Update ggml/src/ggml-cuda/cpy.cu

Co-authored-by: Johannes Gäßler <[email protected]>

Author: yeahdongcn

ggml/src/ggml-cuda/cpy.cu

@@ -603,12 +603,11 @@ void ggml_cuda_cpy(ggml_backend_cuda_context & ctx, const ggml_tensor * src0, gg
 #ifdef GGML_USE_MUSA
         if (src0->type == GGML_TYPE_F32 || src0->type == GGML_TYPE_F16) {
             CUDA_CHECK(mudnnMemcpyAsync(ctx, src1, src0));
-        } else {
+        } else
+#endif // GGML_USE_MUSA
+        {
             CUDA_CHECK(cudaMemcpyAsync(src1_ddc, src0_ddc, ggml_nbytes(src0), cudaMemcpyDeviceToDevice, main_stream));
         }
-#else // GGML_USE_MUSA
-        CUDA_CHECK(cudaMemcpyAsync(src1_ddc, src0_ddc, ggml_nbytes(src0), cudaMemcpyDeviceToDevice, main_stream));
-#endif // GGML_USE_MUSA
     } else if (src0->type == GGML_TYPE_F32 && src1->type == GGML_TYPE_F32) {
         ggml_cpy_f32_f32_cuda (src0_ddc, src1_ddc, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, main_stream, dest_ptrs_d, graph_cpynode_index);
     } else if (src0->type == GGML_TYPE_F32 && src1->type == GGML_TYPE_BF16) {