zhihu/ZhiLight
Inference EnginesA highly optimized LLM inference acceleration engine for Llama and its variants.
5.3
GitHub Metrics
Stars
905
Forks
102
Open Issues
5
Watchers
52
Contributors
9
Weekly Commits
0
Language
C++
License
Apache-2.0
Last Commit
Mar 18, 2026
Created
Dec 6, 2024
Latest Release
v0.4.8
Release Date
Dec 10, 2024
Synced: Jun 3, 2026
Quality Scores
Documentation Qualityw: 20%
4.1
No dedicated docs site. Description: 80 chars. Stars signal: 905. Contributors: 9. Score: 4.1/10
Community Healthw: 20%
5.5
Stars: 905. Contributors: 9. Watchers: 52. Forks: 102. Issue ratio: 0.6%. Score: 5.5/10
Maintenance Velocityw: 15%
4.4
Last commit: 77d ago. Weekly commits: 0. Latest release: v0.4.8. Maturity bonus: 1.5y old. Score: 4.4/10
API Design & DXw: 20%
7.0
Stars/issues ratio: 181. No dedicated API docs. Permissive license: Apache-2.0. Popularity signal: 905 stars. Score: 7/10
Production Readinessw: 15%
5.0
Battle-tested: 905 stars. Peer review: 9 contributors. Versioned: v0.4.8. Licensed: Apache-2.0. Age: 1.5 years. Maintenance: last commit 77d ago. Score: 5/10
Ecosystem Integrationw: 10%
6.1
Fork interest: 102. Ecosystem: C++. Integration-friendly: Apache-2.0. Adoption: 905 stars. Score: 6.1/10
Tags
cudadeepseek-r1gptinference-enginellamallmllm-inferencellm-servingmodel-servingpytorch
Radar
Documentation Quality
Community Health
Maintenance Velocity
API Design & DX
Production Readiness
Ecosystem Integration