Open Source Infrastructure for the AI Native Era
summary
Cloud Native Computing Foundation runs Kubernetes plus 230 projects and focuses on operationalizing AI: deploy, secure, observe, scale. Industry compute flips from 2/3 training to 2/3 inference this year and projects over 90+ gigawatts of inference capacity by decade’s end. Platforms like Ray on Kubernetes enable continuous training for better utilization (Uber case), and CNCF just added LLMD built on vLLM as an inference platform component.
AI-written summary · about
related talks
43mKeynote: Building AI in the Open: How the Cloud Native Community Shapes What Comes Next
17mKeynote - The Next Decade of Cloud Native
12m10 Years of CNCF and Cloud Native's Next Decade
12mKeynote: Building Enterprise AI/ML Platform on Kubernetes
04mA Cloud Native Stack From Bare Metal To Tokens for Large-Scale AI Inference
33mIBM's Approach to Building a Cloud-Native AI Platform
23mMaking Cloud Native Computing Universal and Sustainable
03mWelcome Back + Opening Remarks