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
..
benchmark.ts	refactor(Benchmarks): cleanup api calls	2026-02-01 05:23:11 +00:00
chat.ts	fix(AI): improved perf via rewrite and streaming logic	2026-03-03 20:51:38 -08:00
collections.ts	feat: curated content update checking	2026-02-11 21:49:46 -08:00
docker.ts	feat: initial commit	2025-06-29 15:51:08 -07:00
downloads.ts	feat: curated content system overhaul	2026-02-11 15:44:46 -08:00
files.ts	feat: curated content system overhaul	2026-02-11 15:44:46 -08:00
kv_store.ts	feat(AI Assistant): custom name option for AI Assistant	2026-03-04 20:05:14 -08:00
maps.ts	feat: [wip] new maps system	2025-11-30 22:29:16 -08:00
ollama.ts	feat(AI): thinking and response streaming	2026-02-18 21:22:53 -08:00
rag.ts	feat(RAG): display embedding queue and improve progress tracking	2026-03-04 20:05:14 -08:00
services.ts	feat: Use friendly app names on Dashboard with open source attribution	2026-01-22 16:43:32 -08:00
system.ts	feat(GPU): warn when GPU passthrough not working and offer one-click fix	2026-03-11 14:08:09 -07:00
util.ts	feat: initial commit	2025-06-29 15:51:08 -07:00
zim.ts	feat: zim content embedding	2026-02-08 13:20:10 -08:00