From 52d6aab526bce963e228fc4503f11a619d33698b Mon Sep 17 00:00:00 2001 From: "Danilo M." Date: Fri, 23 Oct 2026 13:58:45 +0200 Subject: agents: llama-server's router unloads with POST /models/unload The counterpart of /models/load, measured: the same body, answers {"success":true}, and the next request loads the model again. sd-webui now calls it before starting sd-server, because a resident Gemma left Pony 1.1 GB of 12 GB and its first step failed. Co-Authored-By: Claude Opus 5.5 --- AGENTS.md | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/AGENTS.md b/AGENTS.md index 35f6356..76a7bb8 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -383,7 +383,10 @@ changing that component. The ones that generalise: the loaded model answers 400 `model is already running`, and an unknown id 404; both measured. With `--models-max 1` a load swaps out the resident model for every client, so the assistant page does it only on a - click. + click. `POST /models/unload` with the same body frees it (answers + `{"success":true}`, measured); the next request for it loads it again. + `sd-webui` unloads whatever is loaded before starting sd-server: a resident + Gemma left Pony 1.1 GB of 12 GB and its first step failed. - **`busctl get-property` escapes non-ASCII as octal.** A name with an accented letter reads `s "Do\303\250r"`-style, which no shell builtin decodes. `busctl --json=short` returns real UTF-8; `userctl` pipes it -- cgit v1.2.3