OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Brevitas

Brevitas is a Python library that adds configurable quantized neural-network layers to PyTorch and supports post-training quantization and quantization-aware training.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Brevitas — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Brevitas when a Python and PyTorch workflow needs quantized layer implementations for PTQ or QAT, or when comparing configurable quantization settings.

Who it is for

  • PyTorch developers integrating quantization into neural-network models.
  • Researchers comparing quantization settings such as bit width and scale granularity.
  • Model developers exploring quantized workflows oriented toward FPGA optimization.

Documented uses

  • Apply post-training quantization to an existing PyTorch model.
  • Use quantized layers in quantization-aware training.
  • Tune quantization settings for inputs, weights, biases and outputs.
  • Compare PTQ configurations on an ImageNet classification model.
Before you choose

Requirements & limits

The repository documents installation of the latest release from PyPI using pip.

  • The listed environment requires Python 3.10 or later and PyTorch versions 1.13 through 2.13.
  • The project lists Windows, Linux and macOS.
  • GPU acceleration for training is optional but recommended.
  • The README characterizes Brevitas as a research project, not an official Xilinx product.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Brevitas for a PyTorch project

Install the library in an environment meeting its listed Python and PyTorch requirements.

Before you start

  • Python 3.10 or later
  • PyTorch 1.13 through 2.13
  • Windows, Linux or macOS

Steps

  1. Prepare a Python environment with the listed Python and PyTorch versions.

  2. Install the latest release from PyPI with the command below.

    Documented command
    pip install brevitas

Expected outcome

Brevitas is installed for use with PyTorch.

Guide limitations

  • GPU acceleration for training is optional, though recommended.
  • The README says PyTorch versions newer than 2.13 would be untested.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
Xilinx/brevitas · Official homepage title · retained in its source language
How we review sourcesSuggest a correction