common : only load backends when required (#22290)

* common : only load backends when required Signed-off-by: Adrien Gallouët <angt@huggingface.co> * llama : call ggml_backend_load_all() directly from llama_backend_init() Signed-off-by: Adrien Gallouët <angt@huggingface.co> * Add ggml_backend_load_all() where llama_backend_init() is not used Signed-off-by: Adrien Gallouët <angt@huggingface.co> --------- Signed-off-by: Adrien Gallouët <angt@huggingface.co>
2026-05-05 09:23:50 +02:00
parent a09a00e502
commit bf76ac77be
6 changed files with 19 additions and 3 deletions
@@ -41,6 +41,9 @@ int main(int argc, char ** argv) {
    std::string result3;

    // init
+
+    ggml_backend_load_all();
+
    auto llama_init = common_init_from_params(params);

    auto * model = llama_init->model();