https://github.com/atlarge-research/kavier
Science Score: 26.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (6.7%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: atlarge-research
- License: mit
- Language: Python
- Default Branch: master
- Size: 11.2 MB
Statistics
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Kavier
Simulating performance, sustainability, and efficiency of LLM Ecosystems under inference.
This repository is the home of Kavier, the first scientific instrument for predicting performance, sustainability, and efficiency of LLM ecosystems under inference, through discrete-event, cache-aware simulation.
Kavier helps operators, researchers, and engineers predict:
* Performance — pre-fill & decode latencies, throughput, GPU utilization
* Sustainability — energy, Wh/Mtoken/s, carbon emissions (kgCO2/Mtoken/s)
* Financial efficiency — €/Mtoken/s given GPU-hour prices
Structure
Documentation
We divide the documentation into the following sections:
- Getting Started
- Using the Kavier CLI
- Thesis
- Contributing guide
Contributing
Questions, suggestions and contributions are welcome and appreciated! Please refer to the contributing guidelines for more details.
License
Kavier is distributed under the MIT license. See LICENSE.txt.
Owner
- Name: @Large Research
- Login: atlarge-research
- Kind: organization
- Email: info@atlarge-research.com
- Website: http://atlarge-research.com/
- Twitter: LargeResearch
- Repositories: 24
- Profile: https://github.com/atlarge-research
Massivizing Computer Systems
GitHub Events
Total
- Push event: 1
- Fork event: 1
Last Year
- Push event: 1
- Fork event: 1
Dependencies
- actions/cache v4 composite
- actions/checkout v4 composite
- actions/setup-python v5 composite
- cachetools >=5.3
- hypothesis >=6.102
- numpy *
- pandas >=2.2
- pyarrow >=16.0
- pydantic >=2.7
- pytest >=8.2
- rich >=13
- tqdm *
- cachetools *
- numpy >=2.2.6
- pandas >=2.2.3
- pyarrow >=20.0.0
- pydantic >=2.11.5
- rich >=14.0.0
- tqdm >=4.67.1