes found. Skip testcase $test_name."
@@ -276,8 +280,8 @@ run_throughput_tests() {
# check if there is enough GPU to run the test
tp=$(echo "$throughput_params" | jq -r '.tensor_parallel_size')
if [ "$ON_CPU" == "1" ]; then
pp=$(echo "$throughput_params" | jq -r '.pipeline_parallel_size')
if [[ "$ON_CPU" == "1" ]]; then
pp=$(echo "$throughput_params" | jq -r '.pipeline_parallel_size // 1')
world_size=$(($tp*$pp))
if [[ $numa_count -lt $world_size && -z "${REMOTE_HOST}" ]]; then
echo "Required world-size $world_size but only $numa_count NUMA nodes found. Skip testcase $test_name."
@@ -393,8 +397,8 @@ run_serving_tests() {
# check if there is enough resources to run the test
tp=$(echo "$server_params" | jq -r '.tensor_parallel_size')
if [ "$ON_CPU" == "1" ]; then
pp=$(echo "$server_params" | jq -r '.pipeline_parallel_size')
if [[ "$ON_CPU" == "1" ]]; then
pp=$(echo "$server_params" | jq -r '.pipeline_parallel_size // 1')
world_size=$(($tp*$pp))
if [[ $numa_count -lt $world_size && -z "${REMOTE_HOST}" ]]; then
echo "Required world-size $world_size but only $numa_count NUMA nodes found. Skip testcase $test_name."
@@ -496,9 +500,9 @@ run_serving_tests() {
main() {
local ARCH
ARCH=''
if [ "$ON_CPU" == "1" ];then
check_cpus
ARCH='-cpu'
if [[ "$ON_CPU" == "1" ]]; then
check_cpus
ARCH="-$gpu_type"
else
check_gpus
ARCH="$arch_suffix"