paper-with-me

Papers

BiSup: Bidirectional Quantization Error Suppression for Large Language Models

2024-05-24 · Minghui Zou, Ronghui Guo, Sai Zhang, Xiaowang Zhang, Zhiyong Feng

As the size and context length of Large Language Models (LLMs) grow, weight-activation quantization has emerged as a crucial technique for efficient deployment of LLMs. Compared to weight-only quantization, weight-activation quantization presents greater challenges due to the presence of outliers in activations. Existing methods have made significant progress by exploring mixed-precision quantization and outlier suppression. However, these methods primarily focus on optimizing the results of single matrix multiplication, neglecting the bidirectional propagation of quantization errors in LLMs. Specifically, errors accumulate vertically within the same token through layers, and diffuse horizontally across different tokens due to self-attention mechanisms. To address this issue, we introduce BiSup, a Bidirectional quantization error Suppression method. By constructing appropriate optimizable parameter spaces, BiSup utilizes a small amount of data for quantization-aware parameter-efficient fine-tuning to suppress the error vertical accumulation. Besides, BiSup employs prompt mixed-precision quantization strategy, which preserves high precision for the key-value cache of system prompts, to mitigate the error horizontal diffusion. Extensive experiments on Llama and Qwen families demonstrate that BiSup can improve performance over two state-of-the-art methods (the average WikiText2 perplexity decreases from 13.26 to 9.41 for Atom and from 14.33 to 7.85 for QuaRot under the W3A3-g128 configuration), further facilitating the practical applications of low-bit weight-activation quantization.

📄 PDF Abstract BibTeX arXiv:2405.15346

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuningQuantization

Methods 이 논문이 사용한 방법론

Focus 설명 없음
LLaMA LLaMA is a collection of foundation language models ranging from 7B to 65B parameters. It is based on the transformer architecture with various improvements that were…

Similar Papers 제목 키워드 기반

Post-Training Quantization via Residual Truncation and Zero Suppression for Diffusion Models

2025-09-30 · Donghoon Kim, Dongyoung Lee, Ik Joon Chang, Sung-Ho Bae arxiv

Diffusion models achieve high-quality image generation but face deployment challenges due to their high computational requirements. Although 8-bit outlier-aware post-training quantization (PTQ) matches full-precision per…

Image Generation

DLLMQuant: Quantizing Diffusion-based Large Language Models

2025-08-14 · Chen Xu, Dawei Yang arxiv

Diffusion-based large language models (DLLMs) have shown promise for non-autoregressive text generation, but their deployment is constrained by large model sizes and heavy computational costs. Post-training quantization …

Text Generation

InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization

2026-05-25 · Ke Li, Dong An, Xiaoling Zang, Can Ye 외 arxiv

Low-bit activation quantization remains a major bottleneck in efficient large language model (LLM) deployment. The difficulty is not only that activations contain outliers, but that their distributions are often poorly m…

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

Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models

2022-09-27 · Xiuying Wei, Yunchen Zhang, Xiangguo Zhang, Ruihao Gong 외

Transformer architecture has become the fundamental element of the widespread natural language processing~(NLP) models. With the trends of large NLP models, the increasing memory and computation costs hinder their effici…

Quantization