Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Brevitas: neural network quantization in PyTorch
| Date | Stars |
|---|---|
| 2026-08-05 | 1559 |
| 2026-08-06 | 1560 |
| 2026-08-08 | 1562 |
| 2026-08-10 | 1563 |
| 2026-08-11 | 1563 |
| 2026-08-15 | 1563 |
| 2026-08-16 | 1564 |
| 2026-08-18 | 1564 |
| 2026-08-19 | 1565 |
| 2026-08-20 | 1565 |
| 2026-08-21 | 1566 |
| 2026-08-22 | 1567 |
| 2026-08-27 | 1567 |
| 2026-08-29 | 1567 |
| 2026-09-01 | 1567 |
| 2026-09-03 | 1570 |
| 2026-09-04 | 1570 |
| 2026-09-06 | 1571 |
| 2026-09-08 | 1572 |
| 2026-09-09 | 1571 |
| 2026-09-10 | 1573 |
| 2026-09-13 | 1572 |
| 2026-09-15 | 1573 |
| 2026-09-16 | 1575 |
| 2026-09-17 | 1576 |
| 2026-09-18 | 1577 |
| 2026-09-19 | 1578 |
| 2026-09-20 | 1578 |
| 2026-09-23 | 1578 |
| 2026-09-24 | 1578 |
| 2026-09-25 | 1580 |
| 2026-09-27 | 1581 |
| 2026-09-28 | 1581 |
| 2026-09-29 | 1582 |
| 2026-10-05 | 1583 |
| 2026-10-08 | 1585 |
| 2026-10-12 | 1585 |
| 2026-10-13 | 1586 |
| 2026-10-15 | 1585 |
| 2026-10-16 | 1586 |
| 2026-10-19 | 1588 |
| 2026-10-20 | 1588 |
| 2026-10-21 | 1589 |
| 2026-10-22 | 1589 |
| 2026-10-23 | 1590 |
| 2026-10-25 | 1590 |
| 2026-10-28 | 1590 |
| 2026-10-30 | 1592 |
| 2026-10-31 | 1593 |
| 2026-11-03 | 1593 |
| 2026-11-04 | 1593 |
Today
— stars today
This week
+3 stars this week
This month
+10 stars this month
Momentum
18.0
growth rate 0.19%/day
# Brevitas
[](https://pepy.tech/project/brevitas)
[](https://github.com/Xilinx/brevitas/actions/workflows/pytest.yml)
[](https://github.com/Xilinx/brevitas/actions/workflows/examples_pytest.yml)
[](https://zenodo.org/badge/latestdoi/140494324)
Brevitas is a PyTorch library for neural network quantization, with support for both *post-training quantization (PTQ)* and *quantization-aware training (QAT)*.
**Please note that Brevitas is a research project and not an official Xilinx product.**
If you like this project please consider ⭐ this repo, as it is the simplest and best way to support it.
## Requirements
* Python >= 3.10
* [Pytorch](https://pytorch.org) >= 1.13, <= 2.13 (more recent versions would be untested).
* Windows, Linux or macOS.
* GPU training-time acceleration (*Optional* but recommended).
## Installation
You can install the latest release from PyPI:
```bash
pip install brevitas
```
## Getting Started
Brevitas currently offers quantized implementations of the most common PyTorch layers used in DNN under `brevitas.nn`, such as `QuantConv1d`, `QuantConv2d`, `QuantConvTranspose1d`, `QuantConvTranspose2d`, `QuantMultiheadAttention`, `QuantRNN`, `QuantLSTM` etc., for adoption within PTQ and/or QAT.
For each one of these layers, quantization of different tensors (inputs, weights, bias, outputs, etc) can be individually tuned according to a wide range of quantization settings.
As a reference for PTQ, Brevitas provides an example user flow for ImageNet classification models under [`brevitas_examples.imagenet_classification.ptq`](https://github.com/Xilinx/brevitas/blob/master/src/brevitas_examples/imagenet_classification/ptq/ptq_evaluate.py) that quantizes an input torchvision model using PTQ under different quantization configurations (e.g. bit-width, granularity of scale, etc).
For more info, checkout our [documentation](https://xilinx.github.io/brevitas/).
## Cite as
If you adopt Brevitas in your work, please cite it as:
```
@software{brevitas,
author = {Franco, Giuseppe and Monteagudo-Lago, Pablo and Colbert, Ian and Pappalardo, Alessandro and Fraser, Nicholas J},
title = {Xilinx/brevitas},
year = {2026},
publisher = {Zenodo},
doi = {10.5281/zenodo.3333552},
url = {https://doi.org/10.5281/zenodo.3333552}
}
```
## History
- *2026/09/23* - Release version 0.13.4, see the [release notes](https://github.com/Xilinx/brevitas/releases/tag/v0.13.4).
- *2026/09/18* - Release version 0.13.3, see the [release notes](https://github.com/Xilinx/brevitas/releases/tag/v0.13.3).
- *2026/08/28* - Release version 0.13.2, see the [release notes](https://github.com/Xilinx/brevitas/releases/tag/v0.13.2).
- *2026/08/25* - Release version 0.13.1, see the [release notes](https://github.com/Xilinx/brevitas/releases/tag/v0.13.1).
- *2026/07/14* - Release version 0.13.0, see the [release notes](https://github.com/Xilinx/brevitas/releases/tag/v0.13.0).
- *2025/08/28* - Release version 0.12.1, see the [release notes](https://github.com/Xilinx/brevitas/releases/tag/v0.12.1).
- *2025/05/09* - Release version 0.12.0, see the [release notes](https://github.com/Xilinx/brevitas/releases/tag/v0.12.0).
- *2024/10/10* - Release version 0.11.0, see the [release notes](https://github.com/Xilinx/brevitas/releases/tag/v0.11.0).
- *2024/07/23* - Minor release version 0.10.3, see the [release notes](https://github.com/Xilinx/brevitas/releases/tag/v0.10.3).
- *2024/02/19* - Minor release version 0.10.2, see the [release notes](https://github.com/Xilinx/brevitas/releases/tag/v0.10.2).
- *2024/02/15* - Minor release version 0.10.1, see the [release notes](https://github.com/Xilinx/brevitas/releases/Excerpt of 5,727 characters
Read on GitHub
703
512
109
76
42
17
9
7
Andrei Stoian · Zama.ai · France
4
4
jinchen · AMD · United States
3
2
2
1
1
Javier Duarte · UC San Diego · United States
1
1
1
1
vfdev · @openteams-ai
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:5a0af2740b05bd6a, topic:deep-learning, topic:pytorch
matched fp:5a0af2740b05bd6a, topic:quantization, desc:quantization, readme:quantization