Frank be878008a2 homepage: update LLM descriptions for model changes ...

frank-large: Qwen3.8-Flash-Next UD-IQ4_XS (87.3 GiB, 200k ctx) →
Qwen3.8-27B IU4/W4A4 (26 GiB, 262k ctx) — the Kairic Edge swap.
frank-medium: Qwen3.8-27B-Uncensored FP8 (~31 GiB) → MXFP4/W4A8
(19.4 GiB) — the MXFP4 checkpoint cut.
frank-small: unchanged (Gemma4-12B QAT).

2026-09-21 20:19:05 -07:00

..

alloy

busybox-static for healthchecks; alloy: rely on the default UI listener

2026-08-22 04:09:04 -07:00

grafana/provisioning

fix(monitoring): llama.cpp reuse ratio, dashboard re-cut for both namespaces, measured prefix-cache granularity

2026-09-20 19:53:14 -07:00

homepage

homepage: update LLM descriptions for model changes

2026-09-21 20:19:05 -07:00

loki

observability configs: loki delete_request_store, prometheus targets, grafana root URL

2026-08-22 03:04:36 -07:00

prometheus

fix(monitoring): scrape node-dankclaw via host.containers.internal

2026-09-21 11:09:03 -07:00

searxng

configure anonymous SearXNG provider defaults

2026-08-25 17:58:22 -07:00