Fine-Tuning - 1

2025 (5)

November (2)

azure: [In preview] Public Preview: Microsoft Foundry Fine-Tuning Updates

Azure Updates

2025-11-18

Microsoft Foundry Fine-Tuning enters Public Preview with a complete UI redesign that emphasizes an agent-first experience. The updated interface streamlines model creation, evaluation, and deployment workflows and adds integration with Visual Studio to improve developer and data scientist productivity.

azure: [In preview] Announcing: Developer Training tier for low-cost fine-tuning training

Azure Updates

2025-11-18

Microsoft Foundry announced a Developer Training tier (preview) that offers ultra-low-cost fine-tuning model training by using spot capacity. The tier aims to provide training affordability comparable to the existing Developer hosting tier, specifically for the training phase of fine-tuning workflows.

October (3)

ai: A Developer’s Guide to Fine-Tuning GPT-4o for Image Classification on Azure AI Foundry

Microsoft AI Foundry Blog

2025-10-20

This guide demonstrates how to quickly improve image classification accuracy by fine-tuning GPT-4o (a vision-language model) on Azure OpenAI via Azure AI Foundry. It targets ML practitioners, app developers, and curious users, and emphasizes that boosting performance can be done without deep learning expertise through a step-by-step walkthrough.

ai: The Developer’s Guide to Smarter Fine-tuning: Unlock custom AI for every business challenge

Microsoft AI Foundry Blog

2025-10-14

Azure AI Foundry provides a streamlined platform for smarter, faster, and more accessible fine-tuning so developers can customize models for practical business problems — from reasoning agents to adaptive tools and scalable workflows — accompanied by best practices, hands-on resources, and recent innovations to accelerate development, testing, and deployment.

azure: [Launched] Generally Available: AI toolchain operator add-on (KAITO) for AKS

Azure Updates

2025-10-07

Microsoft announced general availability of the AI toolchain operator add-on (KAITO) for Azure Kubernetes Service (AKS). KAITO streamlines deployment of AI inference and fine-tuning workflows using popular open-source frameworks, with vLLM set as the default inference engine to simplify management and scaling of model serving.