feat: prefetch streamed layers during compute (#1905)

Co-authored-by: leejet <leejet714@gmail.com>

examples/common/common.h

@@ -151,6 +151,7 @@ struct SDContextParams {
     bool offload_params_to_cpu  = false;
     std::string max_vram        = "0";
     bool stream_layers          = false;
+    bool disable_prefetch       = false;
     bool eager_load             = false;
     std::string backend;
     std::string params_backend;