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

Honor -ngl option for Cuda offloading in llava (#3621)

Browse source
This commit is contained in:
M. Yusuf Sarıgöz 2023-10-14 13:52:44 +03:00 committed by GitHub
parent 2a4bcbacea
commit 11dc1091f6
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
examples/llava/llava.cpp
View file

@ -79,7 +79,13 @@ int main(int argc, char ** argv) {
llama_backend_init(params.numa);
llama_model_params model_params = llama_model_default_params();
llama_model_params model_params = llama_model_default_params();
model_params.n_gpu_layers = params.n_gpu_layers;
model_params.main_gpu = params.main_gpu;
model_params.tensor_split = params.tensor_split;
model_params.use_mmap = params.use_mmap;
model_params.use_mlock = params.use_mlock;
llama_model * model = llama_load_model_from_file(params.model.c_str(), model_params);
if (model == NULL) {
fprintf(stderr , "%s: error: unable to load model\n" , __func__);