Standardized Serverless ML Inference Platform on Kubernetes

Deploying machine learning model using 10+ different deployment tools

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

작업 과정에서 공부한 내역들 정리

KServe Inference Graph Example

Rocks for Kserve

Fine-tuning a BERT model for sentiment analysis and deploy it as a scalable API using Docker, Kubernetes and KServe.

A complete MLOps demo integrating Kubeflow Pipelines with S3, MLflow, and KServe. Designed for learning and experimentation.

AWS EKS + IRSA, Volumes, ISTIO & KServe+ NextJS App + Fastapi Serve + kubernetes + Helm charts + Multimodel or LLM-Deployment The School of AI EMLO-V4 course assignment https://theschoolof.ai/#programs

An end to end machine learning prediction for rossamann store problem

AWS EKS + ArgoCD + Canary deployment + IRSA, Volumes, ISTIO & KServe+ kubernetes + Classifier Deployment The School of AI EMLO-V4 course assignment https://theschoolof.ai/#programs