agg_router.sh 574 Bytes
Newer Older
Alec's avatar
Alec committed
1
2
3
4
5
6
7
8
9
10
#!/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
python -m dynamo.frontend --router-mode kv &

# run workers
11
# --enforce-eager is added for quick deployment. for production use, need to remove this flag
12
CUDA_VISIBLE_DEVICES=0 python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --enforce-eager --connector none &
Alec's avatar
Alec committed
13

14
CUDA_VISIBLE_DEVICES=1 python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --enforce-eager --connector none