paper-with-me

홈 › Papers

OutlierTune: Efficient Channel-Wise Quantization for Large Language Models

2024-06-27 · Jinguang Wang, Yuexi Yin, Haifeng Sun, Qi Qi, Jingyu Wang, Zirui Zhuang, Tingting Yang, Jianxin Liao

Quantizing the activations of large language models (LLMs) has been a significant challenge due to the presence of structured outliers. Most existing methods focus on the per-token or per-tensor quantization of activations, making it difficult to achieve both accuracy and hardware efficiency. To address this problem, we propose OutlierTune, an efficient per-channel post-training quantization (PTQ) method for the activations of LLMs. OutlierTune consists of two components: pre-execution of dequantization and symmetrization. The pre-execution of dequantization updates the model weights by the activation scaling factors, avoiding the internal scaling and costly additional computational overheads brought by the per-channel activation quantization. The symmetrization further reduces the quantization differences arising from the weight updates by ensuring the balanced numerical ranges across different activation channels. OutlierTune is easy to implement and hardware-efficient, introducing almost no additional computational overheads during the inference. Extensive experiments show that the proposed framework outperforms existing methods across multiple different tasks. Demonstrating better generalization, this framework improves the Int6 quantization of the instruction-tuning LLMs, such as OPT-IML, to the same level as half-precision (FP16). Moreover, we have shown that the proposed framework is 1.48x faster than the FP16 implementation while reducing approximately 2x memory usage.

📄 PDF Abstract BibTeX arXiv:2406.18832

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Methods 이 논문이 사용한 방법론

Focus 설명 없음
OPT-IML OPT-IML is a version of OPT fine-tuned on a large collection of 1500+ NLP tasks divided into various task categories.

Similar Papers 제목 키워드 기반

Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling

2023-04-18 · Xiuying Wei, Yunchen Zhang, Yuhang Li, Xiangguo Zhang 외

Post-training quantization~(PTQ) of transformer language models faces significant challenges due to the existence of detrimental outliers in activations. We observe that these outliers are concentrated in specific channe…

Quantization

Channel-Wise Mixed-Precision Quantization for Large Language Models

2024-10-16 · Zihan Chen, Bike Xie, Jundong Li, Cong Shen

Large Language Models (LLMs) have demonstrated remarkable success across a wide range of language tasks, but their deployment on edge devices remains challenging due to the substantial memory requirements imposed by thei…

Quantization

PTQ-SL: Exploring the Sub-layerwise Post-training Quantization

2021-10-15 · Zhihang Yuan, Yiqi Chen, Chenhao Xue, Chenguang Zhang 외

Network quantization is a powerful technique to compress convolutional neural networks. The quantization granularity determines how to share the scaling factors in weights, which affects the performance of network quanti…

Quantization

Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference

2024-09-30 · Ke Yi, Zengke Liu, Jianwei Zhang, Chengyuan Li 외

Large language models have demonstrated promising capabilities upon scaling up parameters. However, serving large language models incurs substantial computation and memory movement costs due to their large scale. Quantiz…

Quantization

C-PTQ: Fisher-weighted Channel-wise Sensitivity for Post-training Quantization of MLLMs

2026-07-23 · Jiameng Li, Han Zhou, Matthew B. Blaschko arxiv

Multimodal large language models (MLLMs) require huge memory and computational costs, which limits their practical deployment. Post-training quantization (PTQ) techniques offer an efficient solution for model compression…

Model Compression