企业内部私有环境部署大模型推理集群时，很容易遇到流量调度混乱、节点负载失衡、会话上下文丢失、接口缺少鉴权防护等一系列问题，单 vLLM 推理节点难以支撑并发请求。本文基于 Ubuntu 22.04 系统环境，搭建 Nginx + vLLM-Semantic-Router + vLLM-Router + vLLM Node 多层推理集群。全文从环境准备、模型拉取、组件分步部署、Nginx SSE 流式反向代理，一直到接口联调验证，完整记录一套可直接复现的落地方案。

架构拓扑

本次部署采用 Nginx + vLLM-Semantic-Router + vLLM-Router + vLLM Node 推理节点的多层分层推理集群架构，实现请求鉴权、负载均衡、语义智能路由、算力负载分流的全流程能力。

架构层级从上至下如下：

• Nginx：作为集群唯一对外入口，提供接口鉴权、请求反向代理、全局负载均衡、SSE 流式响应适配，保障集群安全与流量稳定分发。
• vLLM-Semantic-Router（语义网关）：识别用户请求意图，区分通用对话、代码编写等场景，实现请求的智能分类路由，适配不同业务场景模型。
• vLLM-Router（算力路由层）：监控后端推理节点显存、算力负载，基于一致性哈希策略实现流量均匀分配，支持会话亲和、KV缓存复用，承接上下层流量转发。
• vLLM Node 推理节点：部署大模型推理服务，提供核心的对话、代码生成推理能力，双节点部署实现算力冗余与负载分担。

环境部署

vLLM Node 推理节点部署（双节点）

集群底层算力载体，运行 vLLM 推理服务并加载大模型，负责执行对话、代码生成等实际推理任务。部署双实例，实现算力负载分担与服务冗余。

部署2个独立推理节点，分别绑定5001、5002端口，同时部署5003端口语义识别模型节点，为上层语义路由提供意图识别能力。

1、安装vLLM兼容依赖包，能正常输出版本号即成功。

root@localhost:~# python3 -m venv ~/vllm
root@localhost:~# source ~/vllm/bin/activate

root@localhost:~# pip install -i https://mirrors.cloud.tencent.com/pypi/simple bitsandbytes tiktoken
root@localhost:~# pip install -i https://mirrors.cloud.tencent.com/pypi/simple openvino modelscope vllm
root@localhost:~# python -c "import vllm; print(vllm.__version__)"
0.29.0

2、通过魔搭社区下载轻量化模型，适配本地部署场景，分别用于对话推理、语义意图识别。

root@localhost:~# mkdir -p /data/model/

# 用于对话的模型
root@localhost:~# modelscope download --model Qwen/Qwen2.5-0.5B-Instruct --local_dir /data/model/qwen2.5

# 用于vLLM-Semantic-Router语义检查模型
root@localhost:~# modelscope download --model gongjy/minimind-3 --local_dir /data/model/minimind3

root@localhost:/data/model# ls -lh
total 8.0K
drwxr-xr-x 3 root root 4.0K Sep 10 17:25 minimind3
drwxr-xr-x 2 root root 4.0K Sep 10 17:23 qwen2.5

开启离线模式、配置模型基础参数，分别准备三台Ubuntu系统，其中每台服务器有1-5颗GPU显卡，启动三个节点服务。

root@localhost:~# export HF_HUB_OFFLINE=1

# 节点 1 端口 5001
root@localhost:~# vllm serve /data/model/qwen2.5 \
  --host 127.0.0.1 \
  --port 5001 \
  --trust-remote-code \
  --dtype bfloat16 \
  --max-model-len 512 \
  --tensor-parallel-size 1

# 节点 2 端口 5002
root@localhost:~# vllm serve /data/model/qwen2.5 \
  --host 127.0.0.1 \
  --port 5002 \
  --trust-remote-code \
  --dtype bfloat16 \
  --max-model-len 512 \
  --tensor-parallel-size 1

# 语义检查模型 端口5003
root@localhost:~# vllm serve /data/model/qwen2.5 \
  --host 127.0.0.1 \
  --port 5003 \
  --trust-remote-code \
  --dtype bfloat16 \
  --max-model-len 512 \
  --tensor-parallel-size 1

vLLM-Router（算力路由层）

vLLM-Router为算力负载路由核心，负责监控后端推理节点负载、实现流量均匀分发，支持会话亲和与KV缓存复用，承接语义网关的请求流量。

1、安装路由节点。

root@localhost:~# python3 -m venv vLLM-Router
root@localhost:~# source vLLM-Router/bin/activate
root@localhost:~# pip install -i https://mirrors.cloud.tencent.com/pypi/simple/ vllm-router

2、采用一致性哈希策略，绑定对应推理节点，实现会话固定路由。

# 路由节点1：对接5001通用对话节点 端口6001
root@localhost:~# vllm-router \
--host 127.0.0.1 \
--port 6001 \
--worker-urls http://127.0.0.1:5001 \
--policy consistent_hash

# 路由节点2：对接5002代码推理节点 端口6002
root@localhost:~# vllm-router \
--host 127.0.0.1 \
--port 6002 \
--worker-urls http://127.0.0.1:5002 \
--policy consistent_hash

3、测试可用性，带上X-Session-ID 同一个 session-id 永远路由到同一个 vllm 后端，实现会话亲和、复用 KV 缓存。

root@localhost:~# curl http://127.0.0.1:6001/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-Session-ID: session-001" \
  -d '{
    "model": "qwen3",
    "messages": [
      {"role": "user", "content": "你好"}
    ],
    "temperature": 0.7,
    "max_tokens": 128
  }'

vLLM-Semantic-Router（语义网关）

上层业务路由，解析用户输入识别请求意图，区分普通闲聊、代码编写等场景，按语义规则将请求转发到对应的算力路由后端，实现按业务场景智能分流。

此处的网关服务只能在Docker容器内，无法直接在物理机中运行，此处只提供一个正确的配置文件仅供参考。

1、安装语义网关服务，并调用启动命令生成默认配置文件。

root@localhost:~# python3 -m venv vsr
root@localhost:~# source vsr/bin/activate
root@localhost:~# pip install -i https://mirrors.cloud.tencent.com/pypi/simple/ vllm-sr
root@localhost:~# vllm-sr serve

2、修改生成的config.yaml（对接下层 vllm-router，地址127.0.0.1:8001）

替换为以下完整配置，对接下层算力路由节点，定义语义路由规则：

version: v0.3
listeners:
  - name: http-7001
    address: 0.0.0.0
    port: 7001
    timeout: 300s

providers:
  defaults:
    default_model: qwen-0.5b
  models:
    # 语义识别模型 minimind（图中5003端口 minimind-3）
    - name: minimind
      provider_model_id: minimind
      api_format: openai
      backend_refs:
        - name: minimind-backend
          endpoint: http://127.0.0.1:5003/v1
          protocol: http
          weight: 100
    # 第一个路由节点6001：普通聊天
    - name: qwen-0.5b
      provider_model_id: qwen-0.5b
      api_format: openai
      backend_refs:
        - name: router-6001
          endpoint: http://127.0.0.1:6001/v1
          protocol: http
          weight: 100
    # 第二个路由节点6002：代码编写
    - name: qwen-code
      provider_model_id: qwen-code
      api_format: openai
      backend_refs:
        - name: router-6002
          endpoint: http://127.0.0.1:6002/v1
          protocol: http
          weight: 100

routing:
  # 预先定义自定义信号 code_intent
  signals:
    embeddings:
      - name: code_intent
        threshold: 0.7
        aggregation_method: max
        candidates:
          - "写代码"
          - "编写脚本"
          - "python代码"
          - "java代码"
          - "js代码"
          - "函数实现"
          - "算法编写"
          - "代码调试"
          - "代码改错"
          - "写程序"
          - "代码实现"
          - "写一段代码"

  modelCards:
    - name: minimind
      description: "语义识别模型，用于意图判断"
      capabilities:
        - semantic_routing
    - name: qwen-0.5b
      description: "通用对话模型，普通聊天，路由6001"
      capabilities:
        - chat
    - name: qwen-code
      description: "代码专用模型，代码编写，路由6002"
      capabilities:
        - coding

  decisions:
    # 代码编写意图 → 路由到6002
    - name: route_code_writing
      description: "用户请求编写代码、脚本、程序，路由到代码专用router 6002"
      priority: 100
      rules:
        operator: AND
        conditions:
          - type: embedding
            name: code_intent
      modelRefs:
        - model: qwen-code

    # 兜底：普通聊天 → 路由到6001
    - name: default_chat
      description: "默认普通聊天场景，路由到6001"
      priority: 10
      rules:
        operator: AND
        conditions: []
      modelRefs:
        - model: qwen-0.5b

global:
  health_check:
    interval_seconds: 10

3、前台检测文档可用性，并运行。

root@localhost:~# vllm-sr validate --config /root/config.yaml
2026-09-10 17:25:56,551 - INFO - ============================================================
2026-09-10 17:25:56,551 - INFO - vLLM Semantic Router - Validate Configuration
2026-09-10 17:25:56,551 - INFO - ============================================================
2026-09-10 17:25:56,551 - INFO - Validating: /root/config.yaml
2026-09-10 17:25:56,551 - INFO - 
2026-09-10 17:25:56,558 - INFO - Configuration parsed successfully
2026-09-10 17:25:56,558 - INFO -   Version: v0.3
2026-09-10 17:25:56,559 - INFO -   Listeners: 1
2026-09-10 17:25:56,559 - INFO -   Decisions: 2
2026-09-10 17:25:56,559 - INFO -   Models: 3
2026-09-10 17:25:56,559 - INFO - Validating user configuration...
2026-09-10 17:25:56,559 - INFO - Configuration validation passed
2026-09-10 17:25:56,559 - INFO - ============================================================
2026-09-10 17:25:56,559 - INFO - Configuration is valid!
2026-09-10 17:25:56,559 - INFO - ============================================================
2026-09-10 17:25:56,559 - INFO - 
Configuration summary:
2026-09-10 17:25:56,559 - INFO -   Version: v0.3
2026-09-10 17:25:56,559 - INFO -   Listeners: 1
2026-09-10 17:25:56,559 - INFO -   Embedding signals: 1
2026-09-10 17:25:56,559 - INFO -   Decisions: 2
2026-09-10 17:25:56,559 - INFO -   Models: 3
2026-09-10 17:25:56,559 - INFO -   Default model: qwen-0.5b
2026-09-10 17:25:56,559 - INFO - 

root@localhost:~# vllm-sr serve --config /root/config.yaml
2026-09-10 17:26:16,703 - INFO - Using config file: /root/config.yaml
2026-09-10 17:26:16,713 - INFO - Created effective runtime config: /root/.vllm-sr/runtime-config.yaml

       █     █     █▄   ▄█
 ▄▄ ▄█ █     █     █ ▀▄▀ █
  █▄█▀ █     █     █     █
   ▀▀  ▀▀▀▀▀ ▀▀▀▀▀ ▀     ▀
  Semantic Router
  Intelligent Routing for Mixture-of-Models

2026-09-10 17:26:16,721 - INFO - Starting vLLM Semantic Router
2026-09-10 17:26:16,721 - INFO - Runtime stack: vllm-sr (port offset 0)
2026-09-10 17:26:16,721 - INFO - Config file: /root/config.yaml
2026-09-10 17:26:16,721 - INFO - Configured listeners:
2026-09-10 17:26:16,721 - INFO -   - http-7001: 0.0.0.0:7001
2026-09-10 17:26:16,721 - INFO - Runtime topology: split
2026-09-10 17:26:16,721 - ERROR - Docker not found in PATH
2026-09-10 17:26:16,721 - ERROR - Please install Docker Desktop or Docker Engine to use this tool
2026-09-10 17:26:16,722 - ERROR - 
2026-09-10 17:26:16,722 - ERROR - Installation instructions:
2026-09-10 17:26:16,722 - ERROR -   Docker: https://docs.docker.com/get-docker/

Nginx（反向代理及鉴权）

Nginx作为集群唯一对外入口，实现接口基础鉴权、SSE流式响应适配、双路由节点负载均衡、请求超时统一管控，替代语义网关直接承接外部流量，简化部署架构。

Nginx 入口端口：11433，保留基础鉴权，去掉语义网关，Nginx 直接负载均衡分发流量到两台 router。

1、安装Mginx组件，并编辑配置文件启用反向代理功能。

root@localhost:~# apt install -y nginx apache2-utils
root@localhost:~# vim /etc/nginx/nginx.conf

user www-data;
worker_processes auto;
pid /run/nginx.pid;
include /etc/nginx/modules-enabled/*.conf;

events {
        worker_connections 768;
}

http {
        sendfile on;
        tcp_nopush on;
        types_hash_max_size 2048;
        include /etc/nginx/mime.types;
        default_type application/octet-stream;

        ssl_protocols TLSv1 TLSv1.1 TLSv1.2 TLSv1.3;
        ssl_prefer_server_ciphers on;

        access_log /var/log/nginx/access.log;
        error_log /var/log/nginx/error.log;

        gzip on;

        include /etc/nginx/conf.d/*.conf;
        include /etc/nginx/sites-enabled/*;

# 后端真实vllm-router地址
upstream router_real_6001 {
    server 127.0.0.1:29000;
}
upstream router_real_6002 {
    server 127.0.0.1:29001;
}

# 内部端口6001 仅本机127.0.0.1可访问
server {
    listen 127.0.0.1:6001;
    server_name localhost;

    location / {
        proxy_pass http://router_real_6001;

        # SSE流式必备参数
        proxy_http_version 1.1;
        proxy_set_header Connection "";
        proxy_buffering off;
        proxy_cache off;

        proxy_connect_timeout 300s;
        proxy_send_timeout 300s;
        proxy_read_timeout 300s;
    }
}

# 内部端口6002 仅本机127.0.0.1可访问
server {
    listen 127.0.0.1:6002;
    server_name localhost;

    location / {
        proxy_pass http://router_real_6002;

        # SSE流式必备参数
        proxy_http_version 1.1;
        proxy_set_header Connection "";
        proxy_buffering off;
        proxy_cache off;

        proxy_connect_timeout 300s;
        proxy_send_timeout 300s;
        proxy_read_timeout 300s;
    }
}

# 对外唯一入口：11433，鉴权 + 负载均衡分发到内部6001/6002
upstream vllm_main_pool {
    least_conn;
    server 127.0.0.1:6001 max_fails=2 fail_timeout=15s;
    server 127.0.0.1:6002 max_fails=2 fail_timeout=15s;
    keepalive 16;
}

server {
    listen 11433;
    server_name localhost;

    auth_basic "Restricted Access";
    auth_basic_user_file /etc/nginx/.htpasswd;

    location / {
        proxy_pass http://vllm_main_pool;

        # SSE流式必备
        proxy_http_version 1.1;
        proxy_set_header Connection "";
        proxy_buffering off;
        proxy_cache off;

        # 透传客户端信息
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;

        proxy_connect_timeout 300s;
        proxy_send_timeout 300s;
        proxy_read_timeout 300s;
    }
}
}

2、校验 Nginx 语法可用性。

root@localhost:~# nginx -t
nginx: the configuration file /etc/nginx/nginx.conf syntax is ok
nginx: configuration file /etc/nginx/nginx.conf test is successful

3、创建鉴权账号。

root@localhost:~# htpasswd -c /etc/nginx/.htpasswd vllmuser

root@localhost:~# chown www-data:www-data /etc/nginx/.htpasswd
root@localhost:~# chmod 644 /etc/nginx/.htpasswd

root@localhost:~# nginx -t
root@localhost:~# nginx -s reload

4、测试访问示例，此处使用-u指定用户名及密码。

root@localhost:~# curl http://127.0.0.1:11433/v1/chat/completions \
-u vllmuser:1234 \
-H "Content-Type: application/json" \
-d '{
"model": "qwen2.5",
"messages": [{"role":"user","content":"你好"}],
"stream": true
}'