mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-09-05 04:21:12 +02:00
llama : load MTP tensors only if they are really used (#26296)
* llama : load MTP tensors only if they are really used * llama : skip loading MTP (if not used) in remaining models that support MTP --------- Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
This commit is contained in:
@@ -2390,6 +2390,7 @@ llama_model_params llama_model_default_params() {
|
||||
/*.use_extra_bufts =*/ true,
|
||||
/*.no_host =*/ false,
|
||||
/*.no_alloc =*/ false,
|
||||
/*.load_mtp =*/ false,
|
||||
};
|
||||
|
||||
return result;
|
||||
|
||||
Reference in New Issue
Block a user