Fix obico model_cache mount path to /model_cache/ml_api

obico/docker-compose.yml

@@ -7,9 +7,9 @@ services:
       - obico-internal
 
   obico:
-    # Use :cuda for NVIDIA GPU acceleration, :latest for CPU-only
-    # Note: :cuda tag has had occasional CUDNN/ONNX version issues after updates.
-    # If obico fails to start after an image update, switch to :latest temporarily.
+    # :cuda tag attempts GPU but falls back to CPU if CUDA version mismatch
+    # (libcudart.so.11.0 required; GTX 1660 SUPER with driver 590 has CUDA 12).
+    # ML inference still works on CPU - adequate for a single printer.
     image: ghcr.io/imagegenius/obico:cuda
     container_name: obico
     restart: unless-stopped
@@ -30,7 +30,7 @@ services:
       - ACCOUNT_ALLOW_SIGN_UP=False
     volumes:
       - /srv/obico/config:/config
-      - /srv/obico/config/model_cache:/model_cache
+      - /srv/obico/config/model_cache:/model_cache/ml_api
     ports:
       - "3334:3334"
     deploy: