Skip to content
Draft
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
5 changes: 3 additions & 2 deletions scripts/ci/sglang_benchmark_workflow.sh
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,8 @@ if [[ "${TYPE}" == "launch" ]]; then
--max-prefill-tokens 32768 \
--cuda-graph-max-bs 256 \
--page-size 64 \
--attention-backend triton &
--attention-backend triton \
--max-running-requests 128 &
sglang_pid=$!
else
echo "Unknown model_name: ${model_name}"
Expand Down Expand Up @@ -140,4 +141,4 @@ else
echo
echo "========== SGLANG BENCHMARK ${TYPE} FAILED WITH EXIT CODE $exit_code =========="
exit $exit_code
fi
fi
Loading