Monitors llama-server health with multi-phase checks (zombie detection, health endpoint, loaded model probing) and auto-restarts via systemd or manual relaunch on consecutive failures. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
19 lines
331 B
Desktop File
19 lines
331 B
Desktop File
[Unit]
|
|
Description=llama.cpp Watchdog Service
|
|
After=network.target
|
|
|
|
[Service]
|
|
Type=simple
|
|
User=aj
|
|
ExecStart=/usr/bin/python3 /home/aj/llamacpp-watchdog/llamacpp-watchdog.py
|
|
Restart=always
|
|
RestartSec=10
|
|
|
|
# Logging
|
|
StandardOutput=journal
|
|
StandardError=journal
|
|
SyslogIdentifier=llamacpp-watchdog
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target
|