taksha17

taksha17/lumen-stream-lab

Hybrid LLM orchestration — route prompts to the right model, measure +40% decode tok/s vs always-3B

1 stars 0 forks 1 watchers PowerShell MIT License
View on GitHub
1 Open Issue Need Help Last updated: Sep 2, 2026

Open Issues Need Help

View All on GitHub
Collaborators wanted: hardware profiles beyond GTX 1650 4GB 20 days ago
documentation help wanted good first issue hardware-profile
taksha17/lumen-stream-lab
1

Hybrid LLM orchestration — route prompts to the right model, measure +40% decode tok/s vs always-3B

PowerShell