ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2406.09904
42
4

QQQ: Quality Quattuor-Bit Quantization for Large Language Models

14 June 2024
Ying Zhang
Peng Zhang
Mincong Huang
Jingyang Xiang
Yujie Wang
Chao Wang
Yineng Zhang
Lei Yu
Chuan Liu
Wei Lin
    VLM
    MQ
ArXivPDFHTML
Abstract

Quantization is a proven effective method for compressing large language models. Although popular techniques like W8A8 and W4A16 effectively maintain model performance, they often fail to concurrently speed up the prefill and decoding stages of inference. W4A8 is a promising strategy to accelerate both of them while usually leads to a significant performance degradation. To address these issues, we present QQQ, a Quality Quattuor-bit Quantization method with 4-bit weights and 8-bit activations. QQQ employs adaptive smoothing and Hessian-based compensation, significantly enhancing the performance of quantized models without extensive training. Furthermore, we meticulously engineer W4A8 GEMM kernels to increase inference speed. Our specialized per-channel W4A8 GEMM and per-group W4A8 GEMM achieve impressive speed increases of 3.67×\times× and 3.29 ×\times× over FP16 GEMM. Our extensive experiments show that QQQ achieves performance on par with existing state-of-the-art LLM quantization methods while significantly accelerating inference, achieving speed boosts up to 2.24 ×\times×, 2.10×\times×, and 1.25×\times× compared to FP16, W8A8, and W4A16, respectively.

View on arXiv
Comments on this paper