The Year of Full-Stack OSS AI!

​

​Start the new year with a full immersion in Open-Source AI, building end-to-end applications. We showcase AI leaders from soup to nuts, from hardware and inference to structured output with knowledge graphs.

​Bay Area AI, the longest-running, deepest, biggest, baddest AI meetup in the world (bay.area.ai) and AWS are inviting you to the iconic AW GenAI Loft for the first

​Full-Stack OSS AI event to start your year in AI — with four talks covering all sides of GenAI.

​Open-Source AI Knowledge Stack (OAKS)
Alexy Khrabrov, Neo4j

​We review the OSS AI ecosystem and propose a big tent approach to organizing knowledge for AI applications and building an ecosystem of OSS AI practitioners in LFAI.

​DIY LLMs with Modal
Charles Frye, Modal

​Running your own LLMs is harder than making an API call. But sometimes hard things are worth doing. In this talk, we'll walk through tips and tricks for self-hosting LLM inference using Modal, where provisioning GPUs is just an API call.

​Simple Knowledge Graphs with Outlines, neo4j, and Modal
Cameron Pfiffer, dottxt

​Learn how to convert unstructured data into a structured knowledge graph. In this talk, we'll use Outlines to structure language model output, neo4j to store a knowledge graph, and Modal to run our language model.

​Optimizing LLMs for Cost-Efficient Deployment with vLLM
Michael Goin, Neural Magic

Deploying LLMs is just the starting point; optimizing them for cost-efficient, high-performance serving is the real challenge. In this talk, we’ll explore cutting-edge compression techniques and advanced inference system optimizations that enable fast performance on your hardware of choice. Discover practical strategies and tools enterprises trust to scale deployments while minimizing costs.

​Please note that even though spacious, space is limited. Please manage your RSVP responsibly. We'll prioritize folks to honor their RSVPs for our previous events.