HomeAI Tutorial

edge-serve-ab

Public

This project is a FastAPI + ONNX Runtime microservice that serves image inference with A/B routing, optional shadow traffic, token-bucket rate limiting, payload size guards, and end-to-end observability (Prometheus metrics, Grafana dashboards, structured logs, request tracing).

Creat2025-09-16T16:24:04
Update2025-09-16T21:14:20
0
Stars
0
Stars Increase

Related projects