Skip to content

LLM inference in C/C++

C++ ggml

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

Ihar Hrachyshkacbb7d52ecbda
diff --git a/tests/test-llama-archs.cpp b/tests/test-llama-archs.cpp
index 7a76efccc3..9fba4fdc52 100644
--- a/tests/test-llama-archs.cpp
+++ b/tests/test-llama-archs.cpp
@@ -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;