2 Commits

Author	SHA1	Message	Date
Simon Gardling	096ffeb943	llama-cpp: xmrig + grafana hooks	2026-04-03 00:17:17 -04:00
Simon Gardling	df15be01ea	llama-cpp: pause xmrig during active inference requests ... Add sidecar service that polls llama-cpp /slots endpoint every 3s. When any slot is processing, stops xmrig. Restarts xmrig after 10s grace period when all slots are idle. Handles unreachable llama-cpp gracefully (leaves xmrig untouched).	2026-04-02 17:43:07 -04:00