#!/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 # Set deterministic hash for KV event IDs export PYTHONHASHSEED=0 # Common configuration MODEL="Qwen/Qwen3-0.6B" BLOCK_SIZE=64 # Start frontend with KV routing # The frontend will automatically detect prefill workers and activate an internal prefill router # dynamo.frontend accepts either --http-port flag or DYN_HTTP_PORT env var (defaults to 8000) python -m dynamo.frontend \ --router-mode kv \ --router-reset-states & # two decode workers # --enforce-eager is added for quick deployment. for production use, need to remove this flag CUDA_VISIBLE_DEVICES=0 python3 -m dynamo.vllm \ --model $MODEL \ --block-size $BLOCK_SIZE \ --enforce-eager \ --kv-events-config '{"publisher":"zmq","topic":"kv-events","endpoint":"tcp://*:20080","enable_kv_cache_events":true}'& VLLM_NIXL_SIDE_CHANNEL_PORT=20097 \ CUDA_VISIBLE_DEVICES=1 python3 -m dynamo.vllm \ --model $MODEL \ --block-size $BLOCK_SIZE \ --enforce-eager \ --kv-events-config '{"publisher":"zmq","topic":"kv-events","endpoint":"tcp://*:20081","enable_kv_cache_events":true}' & # two prefill workers # When registered with --is-prefill-worker, these workers are automatically detected # by the frontend, which activates an internal prefill router for KV-aware prefill routing VLLM_NIXL_SIDE_CHANNEL_PORT=20098 \ CUDA_VISIBLE_DEVICES=2 python3 -m dynamo.vllm \ --model $MODEL \ --block-size $BLOCK_SIZE \ --enforce-eager \ --is-prefill-worker \ --kv-events-config '{"publisher":"zmq","topic":"kv-events","endpoint":"tcp://*:20082","enable_kv_cache_events":true}'& VLLM_NIXL_SIDE_CHANNEL_PORT=20099 \ CUDA_VISIBLE_DEVICES=3 python3 -m dynamo.vllm \ --model $MODEL \ --block-size $BLOCK_SIZE \ --enforce-eager \ --is-prefill-worker \ --kv-events-config '{"publisher":"zmq","topic":"kv-events","endpoint":"tcp://*:20083","enable_kv_cache_events":true}'