Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes

Hopsworks - Data-Intensive AI platform with a Feature Store

🪐 1-click Kubeflow using ArgoCD

Carbon Limiting Auto Tuning for Kubernetes

AWS SageMaker, SeldonCore, KServe, Kubeflow & MLflow, VectorDB

My repo for the Machine Learning Engineering bootcamp 2022 by DataTalks.Club

The Machine Learning Zoomcamp teaches foundational and advanced ML concepts using tools like NumPy, Pandas, Scikit-Learn, TensorFlow, XGBoost, Flask, Docker, AWS, Kubernetes, and KServe. It covers regression, classification, evaluation metrics, neural networks, deployment strategies, and end-to-end projects to bridge theory and practice.

End-to-end MLOps architecture built for polyp segmentation — featuring distributed Ray training, MLflow experiment tracking, and automated CI/CD with Kubeflow Pipelines and KServe (Triton) deployment on Google Kubernetes Engine.

Collection of bet practices, reference architectures, examples, and utilities for foundation model development and deployment on AWS.

This repository demonstrates how to deploy, scale, and monitor machine learning models on Kubernetes using KServe and Kubeflow Lite components.

Deploying machine learning model using 10+ different deployment tools

Client/Server system to perform distributed inference on high load systems.

Hands-on labs on deploying machine learning models with tf-serving and KServe

A demo to accompany our blogpost "Scalable Machine Learning with Kafka Streams and KServe"

Kubeflow examples - Notebooks, Pipelines, Models, Model tuning and more

Everything to get industrial kubeflow applications running in production

TeiaCareInferenceClient is a C++ inference client library that implements KServe protocol

In this video, we’ll walk you through building a powerful machine learning model using Kubeflow and deploying it seamlessly to KServe with InferenceService!

A scalable RAG-based Wikipedia Chat Assistant that leverages the Llama-2-7b-chat LLM, inferenced using KServe

MLOps platform for intelligent document processing and validation. Includes OCR, data pipelines, model training, MLflow tracking, Airflow orchestration, and model serving via Seldon Core. Designed for scalable document recognition and classification in enterprise environments