llama.cpp llama : expose llama_model_n_head

llama : expose llama_model_n_head_kv in the API

Open vlovich opened this issue 1 day ago • 0 comments

It's useful to be able to have this from the library layer as it's a key parameter of the model (e.g. to figure out how much KV cache memory is needed).

Feb 21 '25 07:02 vlovich

llama.cpp llama.cpp copied to clipboard

llama : expose llama_model_n_head_kv in the API

llama.cpp
llama.cpp copied to clipboard