Zeus

A Framework for Deep Learning Energy Measurement and Optimization.
https://github.com/ml-energy/zeus

Category: Consumption
Sub Category: Computation and Communication

Keywords

deep-learning energy mlsys

Keywords from Contributors

energy-consumption power power-consumption software-systems sustainability

Last synced: about 16 hours ago
JSON representation

Repository metadata

Measure and optimize the energy consumption of your AI applications!

Host: GitHub
URL: https://github.com/ml-energy/zeus
Owner: ml-energy
License: apache-2.0
Created: 2022-08-13T21:20:30.000Z (over 3 years ago)
Default Branch: master
Last Pushed: 2025-10-25T19:28:58.000Z (about 2 months ago)
Last Synced: 2025-10-27T20:51:35.760Z (about 2 months ago)
Topics: deep-learning, energy, mlsys
Language: Python
Homepage: https://ml.energy/zeus
Size: 155 MB
Stars: 306
Watchers: 9
Forks: 37
Open Issues: 14
Releases: 21
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- Funding: .github/FUNDING.yml
- License: LICENSE

README.md

Project News ⚡

[2025/05] We shared our experience and design philosophy for the ML.ENERGY leaderboard in this paper.
[2025/05] Zeus now supports CPU, DRAM, AMD GPU, Apple Silicon, and NVIDIA Jetson platform energy measurement!
[2024/11] Perseus, an optimizer for large model training, appeared at SOSP'24! Paper | Blog | Optimizer
[2024/05] Zeus is now a PyTorch ecosystem project. Read the PyTorch blog post here!
[2024/02] Zeus was selected as a 2024 Mozilla Technology Fund awardee!

Zeus is a library for (1) measuring the energy consumption of Deep Learning workloads and (2) optimizing their energy consumption.

Zeus is part of The ML.ENERGY Initiative.

Repository Organization

zeus/
├── zeus/             # ⚡ Zeus Python package
│  ├── monitor/       #    - Energy and power measurement (programmatic & CLI)
│  ├── optimizer/     #    - Collection of time and energy optimizers
│  ├── device/        #    - Abstraction layer over CPU and GPU devices
│  ├── utils/         #    - Utility functions and classes
│  ├── _legacy/       #    - Legacy code to keep our research papers reproducible
│  ├── metric.py      #    - Prometheus metric export support
│  ├── show_env.py    #    - Installation & device detection verification script
│  └── callback.py    #    - Base class for callbacks during training
│
├── zeusd             # 🌩️ Zeus daemon
│
├── docker/           # 🐳 Dockerfiles and Docker Compose files
│
└── examples/         # 🛠️ Zeus usage examples

Getting Started

Please refer to our Getting Started page.
After that, you might look at

Docker image

We provide a Docker image fully equipped with all dependencies and environments.
Refer to our Docker Hub repository and Dockerfile.

Examples

We provide working examples for integrating and running Zeus in the examples/ directory.

Research

Zeus is rooted on multiple research papers.
Even more research is ongoing, and Zeus will continue to expand and get better at what it's doing.

Zeus (NSDI 23): Paper | Blog | Slides
Chase (ICLR Workshop 23): Paper
Perseus (SOSP 24): Paper | Blog | Slides
The ML.ENERGY Benchmark (NeurIPS 25 D&B Spotlight): Paper | Repository

If you find Zeus relevant to your research, please consider citing:

@inproceedings{zeus-nsdi23,
    title     = {Zeus: Understanding and Optimizing {GPU} Energy Consumption of {DNN} Training},
    author    = {Jie You and Jae-Won Chung and Mosharaf Chowdhury},
    booktitle = {USENIX NSDI},
    year      = {2023}
}

Other Resources

Energy-Efficient Deep Learning with PyTorch and Zeus (PyTorch conference 2023): Recording | Slides

Contact

Jae-Won Chung (jwnchung@umich.edu)

Owner metadata

Name: ML.ENERGY
Login: ml-energy
Email: admins@ml.energy
Kind: organization
Description: Making modern ML energy-efficient
Website: https://ml.energy
Location: Ann Arbor, MI
Twitter:
Company:
Icon url: https://avatars.githubusercontent.com/u/109987045?v=4
Repositories: 12
Last ynced at: 2025-10-18T13:56:02.479Z
Profile URL: https://github.com/ml-energy

GitHub Events

Total

Create event: 46
Release event: 5
Issues event: 20
Watch event: 82
Delete event: 36
Member event: 1
Issue comment event: 52
Push event: 283
Pull request review comment event: 253
Pull request review event: 210
Pull request event: 88
Fork event: 11

Last Year

Create event: 40
Release event: 5
Issues event: 18
Watch event: 78
Delete event: 33
Member event: 1
Issue comment event: 47
Push event: 258
Pull request event: 81
Pull request review comment event: 226
Pull request review event: 195
Fork event: 11

Name	Email	Commits
Jae-Won Chung	j**g@u**u	324
Wonbin Jin	1****n	11
Parth Raut	6****t	8
Jisang Ahn	1****1	5
Luoxi Meng	6****m	5
Sharon Seungyu Han	8****h	4
danielhou0515	7****5	3
Divyam Sharma	4****m	2
HGangloff	h**f@i**r	2
Ting Sun	s**k@g**m	2
Yongseung Lee	5****1	2
Dorota Kopczyk	d**k@g**m	1
Kitsios Konstantinos	k**t@g**m	1
Vishweshwar Ramanakumar	6****1	1
Yu Fan	4****n	1
Zhenning Yang	z**9@g**m	1
jxunn	1****n	1

Issue and Pull Request metadata

Last synced: about 2 months ago

Total issues: 53
Total pull requests: 199
Average time to close issues: 3 months
Average time to close pull requests: 4 days
Total issue authors: 14
Total pull request authors: 17
Average comments per issue: 0.89
Average comments per pull request: 0.73
Merged pull request: 165
Bot issues: 0
Bot pull requests: 0

Past year issues: 9
Past year pull requests: 70
Past year average time to close issues: 12 days
Past year average time to close pull requests: 5 days
Past year issue authors: 6
Past year pull request authors: 10
Past year average comments per issue: 1.67
Past year average comments per pull request: 0.53
Past year merged pull request: 53
Past year bot issues: 0
Past year bot pull requests: 0

More stats: https://issues.ecosyste.ms/repositories/lookup?url=https://github.com/ml-energy/zeus

Top Issue Authors

jaywonchung (37)
parthraut (2)
sharonsyh (2)
wbjin (2)
michahn01 (1)
zyang37 (1)
amirzenoozi (1)
cmcantalupo (1)
Sunt-ing (1)
kitsiosk (1)
andife (1)
Weiwei1001 (1)
wuqs-net (1)
ImahnShekhzadeh (1)

Top Pull Request Authors

jaywonchung (98)
wbjin (26)
parthraut (14)
DdIiVvYyAaMm (10)
sharonsyh (10)
michahn01 (9)
danielhou0515 (6)
HGangloff (4)
vishwa-11 (4)
Sunt-ing (3)
show981111 (3)
jxunn (2)
fwrrong (2)
FuryMartin (2)
kitsiosk (2)

Top Issue Labels

enhancement (26)
good first issue (10)
integration (4)
bug (3)
documentation (2)
roadmap (2)
maintenance (1)
cpu (1)

Top Pull Request Labels

Package metadata

Total packages: 4
Total downloads:
- cargo: 3,586 total
- pypi: 1,086 last-month
Total dependent packages: 1 (may contain duplicates)
Total dependent repositories: 2 (may contain duplicates)
Total versions: 33
Total maintainers: 2

pypi.org: zeus

A framework for deep learning energy measurement and optimization.

Homepage: https://ml.energy/zeus
Documentation: https://ml.energy/zeus
Licenses: apache-2.0
Latest release: 0.12.3 (published 2 months ago)
Last Synced: 2025-10-29T20:21:44.672Z (about 2 months ago)
Versions: 9
Dependent Packages: 1
Dependent Repositories: 2
Downloads: 511 Last month
Rankings:
- Dependent packages count: 4.746%
- Dependent repos count: 11.571%
- Average: 12.942%
- Downloads: 22.508%
Maintainers (1)
- jaywonchung

pypi.org: zeus-ml

A framework for deep learning energy measurement and optimization.

Homepage: https://ml.energy/zeus
Documentation: https://ml.energy/zeus
Licenses: Apache 2.0
Latest release: 0.11.0 (published 11 months ago)
Last Synced: 2025-10-29T20:21:44.422Z (about 2 months ago)
Versions: 20
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 575 Last month
Rankings:
- Dependent packages count: 6.633%
- Stargazers count: 8.786%
- Forks count: 11.1%
- Average: 16.531%
- Downloads: 25.525%
- Dependent repos count: 30.611%
Maintainers (1)
- jaywonchung

crates.io: zeus

Zeus daemon

Homepage: https://ml.energy/zeus
Documentation: https://docs.rs/zeus/
Licenses: Apache-2.0
Latest release: 0.1.0 (published over 1 year ago)
Last Synced: 2025-10-29T20:21:43.816Z (about 2 months ago)
Versions: 2
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 1,482 Total
Rankings:
- Dependent repos count: 29.318%
- Dependent packages count: 33.812%
- Average: 34.288%
- Downloads: 39.734%
Maintainers (1)
- jaywonchung

crates.io: zeusd

Zeus daemon

Homepage: https://ml.energy/zeus
Documentation: https://docs.rs/zeusd/
Licenses: Apache-2.0
Latest release: 0.2.0 (published 11 months ago)
Last Synced: 2025-10-29T20:21:44.588Z (about 2 months ago)
Versions: 2
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 2,104 Total
Rankings:
- Dependent repos count: 27.35%
- Dependent packages count: 36.273%
- Average: 53.36%
- Downloads: 96.457%
Maintainers (1)
- jaywonchung

Dependencies

capriccio/requirements.txt pypi

datasets ==2.3.2
numpy ==1.22.3
pandas ==1.4.2

docs/requirements.txt pypi

black *
mkdocs-gen-files ==0.3.5
mkdocs-literate-nav ==0.4.1
mkdocs-section-index ==0.3.4
mkdocstrings ==0.19.0

.github/workflows/check_homepage_build.yaml actions

actions/checkout v3 composite
actions/setup-python v2 composite

.github/workflows/deploy_homepage.yaml actions

actions/checkout v3 composite
actions/setup-python v2 composite
cpina/github-action-push-to-another-repository v1.5 composite

.github/workflows/lint.yaml actions

actions/checkout v3 composite
actions/setup-python v2 composite

.github/workflows/publish_pypi.yaml actions

actions/checkout v3 composite
actions/setup-python v2 composite
pypa/gh-action-pypi-publish release/v1 composite

.github/workflows/push_docker.yaml actions

actions/checkout v3 composite
docker/build-push-action v3 composite
docker/login-action v2 composite
docker/metadata-action v4 composite
docker/setup-buildx-action v2 composite

Dockerfile docker

nvidia/cuda 11.3.1-devel-ubuntu20.04 build

examples/imagenet/requirements.txt pypi

torch *
torchvision *

examples/ZeusDataLoader/capriccio/requirements.txt pypi

datasets >=1.8.0
protobuf *
scikit-learn *
scipy *
sentencepiece *
torch >=1.3
transformers ==4.17.0

examples/ZeusDataLoader/cifar100/requirements.txt pypi

torch *
torchvision *

examples/ZeusDataLoader/imagenet/requirements.txt pypi

torch *
torchvision *

pyproject.toml pypi

numpy *
nvidia-ml-py *
pandas *
pydantic *
rich *
scikit-learn *

Score: 17.051946497575873

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Sustainable Technology