LF Edge InfiniEdge AI Release 3.1 Code Lab
LF Edge InfiniEdge AI Release 3.1 Code Lab (2-Hour Intensive)
Meeting link: https://vc-us.larkoffice.com/j/882565401
InfiniEdge AI Release 3.1 Code Lab is a focused, hands-on technical session designed for engineers and architects building real AI systems across distributed edge environments.
Release 3.1 introduces improvements in:
Distributed edge runtime performance
Low-latency inference optimization
Model deployment automation
Edge-to-cloud coordination patterns
Production-grade observability
This 2-hour intensive session eliminates slideware and focuses on real deployment, real tuning, and real trade-offs.
Participants will:
Deploy an AI workload across edge nodes
Measure and optimize inference latency
Understand accuracy vs. latency vs. cost trade-offs
Explore hybrid edge + cloud orchestration patterns
Learn production-ready design practices
This Code Lab is ideal for AI engineers, platform teams, infra architects, robotics developers, and GenAI builders operating in latency-sensitive environments.
🗓 Agenda (2 Hours)
🤖 Live Demo: EngineAI Humanoid Robot Interaction
Experience a live demonstration of EngineAI humanoid robots interacting with the audience in real time.
Participants will see how AI models deployed through distributed edge infrastructure can power robotic perception, reasoning, and responsive behaviors.
The demo will showcase:
• Real-time AI inference at the edge powering robot responses
• Natural interaction between humans and humanoid robots
• Integration of robotics systems with edge AI runtime and cloud coordination
• Practical examples of how generative AI and robotics converge in real-world environments
Audience members will have the opportunity to interact directly with the humanoid robot and explore how edge-deployed AI enables responsive physical intelligence.
1️⃣ Welcome & Architecture Overview (15 min)
State of Edge AI
InfiniEdge AI 3.1 highlights
Control plane vs data plane architecture
2️⃣ Hands-On Lab: Deployment (30 min)
Set up edge runtime
Register & deploy model
Run inference pipeline
3️⃣ Hands-On Lab: Optimization (30 min)
Measure latency
Simulate constrained edge environment
Tune performance parameters
Evaluate trade-offs
4️⃣ Hybrid Patterns & Scaling (15 min)
Edge + cloud coordination
Kubernetes integration
Multi-node scaling strategy
5️⃣ OpenClaw: AI Agent Gateway (15 min)
What is OpenClaw — live install in less than 15 minutes
Connect AI models (Claude, GPT, Gemini) to mobile messaging channels
ClawHub skill marketplace — 3k+ community skills, one-command install
Download the slides here: Google Slides
5️⃣ Q&A + Community Roadmap (15 min)
Production challenges
Contribution pathways
Next release preview
Bring your laptop. Real systems. Real constraints. Real AI at the edge.