raketenkater/llm-server

Model Serving

Auto-tuned launcher for GGUF models on llama.cpp / ik_llama.cpp — OpenAI-compatible server with multi-GPU tensor-split, MoE expert placement, measured flag tuning (AI Tune), hardware-matched HuggingFace downloads, and crash recovery. An Ollama alternative for multi-GPU rigs.

GitHub →

5.1

GitHub Metrics

Stars

280

Forks

Open Issues

Watchers

Contributors

Weekly Commits

Language

License

MIT

Last Commit

Oct 17, 2026

Created

Mar 11, 2026

Latest Release

v3.2.11

Release Date

Oct 14, 2026

Synced: Oct 17, 2026

Quality Scores

Documentation Qualityw: 20%

3.9

No dedicated docs site. Description: 275 chars. Stars signal: 280. Contributors: 3. Score: 3.9/10

Community Healthw: 20%

2.5

Stars: 280. Contributors: 3. Watchers: 3. Forks: 18. Issue ratio: 2.1%. Score: 2.5/10

Maintenance Velocityw: 15%

9.7

Last commit: 0d ago. Weekly commits: 54. Latest release: v3.2.11. Score: 9.7/10

API Design & DXw: 20%

6.4

Stars/issues ratio: 47. Typed language: Go. No dedicated API docs. Permissive license: MIT. Popularity signal: 280 stars. Score: 6.4/10

Production Readinessw: 15%

3.8

Battle-tested: 280 stars. Peer review: 3 contributors. Versioned: v3.2.11. Licensed: MIT. Age: 0.6 years. Maintenance: last commit 0d ago. Score: 3.8/10

Ecosystem Integrationw: 10%

4.8

Fork interest: 18. Major ecosystem: Go. Integration-friendly: MIT. Adoption: 280 stars. Score: 4.8/10