#!/bin/bash # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved. # SPDX-License-Identifier: Apache-2.0 set -e trap 'echo Cleaning up...; kill 0' EXIT # Default model MODEL="Qwen/Qwen3-0.6B" # Parse command line arguments EXTRA_ARGS=() while [[ $# -gt 0 ]]; do case $1 in --model) MODEL="$2" shift 2 ;; *) EXTRA_ARGS+=("$1") shift ;; esac done # run ingress # dynamo.frontend accepts either --http-port flag or DYN_HTTP_PORT env var (defaults to 8000) python -m dynamo.frontend & # run worker # --enforce-eager is added for quick deployment. for production use, need to remove this flag DYN_SYSTEM_PORT=${DYN_SYSTEM_PORT:-8081} \ python -m dynamo.vllm --model "$MODEL" --enforce-eager --connector none "${EXTRA_ARGS[@]}"