xlite-dev/Awesome-LLM-Inference

Inference Engines

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

GitHub →

6.5

GitHub Metrics

Stars

5.3k

Forks

381

Open Issues

—

Watchers

132

Contributors

Weekly Commits

Language

Python

License

GPL-3.0

Last Commit

Apr 20, 2026

Created

Aug 27, 2023

Latest Release

v2.6.20

Release Date

Jun 17, 2025

Synced: Jun 3, 2026

Quality Scores

Documentation Qualityw: 20%

5.5

No dedicated docs site. Description: 127 chars. Stars signal: 5,270. Contributors: 39. Score: 5.5/10

Community Healthw: 20%

7.3

Stars: 5,270. Contributors: 39. Watchers: 132. Forks: 381. Issue ratio: 0.0%. Score: 7.3/10

Maintenance Velocityw: 15%

4.9

Last commit: 44d ago. Weekly commits: 0. Latest release: v2.6.20. Maturity bonus: 2.8y old. Score: 4.9/10

API Design & DXw: 20%

7.0

Stars/issues ratio: 5270. Dynamic language: Python. No dedicated API docs. License: GPL-3.0. Popularity signal: 5,270 stars. Score: 7/10

Production Readinessw: 15%

7.0

Battle-tested: 5,270 stars. Peer review: 39 contributors. Versioned: v2.6.20. Licensed: GPL-3.0. Age: 2.8 years. Maintenance: last commit 44d ago. Score: 7/10

Ecosystem Integrationw: 10%

7.2

Fork interest: 381. Major ecosystem: Python. License: GPL-3.0. Adoption: 5,270 stars. Score: 7.2/10