Chris Sherwood f7515d8e19 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 21:05:49 +00:00
..
zim	fix(Settings): standardize manifest fetching behavior	2026-02-11 16:13:21 -08:00
apps.tsx	fix(Settings): rename port column in Apps Settings	2026-02-03 23:33:49 -08:00
benchmark.tsx	feat(AI Assistant): custom name option for AI Assistant	2026-03-04 20:05:14 -08:00
legal.tsx	fix(legal): update Legal Notices to Apache 2.0 license and add Qdrant attribution	2026-03-04 20:05:14 -08:00
maps.tsx	fix(Settings): standardize manifest fetching behavior	2026-02-11 16:13:21 -08:00
models.tsx	feat(GPU): warn when GPU passthrough not working and offer one-click fix	2026-03-11 21:05:49 +00:00
system.tsx	feat(GPU): warn when GPU passthrough not working and offer one-click fix	2026-03-11 21:05:49 +00:00
update.tsx	fix: update channel flexibility	2026-03-05 04:06:56 +00:00