vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

use mmq

Browse source
This commit is contained in:
slaren 2023-08-30 16:42:01 +02:00
parent 3ef3cf8c3d
commit c436f18cc4
1 changed files with 1 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/llama2-chat/llama2-chat.cpp
View file

@ -25,6 +25,7 @@ struct chat {
lparams = llama_context_default_params(); lparams = llama_context_default_params();
lparams.n_ctx = 4096; lparams.n_ctx = 4096;
lparams.n_gpu_layers = 99; lparams.n_gpu_layers = 99;
lparams.mul_mat_q = true;
model = llama_load_model_from_file(model_file.c_str(), lparams); model = llama_load_model_from_file(model_file.c_str(), lparams);
if (model == NULL) { if (model == NULL) {