Make LightFM supports CuPy sparse matrices

First of all, thank you very much for that awesome package!

I think `lightFM` could use `CuPy` to enable GPU computation.
I have a lot of data and making predictions take long time.
I'm already using `cupy` arrays to store the top-k recommended items, and I could decrease sorting the predictions using `cp.argsort` by the half of time! That's a huge improvement.

Now I'm thinking that the sparse matrices calculations could be massive calculations too.
How about support lightFM to use `cupy` sparse matrices?
https://docs.cupy.dev/en/stable/reference/sparse.html?highlight=sparse

No files, tests, or entry points are identified in the issue. Start by reviewing LightFM's sparse-matrix calculations alongside the linked CuPy sparse API; done means CuPy sparse matrices are supported for the relevant computations without losing existing CPU behavior, with prediction performance verified.

Written by the indexing model from the issue text.