diff --git a/CMakeLists.txt b/CMakeLists.txt
index 6fc6508c5..545aab267 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -302,6 +302,8 @@ if (LLAMA_CUBLAS)
             set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} CUDA::cudart CUDA::cublas CUDA::cublasLt)
         endif()
 
+        set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} CUDA::cuda_driver)
+
     if (NOT DEFINED CMAKE_CUDA_ARCHITECTURES)
         # 52 == lowest CUDA 12 standard
         # 60 == f16 CUDA intrinsics
diff --git a/tests/test-grad0.cpp b/tests/test-grad0.cpp
index 14914def5..8ff76c891 100644
--- a/tests/test-grad0.cpp
+++ b/tests/test-grad0.cpp
@@ -883,9 +883,6 @@ int main(int argc, const char ** argv) {
             srand(seed);
             const int nargs = 1;
 
-            int64_t ne2[4];
-            ne2[0] = 1;
-
             for (int ndims = 1; ndims <= 2; ++ndims) {
                 x[0] = get_random_tensor_f32(ctx0, ndims, ne, -1.0f, 1.0f);