A-SHOJAEI/adaptive-inference-router-with-cascade-serving

A research-grade adaptive inference routing system that learns to dynamically dispatch incoming requests across a cascade of model variants (quantized, pruned, distilled, full-precision) based on predicted query difficulty, SLA constraints, and real-time cluster load using multi-objective reinforcement learning.

11
/ 100
Experimental
No License No Package No Dependents
Maintenance 10 / 25
Adoption 0 / 25
Maturity 1 / 25
Community 0 / 25

How are scores calculated?

Stars

Forks

Language

Python

License

Last pushed

Feb 21, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/A-SHOJAEI/adaptive-inference-router-with-cascade-serving"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.