paper-with-me

Papers

How to Parameterize Asymmetric Quantization Ranges for Quantization-Aware Training

2024-04-25 · Jaeseong You, Minseop Park, Kyunggeun Lee, Seokjun An, Chirag Patel, Markus Nage

This paper investigates three different parameterizations of asymmetric uniform quantization for quantization-aware training: (1) scale and offset, (2) minimum and maximum, and (3) beta and gamma. We perform a comprehensive comparative analysis of these parameterizations' influence on quantization-aware training, using both controlled experiments and real-world large language models. Our particular focus is on their changing behavior in response to critical training hyperparameters, bit width and learning rate. Based on our investigation, we propose best practices to stabilize and accelerate quantization-aware training with learnable asymmetric quantization ranges.

📄 PDF Abstract BibTeX arXiv:2404.16898

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Exploring Post-Training Quantization of Protein Language Models

2023-10-30 · Shuang Peng, Fei Yang, Ning Sun, Sheng Chen 외

Recent advancements in unsupervised protein language models (ProteinLMs), like ESM-1b and ESM-2, have shown promise in different protein prediction tasks. However, these models face challenges due to their high computati…

Protein Structure PredictionQuantization

LSQ+: Improving low-bit quantization through learnable offsets and better initialization

2020-04-20 · Yash Bhalgat, Jinwon Lee, Markus Nagel, Tijmen Blankevoort 외

Unlike ReLU, newer activation functions (like Swish, H-swish, Mish) that are frequently employed in popular efficient architectures can also result in negative activation values, with skewed positive and negative ranges.…

Image ClassificationQuantization

Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning

2025-01-01 · CVPR 2025 1 · Maosen Zhao, Pengtao Chen, Chong Yu, Yan Wen 외

Model quantization reduces the bit-width of weights and activations, improving memory efficiency and inference speed in diffusion models. However, achieving 4-bit quantization remains challenging. Existing methods, p…

DenoisingQuantization

Hybrid and Non-Uniform DNN quantization methods using Retro Synthesis data for efficient inference

2021-01-01 · TEJPRATAP GVSL, Raja Kumar, Pradeep NS

Existing post-training quantization methods attempt to compensate for the quantization loss by determining the quantized weights and activation ranges with the help of training data. Quantization aware training methods, …

Quantization

AFPQ: Asymmetric Floating Point Quantization for LLMs

2023-11-03 · Yijia Zhang, Sicheng Zhang, Shijie Cao, Dayou Du 외

Large language models (LLMs) show great performance in various tasks, but face deployment challenges from limited memory capacity and bandwidth. Low-bit weight quantization can save memory and accelerate inference. Altho…

Quantization