paper-with-me

홈 › Papers

PerfMamba: Performance Analysis and Pruning of Selective State Space Models

2025-11-28 · Abdullah Al Asif, Mobina Kashaniyan, Sixing Yu, Juan Pablo Muñoz, Ali Jannesari arxiv

Recent advances in sequence modeling have introduced selective SSMs as promising alternatives to Transformer architectures, offering theoretical computational efficiency and sequence processing advantages. A comprehensive understanding of selective SSMs in runtime behavior, resource utilization patterns, and scaling characteristics still remains unexplored, thus obstructing their optimal deployment and further architectural improvements. This paper presents a thorough empirical study of Mamba-1 and Mamba-2, systematically profiled for performance to assess the design principles that contribute to their efficiency in state-space modeling. A detailed analysis of computation patterns, memory access, I/O characteristics, and scaling properties was performed for sequence lengths ranging from 64 to 16384 tokens. Our findings show that the SSM component, a central part of the selective SSM architecture, demands a significant portion of computational resources compared to other components in the Mamba block. Based on these insights, we propose a pruning technique that selectively removes low-activity states within the SSM component, achieving measurable throughput and memory gains while maintaining accuracy within a moderate pruning regime. This approach results in performance improvements across varying sequence lengths, achieving a 1.14x speedup and reducing memory usage by 11.50\%. These results offer valuable guidance for designing more efficient SSM architectures that can be applied to a wide range of real-world applications.

📄 PDF Abstract BibTeX arXiv:2511.22849

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Similar Papers 제목 키워드 기반

SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot

2025-06-11 · Kaiwen Tuo, Huan Wang

State-space language models such as Mamba match Transformer quality while permitting linear complexity inference, yet still comprise billions of parameters that hinder deployment. Existing one-shot pruning methods are ta…

MambaState Space Models

Think Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning Models

2025-11-24 · Yang Xiang, Yixin Ji, Juntao Li, Min Zhang arxiv

Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex reasoning benchmarks. However, their long chain-of-thought reasoning processes incur significant inference overhead. Pruning has emerged a…

Investigation and Analysis of Hyper and Hypo neuron pruning to selectively update neurons during Unsupervised Adaptation

2020-01-06 · Vikramjit Mitra, Horacio Franco

Unseen or out-of-domain data can seriously degrade the performance of a neural network model, indicating the model's failure to generalize to unseen data. Neural net pruning can not only help to reduce a model's size but…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Exploring the Limits of Pruning: Task-Specific Neurons, Model Collapse, and Recovery in Task-Specific Large Language Models

2026-04-29 · M. K. Khalidi Siam, Md. Tausif-Ul-Islam, Md. Reshad Romim Khan, Mohammed Ali Hossain 외 arxiv

Neuron pruning is widely used to reduce the computational cost and parameter footprint of large language models, yet it remains unclear whether neurons in task-specific models contribute uniformly to task performance. In…

Mathematical ReasoningCode Generation

Token Pruning in Audio Transformers: Optimizing Performance and Decoding Patch Importance

2025-04-02 · Taehan Lee, Hyukjun Lee

Vision Transformers (ViTs) have achieved state-of-the-art performance across various computer vision tasks, but their high computational cost remains a challenge. Token pruning has been proposed to reduce this cost by se…

Audio Classification