#!/bin/bash # SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. # SPDX-License-Identifier: Apache-2.0 set -e trap 'echo Cleaning up...; kill 0' EXIT MODEL="Qwen/Qwen-Image" # Parse command line arguments EXTRA_ARGS=() while [[ $# -gt 0 ]]; do case $1 in --model) MODEL="$2" shift 2 ;; *) EXTRA_ARGS+=("$1") shift ;; esac done HTTP_PORT="${DYN_HTTP_PORT:-8000}" echo "==========================================" echo "Launching vLLM-Omni Image Generation (1 GPU)" echo "==========================================" echo "Model: $MODEL" echo "Frontend: http://localhost:$HTTP_PORT" echo "==========================================" echo "" echo "Example test command:" echo "" echo " curl http://localhost:${HTTP_PORT}/v1/chat/completions \\" echo " -H 'Content-Type: application/json' \\" echo " -d '{" echo " \"model\": \"${MODEL}\"," echo " \"messages\": [{\"role\": \"user\", \"content\": \"Generate an image of a sunset over mountains.\"}]," echo " \"max_tokens\": 32" echo " }'" echo "" echo "==========================================" python -m dynamo.frontend & FRONTEND_PID=$! sleep 2 echo "Starting Omni worker..." DYN_SYSTEM_PORT=${DYN_SYSTEM_PORT:-8081} \ python -m dynamo.vllm \ --model "$MODEL" \ --omni \ --output-modalities image \ --media-output-fs-url file:///tmp/dynamo_media \ "${EXTRA_ARGS[@]}"