We tried to import RNN-T pytorch model https://github.com/mlperf/inference/tree/master/v0.7/speech_recognition/rnnt/pytorch into TVM.
Pre-trained RNN-T model for MLPerf Inference https://zenodo.org/record/3662521
We found the error:
NotImplementedError: The following operators are not implemented: [‘prim::RaiseException’, ‘prim::Uninitialized’, ‘aten::lstm’, ‘aten::_cast_Int’, ‘aten::__derive_index’, ‘aten::not’, ‘aten::tensor’, ‘aten::item’, ‘aten::cast_Float’, ‘prim::data’, ‘aten::format’, ‘aten::copy’, ‘aten::append’, ‘aten::FloatImplicit’, ‘prim::dtype’, ‘prim::shape’, ‘prim::TupleIndex’, ‘aten::dim’, ‘aten::warn’, ‘aten::is’, ‘prim::unchecked_cast’]
How can we go through these errors to make RNN-T running on TVM?