Closing Remarks
Organiserat KubeCon + CloudNativeCon + OpenInfra Summit + PyTorch Conference China 2026 · 2026-09-07..09-09·
summary
A working token factory is described that stitches OpenStack, Kubernetes, LLMD, Hammy, PyTorch and vLLM into a single pipeline that actually generates tokens and answers questions rather than just showing slides. The claim is concrete: a deployed stack runs inference, scales on Kubernetes, and served interactive responses at the event. Notes emphasize multi‑project integration and global open source collaboration as the engineering focus and success metric.
AI-written summary · about
related talks
16mKeynote: An Open-Source Stack for AI Compute: Kubernetes + Ray + PyTorch + vLLM
23mAn Open Source Post-Training Stack: Kubernetes + Ray + PyTorch + vLLM
15mKeynote: From Platforms to AI Factories. Has Kubernetes Solved It?
08mKeynote: Plug in and Scale: Serving LLM Models on Kubernetes Ma...
06mSponsored Keynote: Building Your AI Factory: Wh...
27mThe playbook for a sovereign Model-as-a-Service platform
11mKeynote: Open Source Stack Empowers the AI Era
22mBuilding a MLOps Platform with Kubeflow on GKE
