STACKQUADRANT

flashinfer-ai/flashinfer

Inference Engines

FlashInfer: Kernel Library for LLM Serving

7.8
GitHub Metrics
Stars
6.6k
Forks
1.6k
Open Issues
1.2k
Watchers
58
Contributors
433
Weekly Commits
25
Language
Cuda
License
Apache-2.0
Last Commit
Oct 13, 2026
Created
Jul 22, 2023
Latest Release
v0.7.1
Release Date
Oct 9, 2026
Synced: Oct 13, 2026
Quality Scores
Documentation Qualityw: 20%
7.7

Has docs site (https://flashinfer.ai). Description: 42 chars. Stars signal: 6,600. Contributors: 433. Score: 7.7/10

Community Healthw: 20%
7.5

Stars: 6,600. Contributors: 433. Watchers: 58. Forks: 1,574. Issue ratio: 18.0%. Score: 7.5/10

Maintenance Velocityw: 15%
9.8

Last commit: 0d ago. Weekly commits: 25. Latest release: v0.7.1. Maturity bonus: 3.2y old. Score: 9.8/10

API Design & DXw: 20%
6.3

Stars/issues ratio: 6. Has documentation site. Permissive license: Apache-2.0. Popularity signal: 6,600 stars. Score: 6.3/10

Production Readinessw: 15%
8.2

Battle-tested: 6,600 stars. Peer review: 433 contributors. Versioned: v0.7.1. Licensed: Apache-2.0. Age: 3.2 years. Maintenance: last commit 0d ago. Score: 8.2/10

Ecosystem Integrationw: 10%
7.8

Fork interest: 1,574. Ecosystem: Cuda. Integration-friendly: Apache-2.0. Adoption: 6,600 stars. Has web presence. Score: 7.8/10

Tags
attentioncudadistributed-inferencegpujitlarge-large-modelsllm-inferencemoenvidiapytorch
Radar
Documentation Quality
Community Health
Maintenance Velocity
API Design & DX
Production Readiness
Ecosystem Integration