paper-with-me

Papers

OuroMamba: A Data-Free Quantization Framework for Vision Mamba Models

2025-03-13 · Akshat Ramachandran, Mingyu Lee, Huan Xu, Souvik Kundu, Tushar Krishna

We present OuroMamba, the first data-free post-training quantization (DFQ) method for vision Mamba-based models (VMMs). We identify two key challenges in enabling DFQ for VMMs, (1) VMM's recurrent state transitions restricts capturing of long-range interactions and leads to semantically weak synthetic data, (2) VMM activations exhibit dynamic outlier variations across time-steps, rendering existing static PTQ techniques ineffective. To address these challenges, OuroMamba presents a two-stage framework: (1) OuroMamba-Gen to generate semantically rich and meaningful synthetic data. It applies contrastive learning on patch level VMM features generated through neighborhood interactions in the latent state space, (2) OuroMamba-Quant to employ mixed-precision quantization with lightweight dynamic outlier detection during inference. In specific, we present a thresholding based outlier channel selection strategy for activations that gets updated every time-step. Extensive experiments across vision and generative tasks show that our data-free OuroMamba surpasses existing data-driven PTQ techniques, achieving state-of-the-art performance across diverse quantization settings. Additionally, we implement efficient GPU kernels to achieve practical latency speedup of up to 2.36x. Code will be released soon.

📄 PDF Abstract BibTeX arXiv:2503.10959

Code (0)

등록된 구현이 없습니다.

Tasks

channel selectionContrastive LearningData Free QuantizationGPUMambaOutlier DetectionQuantization

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Patch Similarity Aware Data-Free Quantization for Vision Transformers

2022-03-04 · Zhikai Li, Liping Ma, Mengjuan Chen, Junrui Xiao 외

Vision transformers have recently gained great success on various computer vision tasks; nevertheless, their high model complexity makes it challenging to deploy on resource-constrained devices. Quantization is an effect…

Data Free QuantizationQuantization

PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers

2022-09-13 · Zhikai Li, Mengjuan Chen, Junrui Xiao, Qingyi Gu

Data-free quantization can potentially address data privacy and security concerns in model compression, and thus has been widely investigated. Recently, PSAQ-ViT designs a relative value metric, patch similarity, to gene…

Data Free Quantizationimage-classificationImage ClassificationModel Compression+4

Data-Free Quantization Through Weight Equalization and Bias Correction

2019-06-11 · ICCV 2019 10 · Markus Nagel, Mart van Baalen, Tijmen Blankevoort, Max Welling

We introduce a data-free quantization method for deep neural networks that does not require fine-tuning or hyperparameter selection. It achieves near-original model performance on common computer vision architectures and…

Data Free Quantizationobject-detectionObject DetectionQuantization+1

FreeAct: Freeing Activations for LLM Quantization

2026-03-02 · Xiaohao Liu, Xiaobo Xia, Manyi Zhang, Ji-Fu Li 외 arxiv

Quantization is pivotal for mitigating the significant memory and computational overhead of Large Language Models (LLMs). While emerging transformation-based methods have successfully enhanced quantization by projecting …

SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models

2025-09-11 · Hengyu Fang, Yijiang Liu, Yuan Du, Li Du 외 arxiv

Vision-Language-Action (VLA) models exhibit unprecedented capabilities for embodied intelligence. However, their extensive computational and memory costs hinder their practical deployment. Existing VLA compression and ac…

Computational Efficiency