背景
本地部署DeepSeek-Coder-V2-Lite-Instruct:14b。要求基础的高可用、监控、安全能力。ollama默认只能使用第一张显卡，多个模型同时调用会有bug（ollama ps显示100GPU，但使用CPU推理）；无法高可用
具体方案
多GPU Ollama部署方案，通过系统服务化+负载均衡实现4块4090显卡的并行利用，边缘使用nginx负载均衡。
- 服务器名：AIGC-01
服务器硬件配置：
- CPU：AMD Ryzen Threadripper PRO 3955WX 16-Cores
- GPU：4 x NVIDIA RTX 4090
- MEM：128G
- 模型：DeepSeek-Coder-V2-Lite-Instruct:14b
ollama配置
# 备份ollama
cd /etc/systemd/system/
mv ollama.service ollama.service.bak
# 创建4个独立服务文件（每个GPU对应一个端口）
for i in {0..3}; do
sudo tee /etc/systemd/system/ollama-gpu${i}.service > /dev/null <<EOF
[Unit]
Description=Ollama Service (GPU $i)
[Service]
# 关键参数配置
Environment="CUDA_VISIBLE_DEVICES=$i"
Environment="OLLAMA_HOST=0.0.0.0:$((11434+i))"
ExecStart=/usr/local/bin/ollama serve
Restart=always
User=ollama
Group=ollama
[Install]
WantedBy=multi-user.target
EOF
done
# 重载服务配置
sudo systemctl daemon-reload
# 启动所有GPU实例
sudo systemctl start ollama-gpu{0..3}.service
# 设置开机自启
sudo systemctl enable ollama-gpu{0..3}.service
nginx配置
nginx 需要编译额外模块，用于健康检查
root@sunmax-AIGC-01:/etc/systemd/system# nginx -V
nginx version: nginx/1.24.0
built by gcc 9.4.0 (Ubuntu 9.4.0-1ubuntu1~20.04.2)
built with OpenSSL 1.1.1f 31 Mar 2020
TLS SNI support enabled
configure arguments: --with-http_ssl_module --add-module=./nginx_upstream_check_module
# /etc/nginx/sites-available/mga.maxiot-inc.com.conf
# 在http块中添加（如果放在server外请确保在http上下文中）
log_format detailed '$remote_addr - $remote_user [$time_local] '
'"$request" $status $body_bytes_sent '
'"$http_referer" "$http_user_agent" '
'RT=$request_time URT=$upstream_response_time '
'Host=$host Proto=$server_protocol '
'Header={\"X-Forwarded-For\": \"$proxy_add_x_forwarded_for\", '
'\"X-Real-IP\": \"$remote_addr\", '
'\"User-Agent\": \"$http_user_agent\", '
'\"Content-Type\": \"$content_type\"} '
'SSL=$ssl_protocol/$ssl_cipher '
'Upstream=$upstream_addr '
'Request_Length=$request_length '
'Request_Method=$request_method '
'Server_Name=$server_name '
'Server_Port=$server_port ';
upstream ollama_backend {
server 127.0.0.1:11436;
server 127.0.0.1:11437;
}
server {
listen 443 ssl;
server_name mga.maxiot-inc.com;
ssl_certificate /etc/nginx/ssl/maxiot-inc.com.pem;
ssl_certificate_key /etc/nginx/ssl/maxiot-inc.com.key;
# 访问日志
access_log /var/log/nginx/mga_maxiot_inc_com_access.log detailed;
# 错误日志
error_log /var/log/nginx/mga_maxiot_inc_com_error.log;
# 负载均衡设置，指向 ollama_backend
location / {
proxy_pass http://ollama_backend; # 会在两个服务器之间轮询
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_set_header X-Forwarded-Proto $scheme;
}
}
