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/AiPage.qml | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'desktop/modules/ai/AiPage.qml') diff --git a/desktop/modules/ai/AiPage.qml b/desktop/modules/ai/AiPage.qml index e89132a..369c1b5 100644 --- a/desktop/modules/ai/AiPage.qml +++ b/desktop/modules/ai/AiPage.qml @@ -12,7 +12,8 @@ import QtQuick import "../.." -// Engines are read-only: stopping either would take its web UI down with it. +// Engines are never stopped, that would take their web UI down with them; +// llama's model can be unloaded, which frees the VRAM and leaves the server up. Column { id: page @@ -42,6 +43,8 @@ Column { return modelData.name === "llama" ? "No model loaded" : "Running"; return (modelData.busy ? "Generating" : "Idle") + " ยท " + modelData.model; } + action: modelData.name === "llama" && modelData.model !== "" ? "Unload" : "" + onTriggered: page.ai.unload(modelData.model) } } -- cgit v1.2.3