How to save "quantitized" model

Sean Moriarity annonces that quantization is available in Axon: https://dockyard.com/blog/2024/08/20/where-are-nx-axon-bumblebee-headed

If you are happy with the new model, I imagine it is useful to do it once for all. Is it possible to save and replace the model on disk?

3 Likes

I go a response on the EEF Slack channel. In the TODO list.

1 Like