Skip to content
Open
Changes from all commits
Commits
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
7 changes: 6 additions & 1 deletion benchmarks/llm/perf.sh
Original file line number Diff line number Diff line change
Expand Up @@ -212,6 +212,11 @@ echo "Concurrency levels: ${concurrency_array[@]}"
for concurrency in "${concurrency_array[@]}"; do
echo "Run concurrency: $concurrency"

# Create a subdirectory for this concurrency level
# The plot script expects subdirectories named -concurrency<number>
concurrency_dir="${artifact_dir}/-concurrency${concurrency}"
mkdir -p "${concurrency_dir}"

# NOTE: For Dynamo HTTP OpenAI frontend, use `nvext` for fields like
# `ignore_eos` since they are not in the official OpenAI spec.
aiperf profile \
Expand All @@ -234,7 +239,7 @@ for concurrency in "${concurrency_array[@]}"; do
--warmup-request-count $(($concurrency*2)) \
--num-dataset-entries $(($concurrency*12)) \
--random-seed 100 \
--artifact-dir ${artifact_dir} \
--artifact-dir ${concurrency_dir} \
--ui simple \
-v \
-H 'Authorization: Bearer NOT USED' \
Expand Down
Loading