can you send a PR to add your implementation of LSTM converter? This is a requested feature (see https://github.com/apache/incubator-tvm/issues/6474)
Unrolling is the standard way to implement lstm op conversion. Both MXNet and ONNX frontend do it. I don't recommend pursuing the approach of control flow when the number of layers are known at compile time. There is a usage of generating a `while` loop in PyTorch frontend, here https://github.com/apache/incubator-tvm/blob/main/python/tvm/relay/frontend/pytorch.py#L3222-L3223. You can use this to turn a static lstm op to a dynamic lstm. But the usage is complicated so I don't recommend it. --- [Visit Topic](https://discuss.tvm.apache.org/t/how-to-use-relay-control-flow/8243/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/a03e262c28af4164619e47c5618a8000d49e4f2e5104a4c65b83bc83a0dd9e43).
