fix

ggml/src/ggml-cuda/softmax.cu

@@ -12,7 +12,7 @@ __device__ float __forceinline__ t2f32<half>(half val) {
 }
 
 template <bool vals_smem, int ncols_template, int block_size_template, typename T>
-static __global__ void soft_max_f32(const float * x, const T * mask, float * dst, const int ncols_par, const int nrows_y, const float scale, const float max_bias, const float m0, const float m1, uint32_t n_head_log2) {
+static __global__ void __launch_bounds__(1024) soft_max_f32(const float * x, const T * mask, float * dst, const int ncols_par, const int nrows_y, const float scale, const float max_bias, const float m0, const float m1, uint32_t n_head_log2) {
     const int ncols = ncols_template == 0 ? ncols_par : ncols_template;
 
     const int tid  = threadIdx.x;