paper-with-me

Papers

ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers

2022-06-04 · Zhewei Yao, Reza Yazdani Aminabadi, Minjia Zhang, Xiaoxia Wu, Conglong Li, Yuxiong He

How to efficiently serve ever-larger trained natural language models in practice has become exceptionally challenging even for powerful cloud servers due to their prohibitive memory/computation requirements. In this work, we present an efficient and affordable post-training quantization approach to compress large Transformer-based models, termed as ZeroQuant. ZeroQuant is an end-to-end quantization and inference pipeline with three main components: (1) a fine-grained hardware-friendly quantization scheme for both weight and activations; (2) a novel affordable layer-by-layer knowledge distillation algorithm (LKD) even without the access to the original training data; (3) a highly-optimized quantization system backend support to remove the quantization/dequantization overhead. As such, we are able to show that: (1) ZeroQuant can reduce the precision for weights and activations to INT8 in a cost-free way for both BERT and GPT3-style models with minimal accuracy impact, which leads to up to 5.19x/4.16x speedup on those models compared to FP16 inference; (2) ZeroQuant plus LKD affordably quantize the weights in the fully-connected module to INT4 along with INT8 weights in the attention module and INT8 activations, resulting in 3x memory footprint reduction compared to the FP16 model; (3) ZeroQuant can be directly applied to two of the largest open-sourced language models, including GPT-J6B and GPT-NeoX20, for which our INT8 model achieves similar accuracy as the FP16 model but achieves up to 5.2x better efficiency.

📄 PDF Abstract BibTeX arXiv:2206.01861

Code (3)

microsoft/DeepSpeed 공식 구현 pytorch
huggingface/transformers-bloom-inference pytorch
modeltc/outlier_suppression_plus pytorch

Tasks

Knowledge DistillationQuantization

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Similar Papers 제목 키워드 기반

ZeroQuant-HERO: Hardware-Enhanced Robust Optimized Post-Training Quantization Framework for W8A8 Transformers

2023-10-26 · Zhewei Yao, Reza Yazdani Aminabadi, Stephen Youn, Xiaoxia Wu 외

Quantization techniques are pivotal in reducing the memory and computational demands of deep neural network inference. Existing solutions, such as ZeroQuant, offer dynamic quantization for models like BERT and GPT but ov…

Quantization

ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation

2023-03-15 · Zhewei Yao, Xiaoxia Wu, Cheng Li, Stephen Youn 외

Post-training quantization (PTQ) has emerged as a promising technique for mitigating memory consumption and computational costs in large language models (LLMs). However, a systematic examination of various quantization s…

Quantization

QERA: an Analytical Framework for Quantization Error Reconstruction

2024-10-08 · Cheng Zhang, Jeffrey T. H. Wong, Can Xiao, George A. Constantinides 외

he growing number of parameters and computational demands of large language models (LLMs) present significant challenges for their efficient deployment. Recently, there is an increasing interest in quantizing weights to …

parameter-efficient fine-tuningQuantization

Art and Science of Quantizing Large-Scale Models: A Comprehensive Overview

2024-09-18 · Yanshu Wang, Tong Yang, Xiyan Liang, Guoan Wang 외

This paper provides a comprehensive overview of the principles, challenges, and methodologies associated with quantizing large-scale neural network models. As neural networks have evolved towards larger and more complex …

Quantization

ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats

2023-07-19 · Xiaoxia Wu, Zhewei Yao, Yuxiong He

In the complex domain of large language models (LLMs), striking a balance between computational efficiency and maintaining model quality is a formidable challenge. Navigating the inherent limitations of uniform quantizat…

Computational EfficiencyQuantization