See if tree compilation will speed up impute_new_data

[AnotherSamWilson]

https://github.com/siboehm/lleaves

[siboehm]

Posting my HN comment here for reference:

I had a brief look at your package, and my impression was that it's only changing model training. If this is correct then the format of the model.txt (calling lgbm.save(model, "model.txt")) is the same as regular lightgbm. This would mean you can use my library for inference.

Basically, if you can store your model as a model.txt and load & predict again using normal LightGBM, then compiling through lleaves should work for you.