# Cheetah: Mixed Low-Precision Hardware & Software Co-Design Framework for DNNs on the Edge

arXiv: https://arxiv.org/abs/1908.02386 · HTML: https://mlsanity.com/paper/1908.02386/

## Key facts

- Cited by 8 papers in the map (data through 13 Oct 2026).
- First posted on arXiv 6 Aug 2019.

## Built on by (most cited first, 8 of 8)

- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Training Transformers with 4-bit Integers](https://mlsanity.com/paper/2306.11987/) (2023)
- [F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization](https://mlsanity.com/paper/2202.05239/) (2022)
- [GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning](https://mlsanity.com/paper/2502.12913/) (2025)
- [Algorithm-Hardware Co-Design of Distribution-Aware Logarithmic-Posit Encodings for Efficient DNN Inference](https://mlsanity.com/paper/2403.05465/) (2024)
- [Low-Precision Mixed-Computation Models for Inference on Edge](https://mlsanity.com/paper/2312.02210/) (2023)
- [PositNN: Training Deep Neural Networks with Mixed Low-Precision Posit](https://mlsanity.com/paper/2105.00053/) (2021)
- [How Low Can We Go: Trading Memory for Error in Low-Precision Training](https://mlsanity.com/paper/2106.09686/) (2021)

## Abstract (arXiv)

Low-precision DNNs have been extensively explored in order to reduce the size of DNN models for edge devices. Recently, the posit numerical format has shown promise for DNN data representation and compute with ultra-low precision in [5..8]-bits. However, previous studies were limited to studying posit for DNN inference only. In this paper, we propose the Cheetah framework, which supports both DNN training and inference using posits, as well as other commonly used formats. Additionally, the framework is amenable for different quantization approaches and supports mixed-precision floating point and fixed-point numerical formats. Cheetah is evaluated on three datasets: MNIST, Fashion MNIST, and CIFAR-10. Results indicate that 16-bit posits outperform 16-bit floating point in DNN training. Furthermore, performing inference with [5..8]-bit posits improves the trade-off between performance and energy-delay-product over both [5..8]-bit float and fixed-point.