Comment by srean

That's different.

You can certainly feed k-grams one at a time to, estimate the the probability distribution over next token and use that to simulate a Markov Chain and reinitialize the LLM (drop context). In this process the LLM is just a look up table to simulate your MC.

But an LLM on its own doesn't drop context to generate, it's transition probabilities change depending on the tokens.