STACKQUADRANT

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.🎉

6.6
GitHub Metrics
Stars
5.5k
Forks
429
Open Issues
6
Watchers
136
Contributors
41
Weekly Commits
0
Language
Python
License
GPL-3.0
Last Commit
Aug 14, 2026
Created
Aug 27, 2023
Latest Release
v2.6.20
Release Date
Jun 17, 2025
Synced: Aug 28, 2026
Quality Scores
Documentation Qualityw: 20%
5.5

No dedicated docs site. Description: 127 chars. Stars signal: 5,478. Contributors: 41. Score: 5.5/10

Community Healthw: 20%
7.3

Stars: 5,478. Contributors: 41. Watchers: 136. Forks: 429. Issue ratio: 0.1%. Score: 7.3/10

Maintenance Velocityw: 15%
5.3

Last commit: 14d ago. Weekly commits: 0. Latest release: v2.6.20. Maturity bonus: 3.0y old. Score: 5.3/10

API Design & DXw: 20%
7.0

Stars/issues ratio: 913. Dynamic language: Python. No dedicated API docs. License: GPL-3.0. Popularity signal: 5,478 stars. Score: 7/10

Production Readinessw: 15%
7.3

Battle-tested: 5,478 stars. Peer review: 41 contributors. Versioned: v2.6.20. Licensed: GPL-3.0. Age: 3.0 years. Maintenance: last commit 14d ago. Score: 7.3/10

Ecosystem Integrationw: 10%
7.3

Fork interest: 429. Major ecosystem: Python. License: GPL-3.0. Adoption: 5,478 stars. Score: 7.3/10

Tags
awesome-llmdeepseekdeepseek-r1deepseek-v3flash-attentionflash-attention-3flash-mlallm-inferenceminimax-01mla
Radar
Documentation Quality
Community Health
Maintenance Velocity
API Design & DX
Production Readiness
Ecosystem Integration