I don't know about golomb coding, but with Arithmetic coding you can do stream decoding(AC), if I remember correctly.

I supervised a student's project whose goal was exactly that : implement compression with LLMs using AC.

Since AC is optimal, if your LLM has an average cross entropy x on some dataset, you can expect that the compression will compress data using x nats per token on average!

Arithmetic coding looks like an extremely interesting approach, given that you can use the model at each step to give you the probabilities of each token.