# Pre-Quantized Deep Learning Models Codified in ONNX to Enable Hardware/Software Co-Design

arXiv: https://arxiv.org/abs/2110.01730 · HTML: https://mlsanity.com/paper/2110.01730/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 10 references that are in the map.
- First posted on arXiv 4 Oct 2021.

## Builds on (most cited first, 4 of 4)

- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Quantized Convolutional Neural Networks for Mobile Devices](https://mlsanity.com/paper/1512.06473/) (2015)
- [Glow: Graph Lowering Compiler Techniques for Neural Networks](https://mlsanity.com/paper/1805.00907/) (2018)
- [Efficient Execution of Quantized Deep Learning Models: A Compiler Approach](https://mlsanity.com/paper/2006.10226/) (2020)

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

- [QONNX: Representing Arbitrary-Precision Quantized Neural Networks](https://mlsanity.com/paper/2206.07527/) (2022)

## Abstract (arXiv)

This paper presents a methodology to separate the quantization process from the hardware-specific model compilation stage via a pre-quantized deep learning model description in standard ONNX format. Separating the quantization process from the model compilation stage enables independent development. The methodology is expressive to convey hardware-specific operations and to embed key quantization parameters into a ONNX model which enables hardware/software co-design. Detailed examples are given for both MLP and CNN based networks, which can be extended to other networks in a straightforward fashion.