Skip to content

[ROCm] Tweak the benchmark script to run on ROCm #14252

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Apr 4, 2025
Merged

[ROCm] Tweak the benchmark script to run on ROCm #14252

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3789f2c
[ROCm] Tweak the benchmark script to run on ROCm
huydhn Mar 5, 2025
97a2965
Merge branch 'main' into add-rocm-benchmark
huydhn Mar 5, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 21 additions & 6 deletions .buildkite/nightly-benchmarks/scripts/run-performance-benchmarks.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,15 +10,24 @@ set -x
set -o pipefail

check_gpus() {
# check the number of GPUs and GPU type.
declare -g gpu_count=$(nvidia-smi --list-gpus | wc -l)
if command -v nvidia-smi; then
# check the number of GPUs and GPU type.
declare -g gpu_count=$(nvidia-smi --list-gpus | wc -l)
elif command -v amd-smi; then
declare -g gpu_count=$(amd-smi list | grep 'GPU' | wc -l)
fi

if [[ $gpu_count -gt 0 ]]; then
echo "GPU found."
else
echo "Need at least 1 GPU to run benchmarking."
exit 1
fi
declare -g gpu_type=$(nvidia-smi --query-gpu=name --format=csv,noheader | awk '{print $2}')
if command -v nvidia-smi; then
declare -g gpu_type=$(nvidia-smi --query-gpu=name --format=csv,noheader | awk '{print $2}')
elif command -v amd-smi; then
declare -g gpu_type=$(amd-smi static -g 0 -a | grep 'MARKET_NAME' | awk '{print $2}')
fi
echo "GPU type is $gpu_type"
}

Expand Down Expand Up @@ -90,9 +99,15 @@ kill_gpu_processes() {


# wait until GPU memory usage smaller than 1GB
while [ "$(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits | head -n 1)" -ge 1000 ]; do
sleep 1
done
if command -v nvidia-smi; then
while [ "$(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits | head -n 1)" -ge 1000 ]; do
sleep 1
done
elif command -v amd-smi; then
while [ "$(amd-smi metric -g 0 | grep 'USED_VRAM' | awk '{print $2}')" -ge 1000 ]; do
sleep 1
done
fi

# remove vllm config file
rm -rf ~/.config/vllm
Expand Down