[registration required on lu.ma/_ai] Full Stack OSS AI: Chips to Apps!
[registration required on lu.ma/_ai] Full Stack OSS AI: Chips to Apps! was a developer community event in San Francisco.
Talks & recordings
4 connected sessions
DIY LLMs with Modal
Running your own LLMs is harder than making an API call, but sometimes hard things are worth doing. Tips and tricks for self-hosting LLM inference using Modal, where provisioning GPUs is just an API call.
DevReal: Simple Knowledge Graphs with Outlines, neo4j, and Modal, Cameron Pfiffer
How to convert unstructured data into a structured knowledge graph using Outlines to structure language model output, Neo4j to store the knowledge graph, and Modal to run the language model.
Open-Source AI Knowledge Stack (OAKS)
A review of the OSS AI ecosystem proposing a big tent approach to organizing knowledge for AI applications and building an ecosystem of OSS AI practitioners in LFAI.
Optimizing LLMs for Cost-Efficient Deployment with vLLM
Cutting-edge compression techniques and advanced inference system optimizations that enable fast LLM performance on hardware of choice. Practical strategies and tools enterprises use to scale deployments while minimizing costs.
Connections
5 relationships