# Mokey: Enabling Narrow Fixed-Point Inference for Out-of-the-Box Floating-Point Transformer Models

arXiv: https://arxiv.org/abs/2203.12758 · HTML: https://mlsanity.com/paper/2203.12758/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 59 references that are in the map.
- First posted on arXiv 23 Mar 2022.

## Builds on (most cited first, 30 of 39)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [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)
- [I-BERT: Integer-only BERT Quantization](https://mlsanity.com/paper/2101.01321/) (2021)
- [SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning](https://mlsanity.com/paper/2012.09852/) (2020)
- [Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning](https://mlsanity.com/paper/2002.08307/) (2020)
- [Block Pruning For Faster Transformers](https://mlsanity.com/paper/2109.04838/) (2021)
- [TernaryBERT: Distillation-aware Ultra-low Bit BERT](https://mlsanity.com/paper/2009.12812/) (2020)
- [Learned Token Pruning for Transformers](https://mlsanity.com/paper/2107.00910/) (2021)
- [HAT: Hardware-Aware Transformers for Efficient Natural Language Processing](https://mlsanity.com/paper/2005.14187/) (2020)
- [Data Movement Is All You Need: A Case Study on Optimizing Transformers](https://mlsanity.com/paper/2007.00072/) (2020)
- [GOBO: Quantizing Attention-Based NLP Models for Low Latency and Energy Efficient Inference](https://mlsanity.com/paper/2005.03842/) (2020)
- [The Cost of Training NLP Models: A Concise Overview](https://mlsanity.com/paper/2004.08900/) (2020)
- [Compressing Large-Scale Transformer-Based Models: A Case Study on BERT](https://mlsanity.com/paper/2002.11985/) (2020)
- [Knowledge Distillation from Internal Representations](https://mlsanity.com/paper/1910.03723/) (2019)
- [Compute and Energy Consumption Trends in Deep Learning Inference](https://mlsanity.com/paper/2109.05472/) (2021)

## Built on by (most cited first, 19 of 19)

- [Efficient Methods for Natural Language Processing: A Survey](https://mlsanity.com/paper/2209.00099/) (2022)
- [A Survey of Techniques for Optimizing Transformer Inference](https://mlsanity.com/paper/2307.07982/) (2023)
- [Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous Batching](https://mlsanity.com/paper/2409.01141/) (2024)
- [A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models](https://mlsanity.com/paper/2410.07265/) (2024)
- [LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference](https://mlsanity.com/paper/2408.06003/) (2024)
- [BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration](https://mlsanity.com/paper/2411.11745/) (2024)
- [Ditto: Accelerating Diffusion Model via Temporal Value Similarity](https://mlsanity.com/paper/2501.11211/) (2025)
- [M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type](https://mlsanity.com/paper/2502.18755/) (2025)
- [Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization](https://mlsanity.com/paper/2503.18599/) (2025)
- [MX+: Pushing the Limits of Microscaling Formats for Efficient Large Language Model Serving](https://mlsanity.com/paper/2510.14557/) (2025)
- [Anda: Unlocking Efficient LLM Inference with a Variable-Length Grouped Activation Data Format](https://mlsanity.com/paper/2411.15982/) (2024)
- [LO-BCQ: Block Clustered Quantization for 4-bit (W4A4) LLM Inference](https://mlsanity.com/paper/2502.05376/) (2025)
- [Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Serving](https://mlsanity.com/paper/2507.10178/) (2025)
- [TATAA: Programmable Mixed-Precision Transformer Acceleration with a Transformable Arithmetic Architecture](https://mlsanity.com/paper/2411.03697/) (2024)
- [AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization](https://mlsanity.com/paper/2604.18137/) (2026)
- [Just-in-time Quantization with Processing-In-Memory for Efficient ML Training](https://mlsanity.com/paper/2311.05034/) (2023)
- [HEPPO-GAE: Hardware-Efficient Proximal Policy Optimization with Generalized Advantage Estimation](https://mlsanity.com/paper/2501.12703/) (2025)
- [DNA-TEQ: An Adaptive Exponential Quantization of Tensors for DNN Inference](https://mlsanity.com/paper/2306.16430/) (2023)
- [LightNobel: Improving Sequence Length Limitation in Protein Structure Prediction Model via Adaptive Activation Quantization](https://mlsanity.com/paper/2505.05893/) (2025)

## Abstract (arXiv)

Increasingly larger and better Transformer models keep advancing state-of-the-art accuracy and capability for Natural Language Processing applications. These models demand more computational power, storage, and energy. Mokey reduces the footprint of state-of-the-art 32-bit or 16-bit floating-point transformer models by quantizing all values to 4-bit indexes into dictionaries of representative 16-bit fixed-point centroids. Mokey does not need fine-tuning, an essential feature as often the training resources or datasets are not available to many. Exploiting the range of values that naturally occur in transformer models, Mokey selects centroid values to also fit an exponential curve. This unique feature enables Mokey to replace the bulk of the original multiply-accumulate operations with narrow 3b fixed-point additions resulting in an area- and energy-efficient hardware accelerator design. Over a set of state-of-the-art transformer models, the Mokey accelerator delivers an order of magnitude improvements in energy efficiency over a Tensor Cores-based accelerator while improving performance by at least 4× and as much as 15× depending on the model and on-chip buffering capacity. Optionally, Mokey can be used as a memory compression assist for any other accelerator, transparently stashing wide floating-point or fixed-point activations or weights into narrow 4-bit indexes. Mokey proves superior to prior state-of-the-art quantization methods for Transformers.