paper-with-me

Papers

QS4D: Quantization-aware training for efficient hardware deployment of structured state-space sequential models

2025-07-08 · Sebastian Siegel, Ming-Jay Yang, Younes Bouhadjar, Maxime Fabre, Emre Neftci, John Paul Strachan

Structured State Space models (SSM) have recently emerged as a new class of deep learning models, particularly well-suited for processing long sequences. Their constant memory footprint, in contrast to the linearly scaling memory demands of Transformers, makes them attractive candidates for deployment on resource-constrained edge-computing devices. While recent works have explored the effect of quantization-aware training (QAT) on SSMs, they typically do not address its implications for specialized edge hardware, for example, analog in-memory computing (AIMC) chips. In this work, we demonstrate that QAT can significantly reduce the complexity of SSMs by up to two orders of magnitude across various performance metrics. We analyze the relation between model size and numerical precision, and show that QAT enhances robustness to analog noise and enables structural pruning. Finally, we integrate these techniques to deploy SSMs on a memristive analog in-memory computing substrate and highlight the resulting benefits in terms of computational efficiency.

📄 PDF Abstract BibTeX arXiv:2507.06079

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyEdge-computingQuantizationState Space Models

Similar Papers 제목 키워드 기반

Deep Microcompression: Structured Pruning and Bit-packed Quantization for Microcontrollers

2026-09-04 · Opegbemi Matthias Busoye, Tolulope Matthew Busoye, Eghonghon-aye Eigbe arxiv

This paper introduces Deep Microcompression (DMC), a hardware-aware pipeline for deep learning inference on bare-metal microcontrollers. DMC integrates structured pruning, quantization-aware training, and fixed-length bi…

Boost Vision Transformer with GPU-Friendly Sparsity and Quantization

2023-05-18 · CVPR 2023 1 · Chong Yu, Tao Chen, Zhongxue Gan, Jiayuan Fan

The transformer extends its success from the language to the vision domain. Because of the stacked self-attention and cross-attention blocks, the acceleration deployment of vision transformer on GPU hardware is challengi…

BenchmarkingGPUKnowledge DistillationQuantization

IMSSA: Deploying modern state-space models on memristive in-memory compute hardware

2024-12-28 · Sebastian Siegel, Ming-Jay Yang, John-Paul Strachan

Processing long temporal sequences is a key challenge in deep learning. In recent years, Transformers have become state-of-the-art for this task, but suffer from excessive memory requirements due to the need to explicitl…

GPUQuantizationState Space ModelsTemporal Sequences

From Bits to Chips: An LLM-based Hardware-Aware Quantization Agent for Streamlined Deployment of LLMs

2026-01-07 · Kaiyuan Deng, Hangyu Zheng, Minghai Qing, Kunxiong Zhu 외 arxiv

Deploying models, especially large language models (LLMs), is becoming increasingly attractive to a broader user base, including those without specialized expertise. However, due to the resource constraints of certain ha…

Efficient Network Inference via Hardware-Aware Architecture Search, Model Pruning & Quantization

2026-06-22 · Lucas Heublein, Mark Deutel, Axel Plinge, Felix Ott arxiv

Embedded global navigation satellite system (GNSS) interference monitoring requires fast and memory-efficient inference to process large volumes of raw in-phase and quadrature (IQ) samples in real time. At the same time,…

Neural Architecture SearchModel Compression