STACKQUADRANT

alibaba/rtp-llm

Model Serving

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

6.0
GitHub Metrics
Stars
1.2k
Forks
219
Open Issues
157
Watchers
19
Contributors
104
Weekly Commits
0
Language
Cuda
License
Apache-2.0
Last Commit
Jun 28, 2026
Created
Dec 27, 2023
Latest Release
v0.2.0
Release Date
Oct 31, 2025
Synced: Jun 29, 2026
Quality Scores
Documentation Qualityw: 20%
5.4

No dedicated docs site. Description: 82 chars. Stars signal: 1,240. Contributors: 104. Score: 5.4/10

Community Healthw: 20%
5.9

Stars: 1,240. Contributors: 104. Watchers: 19. Forks: 219. Issue ratio: 12.7%. Score: 5.9/10

Maintenance Velocityw: 15%
6.2

Last commit: 0d ago. Weekly commits: 0. Latest release: v0.2.0. Maturity bonus: 2.5y old. Score: 6.2/10

API Design & DXw: 20%
5.4

Stars/issues ratio: 8. No dedicated API docs. Permissive license: Apache-2.0. Popularity signal: 1,240 stars. Score: 5.4/10

Production Readinessw: 15%
7.2

Battle-tested: 1,240 stars. Peer review: 104 contributors. Versioned: v0.2.0. Licensed: Apache-2.0. Age: 2.5 years. Maintenance: last commit 0d ago. Score: 7.2/10

Ecosystem Integrationw: 10%
6.7

Fork interest: 219. Ecosystem: Cuda. Integration-friendly: Apache-2.0. Adoption: 1,240 stars. Score: 6.7/10

Tags
gptinferencellamallmllm-servingllmopsmodel-serving
Radar
Documentation Quality
Community Health
Maintenance Velocity
API Design & DX
Production Readiness
Ecosystem Integration