TF_CAPI_EXPORT extern bool TFE_ExecutorIsAsync(TFE_Executor*);

// Causes the calling thread to block till all ops dispatched in this executor
// have been executed. Note that "execution" here refers to kernel execution /
// scheduling of copies, etc. Similar to sync execution, it doesn't guarantee
// that lower level device queues (like GPU streams) have been flushed.
//
// This call may not block for execution of ops enqueued concurrently with this
// call.

// backwards functions are deleted.
// If `persistent_tape` is false, op_tape is cleared and backwards functions
// not needed for gradient computation are deleted. Backwards functions that
// are needed, are copied and returned in BackpropInitialState.
template <typename BackwardFunction, typename TapeTensor>
BackpropInitialState<BackwardFunction, TapeTensor> PrepareBackprop(