// will block till the operation that produces `h` has completed.
TF_CAPI_EXPORT extern const char* TFE_TensorHandleDeviceName(
    TFE_TensorHandle* h, TF_Status* status);

// Returns the name of the device in whose memory `h` resides.
//
// This function will block till the operation that produces `h` has completed.
TF_CAPI_EXPORT extern const char* TFE_TensorHandleBackingDeviceName(

// combined status.
TF_CAPI_EXPORT extern void TFE_ContextAsyncWait(TFE_Context* ctx,
                                                TF_Status* status);

// This function will block till the operation that produces `h` has
// completed. This is only valid on local TFE_TensorHandles. The pointer
// returned will be on the device in which the TFE_TensorHandle resides (so e.g.

  buf->Unref();
  return tensorflow::wrap(tensorflow::TensorHandle::CreateLocalHandle(
      std::move(t), device, device, context));
}

// This function will block till the operation that produces `h` has
// completed. This is only valid on local TFE_TensorHandles. Returns the size in
// bytes of the memory pointed to by the device pointer returned above.
size_t TFE_TensorHandleDeviceMemorySize(TFE_TensorHandle* h,

      const std::function<void(BackwardFunction*)>& backward_function_deleter);

  void DeleteTrace(int64_t tensor_id);

  // Consumes the internal state of the tape (so cannot be called more than
  // once) and produces the gradient of the target tensors with respect to the
  // source tensors. The output gradients are used if not empty and not
  // null. The result is populated with one tensor per target element.