Turn foundation models into production AI on Microsoft Foundry | BRKSP91
Microsoft Foundry Fireworks Ai Llm Inference Azure Ai Model Deployment Enterprise Ai Mlops Foundation Models Production Ai Provisioned Throughput
This session demonstrates how to build production-ready AI systems by integrating Fireworks AI with Microsoft Foundry for model customization, optimized inference, and enterprise-scale deployment. Through a live demo and case study, developers learn practical patterns for reducing cost, latency, and time-to-production using PTU mode and Azure integration. Designed for developers and ML engineers building production AI systems.
Related videos
Turn APIs, tools, and data into real agent velocity | DEM331
Turn your agents into action: Connect tools, APIs, and documents | BRK242
Frontier Tuning: Microsoft Build 2026
Microsoft Foundry + Agent 365: Microsoft Build 2026
Deliver production-ready AI search on unstructured data with RAG | ODSP925
From observability to ROI for AI agents on any framework | BRK252
Beyond VLLM: Distributed LLM Inferencing With Llm-d on Kubernetes - Ravindra Patil, Red Hat
What's new for AI on GKE: Training, serving, and agents
Engineering the future of Kubernetes for AI at scale
From pilot to production: Scaling Gemini with proven practices
From Prompt Hacking to Architectural Determinism: Engineering Reliable GenAI Systems
