在使用paddlenlp LSTMEncoder的时候，在cpu下一运行就直接重启，以下是报错，去掉LSTM模块一切正常，初步判断是seq_len参数有问题，以下是报错信息

--------------------------------------
C++ Traceback (most recent call last):
--------------------------------------
0 paddle::imperative::Tracer::TraceOp(std::string const&, paddle::imperative::NameVarBaseMap const&, paddle::imperative::NameVarBaseMap const&, paddle::framework::AttributeMap, paddle::platform::Place const&, bool, std::map, std::allocator > > const&)
1 paddle::imperative::PreparedOp::Run(paddle::imperative::NameVarBaseMap const&, paddle::imperative::NameVarBaseMap const&, paddle::framework::AttributeMap const&)
2 std::_Function_handler, paddle::operators::RNNCPUKernel >::operator()(char const*, char const*, int) const::{lambda(paddle::framework::ExecutionContext const&)#1}>::_M_invoke(std::_Any_data const&, paddle::framework::ExecutionContext const&)
3 paddle::operators::RNNCPUKernel::Compute(paddle::framework::ExecutionContext const&) const
4 void paddle::operators::RnnFunc, paddle::operators::Layer, paddle::operators::SingleLayer, paddle::operators::BidirLayer, float>(paddle::framework::ExecutionContext const&, paddle::framework::Tensor const*, std::vector >, paddle::framework::Tensor const*, paddle::framework::Tensor const*, paddle::framework::Tensor const*, paddle::framework::Tensor*, paddle::framework::Tensor*, paddle::framework::Tensor*, paddle::framework::Tensor*, int const&, int const&, int const&, int const&, bool const&, std::string const&, float const&, bool const&, int const&, paddle::framework::Tensor*)
5 paddle::operators::BidirLayer >::operator()(paddle::framework::ExecutionContext const&, paddle::framework::Tensor const*, std::vector > const&, std::vector > const&, std::vector > const&, paddle::framework::Tensor const*, std::vector >, std::vector >, paddle::framework::Tensor*, int const&, int const&, paddle::framework::Tensor*, paddle::framework::Tensor*, paddle::framework::Tensor*, bool)
6 paddle::operators::Layer >::RunIter(paddle::framework::ExecutionContext const&, paddle::framework::Tensor const*, std::vector > const&, std::vector > const&, std::vector > const&, paddle::framework::Tensor const*, std::vector >*, std::vector >*, paddle::framework::Tensor*, int, paddle::framework::Tensor*, paddle::framework::Tensor*, paddle::framework::Tensor*, bool, int, bool)
7 void paddle::operators::create_mask_matrix(paddle::framework::ExecutionContext const&, paddle::framework::Tensor const*, paddle::framework::Tensor*, bool const&, int*)
8 paddle::framework::SignalHandle(char const*, int)
9 paddle::platform::GetCurrentTraceBackString[abi:cxx11]()

----------------------
Error Message Summary:
----------------------
FatalError: `Segmentation fault` is detected by the operating system.
[TimeInfo: *** Aborted at 1619945639 (unix time) try "date -d @1619945639" if you are using GNU date ***]
[SignalInfo: *** SIGSEGV (@0x7f2d1352e000) received by PID 89 (TID 0x7f2d66ada700) from PID 324198400 ***]