b4rtaz/distributed-llama

Inference Engines

Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.

GitHub →

6.1

GitHub Metrics

Stars

3.0k

Forks

248

Open Issues

Watchers

Contributors

Weekly Commits

Language

C++

License

MIT

Last Commit

Jul 5, 2026

Created

Dec 5, 2023

Latest Release

v0.16.5

Release Date

Feb 2, 2026

Synced: Sep 2, 2026

Quality Scores

Documentation Qualityw: 20%

5.0

No dedicated docs site. Description: 137 chars. Stars signal: 3,050. Contributors: 15. Score: 5/10

Community Healthw: 20%

6.1

Stars: 3,050. Contributors: 15. Watchers: 52. Forks: 248. Issue ratio: 1.6%. Score: 6.1/10

Maintenance Velocityw: 15%

5.7

Last commit: 58d ago. Weekly commits: 0. Latest release: v0.16.5. Maturity bonus: 2.7y old. Score: 5.7/10

API Design & DXw: 20%

6.8

Stars/issues ratio: 64. No dedicated API docs. Permissive license: MIT. Popularity signal: 3,050 stars. Score: 6.8/10

Production Readinessw: 15%

6.3

Battle-tested: 3,050 stars. Peer review: 15 contributors. Versioned: v0.16.5. Licensed: MIT. Age: 2.7 years. Maintenance: last commit 58d ago. Score: 6.3/10

Ecosystem Integrationw: 10%

7.0

Fork interest: 248. Ecosystem: C++. Integration-friendly: MIT. Adoption: 3,050 stars. Score: 7/10