Initial commit: llama.cpp watchdog service
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>
This commit is contained in:
@@ -0,0 +1,18 @@
|
||||
[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
|
||||
Reference in New Issue
Block a user