horovod
Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
GraphCanon updated today · GitHub synced today
Trust & integrity
Full report- Maintenance
- Active (21d since push)
- As of today · Source: github_public_v1
- Provenance
- Not a fork · Organization account
- As of today · Source: github_public_v1
- Security (OSV)
- No lockfile
- As of today · Source: none
Public GitHub metadata and optional OSV dependency scans. Signals, not a guarantee. Trust methodology.
Overview
Horovod is designed to facilitate fast and easy distributed deep learning training across multiple frameworks such as TensorFlow, Keras, PyTorch, and Apache MXNet by optimizing the communication and coordination between distributed processes.
Capability facts
- Languages
- python
Source: github.language · Jul 12, 2026
Categories
Tags
README
.. raw:: html
<p align="center"><img src="https://user-images.githubusercontent.com/16640218/34506318-84d0c06c-efe0-11e7-8831-0425772ed8f2.png" alt="Logo" width="200"/></p>
<br/>
Horovod
.. raw:: html
.. image:: https://badge.fury.io/py/horovod.svg :target: https://badge.fury.io/py/horovod :alt: PyPI Version
.. image:: https://badge.buildkite.com/6f976bc161c69d9960fc00de01b69deb6199b25680a09e5e26.svg?branch=master :target: https://buildkite.com/horovod/horovod :alt: Build Status
.. image:: https://readthedocs.org/projects/horovod/badge/?version=latest :target: https://horovod.readthedocs.io/en/latest/ :alt: Documentation Status
.. image:: https://img.shields.io/badge/slack-chat-green.svg?logo=slack :target: https://forms.gle/cPGvty5hp31tGfg79 :alt: Slack
.. raw:: html
.. raw:: html
.. image:: https://img.shields.io/badge/License-Apache%202.0-blue.svg :target: https://img.shields.io/badge/License-Apache%202.0-blue.svg :alt: License
.. image:: https://app.fossa.com/api/projects/git%2Bgithub.com%2Fhorovod%2Fhorovod.svg?type=shield :target: https://app.fossa.com/projects/git%2Bgithub.com%2Fhorovod%2Fhorovod?ref=badge_shield :alt: FOSSA Status
.. image:: https://bestpractices.coreinfrastructure.org/projects/2373/badge :target: https://bestpractices.coreinfrastructure.org/projects/2373 :alt: CII Best Practices
.. image:: https://pepy.tech/badge/horovod :target: https://pepy.tech/project/horovod :alt: Downloads
.. raw:: html
.. inclusion-marker-start-do-not-remove
|
Horovod is a distributed deep learning training framework for TensorFlow, Keras, PyTorch, and Apache MXNet. The goal of Horovod is to make distributed deep learning fast and easy to use.
.. raw:: html
Horovod is hosted by the LF AI & Data Foundation <https://lfdl.io>_ (LF AI & Data). If you are a company that is deeply
committed to using open source technologies in artificial intelligence, machine, and deep learning, and want to support
the communities of open source projects in these domains, consider joining the LF AI & Data Foundation. For details
about who's involved and how Horovod plays a role, read the Linux Foundation announcement <https://lfdl.io/press/2018/12/13/lf-deep-learning-welcomes-horovod-distributed-training-framework-as-newest-project/>_.
|
.. contents::
|
Documentation
Latest Release <https://horovod.readthedocs.io/en/stable>_master <https://horovod.readthedocs.io/en/latest>_
|
Why Horovod?
The primary motivation for this project is to make it easy to take a single-GPU training script and successfully scale it to train across many GPUs in parallel. This has two aspects:
- How much modification does one have to make to a program to make it distributed, and how easy is it to run it?
- How much faster would it run in distributed mode?
Internally at Uber we found the MPI model to be much more straightforward and require far less code changes than previous
solutions such as Distributed TensorFlow with parameter servers. Once a training script has been written for scale with
Horovod, it can run on a single-GPU, multiple-GPUs, or even multiple hosts without any further code changes.
See the Usage <#usage>__ section for more details.
In addition to being easy to use, Horovod is fast. Below is a chart representing the benchmark that was done on 128 servers with 4 Pascal GPUs each connected by RoCE-capable 25 Gbit/s network:
.. image:: https://user-images.githubusercontent.com/16640218/38965607-bf5c46ca-4332-11e8-895a-b9c137e86013.png :alt: 512-GPU Benchmark
Horovod achieves 90% scaling efficiency for both Inception V3 and ResNet-101, and 68% scalin