agg_router.sh

#!/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

HTTP_PORT="${DYN_HTTP_PORT:-8000}"
echo "=========================================="
echo "Launching Aggregated + KV Routing (2 GPUs)"
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\": \"Explain why Roger Federer is considered one of the greatest tennis players of all time\"}],"
echo "      \"max_tokens\": 32"
echo "    }'"
echo ""
echo "=========================================="

# run frontend + KV 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 &

# run workers
# --enforce-eager is added for quick deployment. for production use, need to remove this flag
#
# If multiple workers are launched, they must not share the same system/metrics port.
# Use DYN_SYSTEM_PORT{1,2} so tests/launchers can provide a simple numbered port set.
#
DYN_SYSTEM_PORT=${DYN_SYSTEM_PORT1:-8081} \
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}' &

DYN_SYSTEM_PORT=${DYN_SYSTEM_PORT2:-8082} \
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}'