STACKQUADRANT

gpustack/gpustack

Inference Engines

Performance-optimized AI inference on your GPUs. Unlock superior throughput by selecting and tuning engines like vLLM or SGLang.

7.0
GitHub Metrics
Stars
5.3k
Forks
576
Open Issues
618
Watchers
42
Contributors
46
Weekly Commits
32
Language
Python
License
Apache-2.0
Last Commit
Jul 17, 2026
Created
May 11, 2024
Latest Release
v2.2.1
Release Date
Jul 3, 2026
Synced: Jul 18, 2026
Quality Scores
Documentation Qualityw: 20%
7.4

Has docs site (https://gpustack.ai). Description: 128 chars. Stars signal: 5,337. Contributors: 46. Score: 7.4/10

Community Healthw: 20%
6.3

Stars: 5,337. Contributors: 46. Watchers: 42. Forks: 576. Issue ratio: 11.6%. Score: 6.3/10

Maintenance Velocityw: 15%
7.6

Last commit: 1d ago. Weekly commits: 0. Latest release: v2.2.1. Maturity bonus: 2.2y old. Score: 7.6/10

API Design & DXw: 20%
6.4

Stars/issues ratio: 9. Dynamic language: Python. Has documentation site. Permissive license: Apache-2.0. Popularity signal: 5,337 stars. Score: 6.4/10

Production Readinessw: 15%
7.3

Battle-tested: 5,337 stars. Peer review: 46 contributors. Versioned: v2.2.1. Licensed: Apache-2.0. Age: 2.2 years. Maintenance: last commit 1d ago. Score: 7.3/10

Ecosystem Integrationw: 10%
7.9

Fork interest: 576. Major ecosystem: Python. Integration-friendly: Apache-2.0. Adoption: 5,337 stars. Has web presence. Score: 7.9/10

Tags
ascendcudadeepseekdistributed-inferencegenaihigh-performance-inferenceinferencellamallmllm-inference
Radar
Documentation Quality
Community Health
Maintenance Velocity
API Design & DX
Production Readiness
Ecosystem Integration