A Quantitative Analysis of Mamba-2-Based Large Language Model: Study of State Space Duality

Mamba is based on a state space model (SSM) to address limitations of attention-based large language models (LLMs) associated with long-context processing. While Mamba achieves accuracy comparable to attention-based LLMs, it introduces recurrent computation that limits efficiency during the prefill phase of inference. To mitigate this, Mamba-2 introduces the state space duality (SSD), which increases parallelism during multi-token processing. However, its workload characteristics remain unexamined from a systems and architectural perspective. This work presents a system-level analysis of SSD in Mamba2, characterizing its compute and memory behavior on modern hardware. Our findings reveal the computational characteristics of SSD and provide the first architectural insight into its execution. In addition, we identify performance bottlenecks and propose directions for addressing them in future work.