How to fetch kv cache under llamacpp like “past_key_values“？

[hitdra]

With pytorch and the transformer framework, I can get the kv cache like this
generated = model.generate(input_ids, max_new_tokens = 1, return_dict_in_generate=True)
kv = generated['past_key_values']
How to get the corresponding kv cache under llamacpp?
I really appreciate everyone being able to answer my questions, thanks a million!

[bingo787]

I want to konw also.