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

arXiv: https://arxiv.org/abs/2310.17723 · HTML: https://mlsanity.com/paper/2310.17723/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 25 references that are in the map.
- First posted on arXiv 26 Oct 2023.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers](https://mlsanity.com/paper/2206.01861/) (2022)
- [HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision](https://mlsanity.com/paper/1905.03696/) (2019)
- [Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT](https://mlsanity.com/paper/1909.05840/) (2019)
- [Q8BERT: Quantized 8Bit BERT](https://mlsanity.com/paper/1910.06188/) (2019)
- [HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks](https://mlsanity.com/paper/1911.03852/) (2019)
- [Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models](https://mlsanity.com/paper/2209.13325/) (2022)
- [BinaryBERT: Pushing the Limit of BERT Quantization](https://mlsanity.com/paper/2012.15701/) (2020)
- [TernaryBERT: Distillation-aware Ultra-low Bit BERT](https://mlsanity.com/paper/2009.12812/) (2020)
- [Understanding and Overcoming the Challenges of Efficient Transformer Quantization](https://mlsanity.com/paper/2109.12948/) (2021)
- [GOBO: Quantizing Attention-Based NLP Models for Low Latency and Energy Efficient Inference](https://mlsanity.com/paper/2005.03842/) (2020)
- [Compression of Generative Pre-trained Language Models via Quantization](https://mlsanity.com/paper/2203.10705/) (2022)
- [ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation](https://mlsanity.com/paper/2303.08302/) (2023)
- [HAWQV3: Dyadic Neural Network Quantization](https://mlsanity.com/paper/2011.10680/) (2020)
- [ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats](https://mlsanity.com/paper/2307.09782/) (2023)
- [KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantization](https://mlsanity.com/paper/2101.05938/) (2021)

## Built on by (most cited first, 1 of 1)

- [ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks](https://mlsanity.com/paper/2312.08583/) (2023)

## Abstract (arXiv)

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 overlook crucial memory-bounded operators and the complexities of per-token quantization. Addressing these gaps, we present a novel, fully hardware-enhanced robust optimized post-training W8A8 quantization framework, ZeroQuant-HERO. This framework uniquely integrates both memory bandwidth and compute-intensive operators, aiming for optimal hardware performance. Additionally, it offers flexibility by allowing specific INT8 modules to switch to FP16/BF16 mode, enhancing accuracy.