## Description - Quantized the CLIP text encoder - Moved preprocessing and postprocessing of face detection inside the model - Optimised the ONNX models more wherever possible - Created a place in infra for ML version control of sorts ## Tests Have tested the changes on mobile, but not on desktop. Please carefully review the changes on desktop, especially regarding the face detection post-processing, more specifically the image (re-)size correction.
Infra
Various knick-knacks that we use when hosting our servers.
These are not needed for running Ente's server or for self-hosting, these are just additional services we run to make our infrastructure more robust. As such, it's unlikely that you'll find the pieces here directly useful for your needs, but feel free to have a look around if you're curious!