From 779492e8b40084032e218c89f211e60527a28b98 Mon Sep 17 00:00:00 2001 From: "Danilo M." Date: Wed, 28 Oct 2026 09:15:55 +0100 Subject: ai: unload llama's model from the engine row The llama.cpp row offers Unload while a model is loaded. It posts to the router's /models/unload, which frees the VRAM and leaves llama-server up, so its web UI stays available; the engines themselves are still never stopped from here. The answer is not read: the next poll shows the row without a model, or with it if the unload failed. Co-Authored-By: Claude Opus 5.5 --- desktop/modules/ai/README.md | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'desktop/modules/ai/README.md') diff --git a/desktop/modules/ai/README.md b/desktop/modules/ai/README.md index 5aec615..e71159b 100644 --- a/desktop/modules/ai/README.md +++ b/desktop/modules/ai/README.md @@ -8,8 +8,10 @@ The tile counts running apps and names any engine that is generating, or says ## Engines llama.cpp (`llama-server`, router mode, port 8181) and stable-diffusion.cpp -(`sd-server`, started by `~/bin/sd-webui`). Both rows are read-only: each -engine also serves a web UI, and stopping it would take that down. +(`sd-server`, started by `~/bin/sd-webui`). Neither is ever stopped: each +engine also serves a web UI, and stopping it would take that down. llama's +row offers Unload while a model is loaded, `POST /models/unload` to the +router, which frees the VRAM and leaves the server up. llama's state comes from its API: `/models` for the loaded model, then `/slots?model=&autoload=false` for whether a slot is processing. The -- cgit v1.2.3