test server

ollama.service

@@ -0,0 +1,37 @@
+[Unit]
+Description=Ollama Server
+After=network-online.target
+Wants=network-online.target
+StartLimitIntervalSec=0
+
+[Service]
+Type=exec
+ExecStart=/usr/local/bin/ollama serve
+User=aiserver
+Group=aiserver
+Restart=always
+RestartSec=3
+Environment="OLLAMA_HOST=0.0.0.0:11434"
+Environment="OLLAMA_KEEP_ALIVE=24h"
+Environment="OLLAMA_NUM_PARALLEL=2"
+Environment="OLLAMA_MAX_LOADED_MODELS=2"
+Environment="OLLAMA_FLASH_ATTENTION=1"
+Environment="CUDA_VISIBLE_DEVICES=0"
+Environment="OLLAMA_GPU_OVERHEAD=0.2"
+WorkingDirectory=/opt/ai-server
+StandardOutput=journal
+StandardError=journal
+
+# Security settings
+NoNewPrivileges=true
+PrivateTmp=true
+ProtectSystem=strict
+ProtectHome=true
+ReadWritePaths=/opt/ai-server
+
+# Resource limits for RTX 2060
+MemoryMax=8G
+CPUQuota=400%
+
+[Install]
+WantedBy=multi-user.target