#!/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 # run ingress # dynamo.frontend accepts either --http-port flag or DYN_HTTP_PORT env var (defaults to 8000) python -m dynamo.frontend & # --enforce-eager is added for quick deployment. for production use, need to remove this flag DYN_SYSTEM_PORT=${DYN_SYSTEM_PORT1:-8081} \ CUDA_VISIBLE_DEVICES=0 python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --enforce-eager & DYN_SYSTEM_PORT=${DYN_SYSTEM_PORT2:-8082} \ DYN_VLLM_KV_EVENT_PORT=20081 \ VLLM_NIXL_SIDE_CHANNEL_PORT=20097 \ CUDA_VISIBLE_DEVICES=1 python3 -m dynamo.vllm \ --model Qwen/Qwen3-0.6B \ --enforce-eager \ --is-prefill-worker