paper-with-me

Papers

QFT: Post-training quantization via fast joint finetuning of all degrees of freedom

2022-12-05 · Alex Finkelstein, Ella Fuchs, Idan Tal, Mark Grobman, Niv Vosco, Eldad Meller

The post-training quantization (PTQ) challenge of bringing quantized neural net accuracy close to original has drawn much attention driven by industry demand. Many of the methods emphasize optimization of a specific degree-of-freedom (DoF), such as quantization step size, preconditioning factors, bias fixing, often chained to others in multi-step solutions. Here we rethink quantized network parameterization in HW-aware fashion, towards a unified analysis of all quantization DoF, permitting for the first time their joint end-to-end finetuning. Our single-step simple and extendable method, dubbed quantization-aware finetuning (QFT), achieves 4-bit weight quantization results on-par with SoTA within PTQ constraints of speed and resource.

📄 PDF Abstract BibTeX arXiv:2212.02634

Code (0)

등록된 구현이 없습니다.

Tasks

AllQuantization

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization

2026-02-03 · Maximilian Kleinegger, Elvir Crnčević, Dan Alistarh arxiv

Matryoshka Quantization (MatQuant) is a recent quantization approach showing that a single integer-quantized model can be served across multiple precisions, by slicing the most significant bits (MSB) at inference time. T…

Data-Free Group-Wise Fully Quantized Winograd Convolution via Learnable Scales

2024-12-27 · CVPR 2025 1 · Shuokai Pan, Gerti Tuzi, Sudarshan Sreeram, Dibakar Gope

Despite the revolutionary breakthroughs of large-scale text-to-image diffusion models for complex vision and downstream tasks, their extremely high computational and storage costs limit their usability. Quantization of d…

image-classificationImage ClassificationImage GenerationQuantization+2

Sensitivity-Aware Finetuning for Accuracy Recovery on Deep Learning Hardware

2023-06-05 · Lakshmi Nair, Darius Bunandar

Existing methods to recover model accuracy on analog-digital hardware in the presence of quantization and analog noise include noise-injection training. However, it can be slow in practice, incurring high computational c…

Deep LearningQuantizationSensitivity

Loss Aware Post-training Quantization

2019-11-17 · Yury Nahshan, Brian Chmiel, Chaim Baskin, Evgenii Zheltonozhskii 외

Neural network quantization enables the deployment of large models on resource-constrained devices. Current post-training quantization methods fall short in terms of accuracy for INT4 (or lower) but provide reasonable ac…

Quantization

Outlier-Aware Post-Training Quantization for Image Super-Resolution

2025-11-01 · Hailing Wang, jianglin Lu, Yitian Zhang, Yun Fu arxiv

Quantization techniques, including quantization-aware training (QAT) and post-training quantization (PTQ), have become essential for inference acceleration of image super-resolution (SR) networks. Compared to QAT, PTQ ha…

Image Super-Resolution