diff --git a/ggml/src/ggml-cuda/mmq.cu b/ggml/src/ggml-cuda/mmq.cu
index 65b87303..f30b55a6 100644
--- a/ggml/src/ggml-cuda/mmq.cu
+++ b/ggml/src/ggml-cuda/mmq.cu
@@ -146,7 +146,7 @@ void ggml_cuda_op_mul_mat_q(
     ggml_backend_cuda_context & ctx,
     const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst, const char * src0_dd_i, const float * src1_ddf_i,
     const char * src1_ddq_i, float * dst_dd_i, const int64_t row_low, const int64_t row_high, const int64_t src1_ncols,
-    const int64_t src1_padded_row_size, cudaStream_t stream) {
+    const int64_t src1_padded_row_size, [[maybe_unused]] cudaStream_t stream) {
 
     const int64_t ne00 = src0->ne[0];
     const int64_t nb01 = ggml_row_size(src0->type, ne00);