You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
llama : expose llama_model_n_head_kv in the API (ggml-org#11997)
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).
0 commit comments