Revert

paddle/fluid/framework/details/threaded_ssa_graph_executor.cc

@@ -204,8 +204,8 @@ void ThreadedSSAGraphExecutor::RunOp(
       VLOG(10) << op << " " << op->Name() << "Signal posted";
     } catch (platform::EnforceNotMet ex) {
       exception_.reset(new platform::EnforceNotMet(ex));
-    } catch (std::exception &exp) {
-      LOG(FATAL) << exp.what();
+    } catch (...) {
+      LOG(FATAL) << "Unknown exception catched";
     }
   };
   if (pool_) {

paddle/fluid/pybind/tensor_py.h

@@ -190,7 +190,6 @@ void PyCUDATensorSetFromArray(
       static_cast<const platform::CUDADeviceContext *>(pool.Get(place));
   paddle::platform::GpuMemcpyAsync(dst, array.data(), sizeof(T) * array.size(),
                                    cudaMemcpyHostToDevice, dev_ctx->stream());
-  dev_ctx->Wait();
 }
 
 template <>