Excited to share that our #ICML2025 paper “Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models”!

Our work Quamba, an 8-bit weight-activation quantization method for Selective State Space Models (SSMs), is being presented at #ICLR2025!

We’re excited to pre-release our latest work: Quamba2 🔧 Supports W4A8 / W4A16 / W4AX / W8A8 for Mamba1 and Mamba2 🚀 Achieves 4× memory reduction and 3× generation speedup ⚡️ Enables 8B model inference on Orin Nano 8G at 13 tokens/sec 🔥 Outperforms W4A8KV4 Llama3-8B in both speed and quality