Norbert d678a4d3d4 feat: ollama VRAM status + model loading/pinning on switch ...

- Show loaded models with VRAM usage bar (24GB 3090)
- On mode switch: unload old model, load+pin target model (keep_alive=-1m)
- Loading banner with spinner (polls faster at 2s while loading)
- Lab model changes also trigger model swap when in lab mode
- Manual load/unload API endpoints

2026-02-18 19:47:22 +00:00

11 KiB

Raw Blame History

View Raw