Chris Sherwood 650ae407f3 feat(GPU): warn when GPU passthrough not working and offer one-click fix ... Ollama can silently run on CPU even when the host has an NVIDIA GPU, resulting in ~3 tok/s instead of ~167 tok/s. This happens when Ollama was installed before the GPU toolkit, or when the container was recreated without proper DeviceRequests. Users had zero indication. Adds a GPU health check to the system info API response that detects when the host has an NVIDIA runtime but nvidia-smi fails inside the Ollama container. Shows a warning banner on the System Information and AI Settings pages with a one-click "Reinstall AI Assistant" button that force-reinstalls Ollama with GPU passthrough. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-03-11 14:08:09 -07:00
..
app	feat: [wip] native AI chat interface	2026-01-31 20:39:49 -08:00
components	fix(AI): allow force refresh of models list	2026-03-11 14:08:09 -07:00
context	feat: container controls & convienience scripts	2025-08-08 15:07:32 -07:00
css	feat: alert and button styles redesign	2025-11-30 23:32:16 -08:00
hooks	feat(RAG): display embedding queue and improve progress tracking	2026-03-04 20:05:14 -08:00
layouts	feat(AI Assistant): custom name option for AI Assistant	2026-03-04 20:05:14 -08:00
lib	fix(AI): allow force refresh of models list	2026-03-11 14:08:09 -07:00
pages	feat(GPU): warn when GPU passthrough not working and offer one-click fix	2026-03-11 14:08:09 -07:00
providers	feat: improve global error reporting with user notifs	2026-02-04 22:58:21 -08:00
tsconfig.json	fix(Docs): documentation renderer fixes	2025-12-23 16:00:33 -08:00