AJ Isaacs 174db1e5db feat: per-model failure tracking to avoid unnecessary full restarts ...

Individual model probe failures are now tracked separately from router
health failures. Models get a grace period after loading, and persistently
failing models are unloaded and put in cooldown rather than triggering a
full service restart. Only router-level health failures cause restarts.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-08 12:09:07 -05:00

llamacpp-watchdog.py

feat: per-model failure tracking to avoid unnecessary full restarts

2026-02-08 12:09:07 -05:00

llamacpp-watchdog.service

Initial commit: llama.cpp watchdog service

2026-02-06 22:47:12 -05:00

Description

No description provided

31 KiB

Languages

Python 100%