Skip to content

Scalable microservice leveraging DistilBERT, FastAPI, Docker, and Kubernetes (AWS EKS), featuring Redis caching and comprehensive load testing with k6 and Grafana.

Notifications You must be signed in to change notification settings

napronald/Full-End-to-End-Machine-Learning-API

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ML API — Kubernetes Deployment & Load Testing

This repo contains the code and infrastructure configuration for a machine-learning prediction API deployed on AWS EKS (Kubernetes) with Redis caching, Istio, and Grafana-based load-testing analysis (k6 + Prometheus).

I wrote a full project walkthrough here:

👉 Project Page: https://napronald.github.io/pages/mlapi.html

About this Repository

The goal of the project is to demonstrate how to run a real ML service in production-style infrastructure — including caching, autoscaling, and latency analysis under load.

About

Scalable microservice leveraging DistilBERT, FastAPI, Docker, and Kubernetes (AWS EKS), featuring Redis caching and comprehensive load testing with k6 and Grafana.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published