Fall Meet Up with vLLM, Meta & AMD
You are invited for "vLLM, Meta and AMD Meet-up" on November 12th, 2025, from 4:30 PM to 8:30 PM at Playground, Palo Alto! Join us for an engaging evening with fellow builders, researchers and curious minds, featuring hands-on workshop, tech talks, networking opportunities, delicious food and drinks. Seats are limited. We encourage you to register in advance to secure your spot.
Agenda
4:30 PM: Workshop Registration
4:45 PM - 5:30 PM: Group workshop (Optional)
5:15 PM: Meet Up Registration
5:40 - 5:45: Welcome opening talk by Ramine Roane
5:45 - 5:50: Update about AMD's Open-source initiative by Anush Elangovan
5:50 PM - 6:10 PM: vLLM Overview, Update, and Roadmap by Simon Mo
6:10 PM - 6:25 PM: High Performance LLM Inference with vLLM by Lu Fang
6:25 PM - 6:45 PM: vLLM Performance Optimization on AMD GPU by Andy Luo
6:45 PM - 8:30 PM: Reception & Networking
Workshop details:
Title: Building a Two-Agent System on AMD GPUs (vLLM + MCP)
Discover how to design and deploy a multi-agent AI system that combines reasoning, perception, and real-time tool use, powered by open models running efficiently on AMD GPUs. In this instructor-led, hands-on Agents workshop, you’ll learn how to:
- Connect multiple specialized agents through the Model Context Protocol (MCP) to enable seamless communication and tool sharing.
- Run open-weight models with vLLM for high-performance inference on AMD GPUs.
- Build an interactive pipeline where agents coordinate tasks, exchange structured information, and produce reliable, explainable results.
By the end of the session, you’ll have implemented a functional two-agent system that showcases how open hardware, open models, and open protocols can power the next generation of intelligent, action-taking AI applications.
[Please bring a laptop, all other tools and resources will be provided through AMD Developer Cloud]
By registering for this event and entering Playground’s offices, you agree to comply with their Visitor Policy, which can be found here.