test-llama-archs : initialize backends before generating models (#30034)

With GGML_BACKEND_DL=ON, backends must be loaded explicitly before
creating models.

Assisted-by: Codex
This commit is contained in:
Ihar Hrachyshka authored and GitHub committed 2026-10-06 09:49:52 +02:00
1 parent 63bef2728d
commit cbb7d52ecb
1 file changed
+1
+1
View File
@@ -1058,6 +1058,7 @@ int main(int argc, char ** argv) {
// init the logger at max verbosity. filter with a custom callback respecting the user-configure verbosity
common_log_set_verbosity_thold(LOG_LEVEL_DEBUG);
common_init();
llama_backend_init();
std::random_device rd;