obico's own comment already notes its :cuda tag falls back to CPU
inference on this driver/GPU combo, but it was still reserving 826MB
of VRAM it never used productively. That squeeze was forcing ollama
to offload only 20/29 model layers to GPU, pushing the rest onto CPU
and causing severe latency (multi-minute LLM calls) that stalled
SUB/WAVE's track picking.
Claude-Session: https://claude.ai/code/session_01L7Rwa6guD5wK8F8tWQwcJX
Model weights (~193MB each, darknet + onnx) are stored at
/srv/obico/config/model_cache/ and mounted at /model_cache in the
container since they are not baked into the imagegenius image.
imagegenius monolithic image with NVIDIA GPU (GTX 1660 SUPER) via cuda tag.
Includes internal Redis, npm-network for reverse proxy, DJANGO_SECRET_KEY
as env var placeholder for Portainer.
poprhythm