diff --git a/ggml/src/ggml-cuda/softmax.cu b/ggml/src/ggml-cuda/softmax.cu
index 4773d93f7e..1ae84ebf63 100644
--- a/ggml/src/ggml-cuda/softmax.cu
+++ b/ggml/src/ggml-cuda/softmax.cu
@@ -419,7 +419,9 @@ static void soft_max_f32_cuda(const float *                                x,
         // Parallelize across SMs for top-p/dist-sampling
         // The heuristic for parallelizing rows across SMs vs parallelizing single row & looping over all rows was done on the basis of a B6000 GPU and
         // Can be adapted further for lower-SM-count GPUs, though keeping data in registers should be implemented first as that is the optimal solution.
-        if (ggml_cuda_info().devices[id].supports_cooperative_launch && ncols_x / (params.ne01 * params.ne02 * params.ne03) > 8192 && mask == nullptr && sinks == nullptr && params.scale == 1.0f && params.max_bias == 0.0f) {
+        if (ggml_cuda_info().devices[id].supports_cooperative_launch &&
+            ncols_x / (params.ne01 * params.ne02 * params.ne03) > 8192 && mask == nullptr && sinks == nullptr &&
+            params.scale == 1.0f && params.max_bias == 0.0f) {
             ggml_cuda_pool_alloc<float> tmp_maxs_alloc(ctx.pool(), ggml_cuda_info().devices[id].nsm * sizeof(float));
             ggml_cuda_pool_alloc<float> tmp_sums_alloc(ctx.pool(), ggml_cuda_info().devices[id].nsm * sizeof(float));