Can the model be exported to ONNX or other formats for deployment and inference?

[coptersack]

Thank you for your work, it is a truly great innovation. I downloaded your pre-trained weights and achieved outstanding results when fine-tuning them on my own dataset for classification tasks. However, I now need to evaluate the inference speed of the model. Could you please let me know if the Mamba model can be exported to ONNX format or other formats for deployment and inference? I do not have much prior experience with Mamba-based networks, so I am seeking your guidance.

[Apostatee]

The answer is "NO"