This is the official weight (4-bit quantized) of LightMamba.
Our paper LightMamba: Efficient Mamba Acceleration on FPGA with Quantization and Hardware Co-design is available at: https://arxiv.org/abs/2502.15260.
Our code is available at GitHub: https://github.com/PKU-SEC-Lab/LightMamba.
If our work assists your research, feel free to cite us with:
@inproceedings{wei2025lightmamba,
title={Lightmamba: Efficient mamba acceleration on fpga with quantization and hardware co-design},
author={Wei, Renjie and Xu, Songqiang and Zhong, Linfeng and Yang, Zebin and Guo, Qingyu and Wang, Yuan and Wang, Runsheng and Li, Meng},
booktitle={2025 Design, Automation & Test in Europe Conference (DATE)},
pages={1--7},
year={2025},
organization={IEEE}
}
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support