# Shrinking the Giant : Quasi-Weightless Transformers for Low Energy Inference

arXiv: https://arxiv.org/abs/2411.01818 · HTML: https://mlsanity.com/paper/2411.01818/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 4 Nov 2024.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits](https://mlsanity.com/paper/2402.17764/) (2024)
- [Q8BERT: Quantized 8Bit BERT](https://mlsanity.com/paper/1910.06188/) (2019)
- [Post-Training Quantization for Vision Transformer](https://mlsanity.com/paper/2106.14156/) (2021)
- [BinaryBERT: Pushing the Limit of BERT Quantization](https://mlsanity.com/paper/2012.15701/) (2020)
- [AI and Memory Wall](https://mlsanity.com/paper/2403.14123/) (2024)
- [Recurrent Neural Networks (RNNs): A gentle Introduction and Overview](https://mlsanity.com/paper/1912.05911/) (2019)
- [LogicNets: Co-Designed Neural Networks and Circuits for Extreme-Throughput Applications](https://mlsanity.com/paper/2004.03021/) (2020)
- [PolyLUT: Learning Piecewise Polynomials for Ultra-Low Latency FPGA LUT-based Inference](https://mlsanity.com/paper/2309.02334/) (2023)
- [Differentiable Weightless Neural Networks](https://mlsanity.com/paper/2410.11112/) (2024)
- [SwiftTron: An Efficient Hardware Accelerator for Quantized Transformers](https://mlsanity.com/paper/2304.03986/) (2023)
- [Weightless Neural Networks for Efficient Edge Inference](https://mlsanity.com/paper/2203.01479/) (2022)
- [ULEEN: A Novel Architecture for Ultra Low-Energy Edge Neural Networks](https://mlsanity.com/paper/2304.10618/) (2023)
- [Multiplication-Free Transformer Training via Piecewise Affine Operations](https://mlsanity.com/paper/2305.17190/) (2023)

## Abstract (arXiv)

Transformers are set to become ubiquitous with applications ranging from chatbots and educational assistants to visual recognition and remote sensing. However, their increasing computational and memory demands is resulting in growing energy consumption. Building models with fast and energy-efficient inference is imperative to enable a variety of transformer-based applications. Look Up Table (LUT) based Weightless Neural Networks are faster than the conventional neural networks as their inference only involves a few lookup operations. Recently, an approach for learning LUT networks directly via an Extended Finite Difference method was proposed. We build on this idea, extending it for performing the functions of the Multi Layer Perceptron (MLP) layers in transformer models and integrating them with transformers to propose Quasi Weightless Transformers (QuWeiT). This allows for a computational and energy-efficient inference solution for transformer-based models. On I-ViT-T, we achieve a comparable accuracy of 95.64% on CIFAR-10 dataset while replacing approximately 55% of all the multiplications in the entire model and achieving a 2.2x energy efficiency. We also observe similar savings on experiments with the nanoGPT framework.