paper-with-me

Papers

FPTQ: Fine-grained Post-Training Quantization for Large Language Models

2023-08-30 · Qingyuan Li, Yifan Zhang, Liang Li, Peng Yao, Bo Zhang, Xiangxiang Chu, Yerui Sun, Li Du, Yuchen Xie

In the era of large-scale language models, the substantial parameter size poses significant challenges for deployment. Being a prevalent compression technique, quantization has emerged as the mainstream practice to tackle this issue, which is mainly centered on two recipes W8A8 and W4A16 (i.e. weights and activations in such bit widths). In this study, we propose a novel W4A8 post-training quantization method for the available open-sourced LLMs, which combines the advantages of both two recipes. Therefore, we can leverage the benefit in the I/O utilization of 4-bit weight quantization and the acceleration due to 8-bit matrix computation. Nevertheless, the W4A8 faces notorious performance degradation. As a remedy, we involve layerwise activation quantization strategies which feature a novel logarithmic equalization for most intractable layers, and we combine them with fine-grained weight quantization. Without whistles and bells, we eliminate the necessity for further fine-tuning and obtain the state-of-the-art W4A8 quantized performance on BLOOM, LLaMA, and LLaMA-2 on standard benchmarks. We confirm that the W4A8 quantization is achievable for the deployment of large language models, fostering their wide-spreading real-world applications.

📄 PDF Abstract BibTeX arXiv:2308.15987

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Methods 이 논문이 사용한 방법론

BLOOM BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages…

Similar Papers 제목 키워드 기반

FPTQuant: Function-Preserving Transforms for LLM Quantization

2025-06-05 · Boris van Breugel, Yelysei Bondarenko, Paul Whatmough, Markus Nagel

Large language models (LLMs) require substantial compute, and thus energy, at inference time. While quantizing weights and activations is effective at improving efficiency, naive quantization of LLMs can significantly de…

Quantization

Fine-grained Data Distribution Alignment for Post-Training Quantization

2021-09-09 · Yunshan Zhong, Mingbao Lin, Mengzhao Chen, Ke Li 외

While post-training quantization receives popularity mostly due to its evasion in accessing the original complete training dataset, its poor performance also stems from scarce images. To alleviate this limitation, in thi…

Quantization

Integer Scale: A Free Lunch for Faster Fine-grained Quantization of LLMs

2024-05-23 · Qingyuan Li, Ran Meng, Yiduo Li, Bo Zhang 외

We introduce Integer Scale, a novel post-training quantization scheme for large language models that effectively resolves the inference bottleneck in current fine-grained quantization approaches while maintaining similar…

Quantization

Task-Stratified Knowledge Scaling Laws for Post-Training Quantized Large Language Models

2025-08-26 · Chenxi Zhou, Pengfei Cao, Jiang Li, Bohan Yu 외 arxiv

Post-Training Quantization (PTQ) is a critical strategy for efficient Large Language Models (LLMs) deployment. However, existing scaling laws primarily focus on general performance, overlooking crucial fine-grained facto…

Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients

2026-03-18 · Ziwei Xiang, Fanhu Zeng, Hongjian Fang, Rui-Qi Wang 외 arxiv

Large Vision Language Models (LVLMs) have achieved remarkable success in a range of downstream tasks that require multimodal interaction, but their capabilities come with substantial computational and memory overhead, wh…