🦙 Llama Stack: Zero to Production Hero

​You’ve played with Llama 2, Llama 3, or perhaps even Llama 4 models. Maybe you’ve set up your own inference endpoints to tap into these open-source models via API. Perhaps you’ve heard of guardrails, and even used a Llama Guard model?

​But have you heard of Llama Stack? It helps you “build once, deploy anywhere.”

​[It’s a] comprehensive system that provides a uniform set of tools for building, scaling, and deploying generative AI applications, enabling developers to create, integrate, and orchestrate multiple AI services and capabilities into an adaptable setup.”

​In other words, it helps you move from just using models to shipping real-world applications. Further, Llama Stack can help you scale from your GPU local GPU to an inference server, edge device, or even Kubernetes without rewriting your entire codebase!

​Meta’s open-source, universal framework standardizes every layer of a generative-AI workload—Inference, RAG, Agents, Tools, Safety, Evals, and Telemetry—behind one consistent set of APIs.

​We think that’s pretty dope, and we want to check it out live!

​Think of Llama Stack as the Docker + Kubernetes for Llama models: a composable server plus language-specific SDKs that let you swap providers without touching your application logic.

​During this event, we’ll cover the architecture of Llama Stack, discuss how you can use guardrails like Llama Guard as safety shields within the Llama Stack framework.

​In short, we’ll cover this end-to-end framework for building, shipping, and sharing agent, build a LangGraph-powered application on rails, and give you our take on how it stacks up against the competition!

​🤖 Who should attend

• ​AI engineers building production-grade Llama applications with guardrails

• ​Platform architects designing multi-environment ML infrastructure

• ​Open-source contributors & researchers curious about Llama 4 and the broader Meta ecosystem

• ​Dev-Ops/SRE teams who need predictable, repeatable LLM deployments

​Speakers:

• ​Dr. Greg” Loughnane is the Co-Founder & CEO of AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. Since 2021, he has built and led industry-leading Machine Learning education programs.  Previously, he worked as an AI product manager, a university professor teaching AI, an AI consultant and startup advisor, and an ML researcher.  He loves trail running and is based in Dayton, Ohio.

• ​Chris “The Wiz” Alexiuk is the Co-Founder & CTO at AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. During the day, he is also a Developer Advocate at NVIDIA. Previously, he was a Founding Machine Learning Engineer, Data Scientist, and ML curriculum developer and instructor. He’s a YouTube content creator YouTube who’s motto is “Build, build, build!” He loves Dungeons & Dragons and is based in Toronto, Canada.

​Follow AI Makerspace on LinkedIn and YouTube to stay updated about workshops, new courses, and corporate training opportunities.