[Feature] Machine Learning using Intel NPU in OpenVINO on supported Core Ultra Processors

I have searched the existing feature requests to make sure this is not a duplicate request.


• Yes

The feature


I have installed the drivers regarding the Release notes on my Ubuntu 24.04.
• The /dev/accel/accel0 device is available on the host system now. I attached it to the Immich machine learning image by adding a further device with
• /dev/accel:/dev/accel

This doesn‘t seem to be enough, to enable it in the Immich ml image for openvino.
There will be more and more of the Core Ultra CPU with integrated NPU on the market.

it would be nice to have this working in the container.


Platform


• Server
• Web
• Mobile