Save $900/Day with WasmEdge: Live Demos on Self-Hosted AI & GenAI Stacks at KubeCon China 2025

Jun 03, 2025 • 3 minutes to read

The cloud-native and open-source community is buzzing with anticipation for the upcoming KubeCon + CloudNativeCon China 2025, scheduled to take place in Hong Kong from June 10-11, 2025. This once-in-a-year premier event promises to be a remarkable gathering of open-source luminaries, industry leaders, and developers, offering unparalleled opportunities for face-to-face interactions and insights into the future of open source and cloud-native computing.

A standout presence at this year's conference will undoubtedly be Second State/ WasmEdge team. As a key player in the open source and AI landscape, Second State and WasmEdge are poised to showcase our cutting-edge open-source AI tech explorations and AI solutions through prominent keynotes, insightful regular talks, and engaging booth presence. Notably, Vivian Hu, Product Manager at Second State and a founding member of WasmEdge, is serving as a Program Co-Chair for KubeCon + CloudNativeCon China 2025.

Keynotes and talks

Keynote: An Optimized Linux Stack for GenAI Workloads by Michael Yuan https://sched.co/1x5jJ
Dr. Michael Yuan, Founder and Maintainer of WasmEdge, will address the complexities of running Generative AI (GenAI) workloads on Linux, particularly within containerized environments. He will highlight how CNCF's project, with its immutable system, can be optimized for both host and guest systems, and its powerful support for cross-platform and cross-GPU Wasm workloads

Keynote: How We Save $900 per Day with Self-Hosted AI: Building Scalable Local LLM Infrastructure – Vivian Hu, Product Manager, Second State & Lv Yi, CTO, 5miles https://sched.co/1x5hf
Vivian Hu, Product Manager at Second State and a founding member of WasmEdge, along with Lv Yi from 5miles, will share practical insights into building scalable local LLM infrastructure and the significant cost savings achieved through self-hosted AI. This keynote will demonstrate how companies can leverage open-source solutions to deploy and manage large language models efficiently, ensuring privacy, customization, and cost control.

  • Date & Time: Wednesday, June 11, 2025, 09:48 - 09:58 HKT
  • Location: Level 16 | Grand Ballroom I

Project Lightning Talk: What's New in WasmEdge 0.15.0? - Michael Yuan, Maintainer https://sched.co/1xjzT
This release brings key WebAssembly features including the component model proposal, plus expanded support for multimodal models and the latest OpenVINO plugin support.

  • Date & Time: Tuesday June 10, 2025 12:10 - 12:15 HKT
  • Location: Level 16 | Grand Ballroom I

Lightning Talk: Scaling AI With Wasm and Edge Computing - Miley Fu, WasmEdge https://sched.co/1x5j1
Exciting potential of combining WebAssembly (Wasm) with edge computing to scale AI workloads. This session will cover how WasmEdge enables efficient and portable AI inference across diverse edge devices, offering a glimpse into the future of highly scalable AI applications.

  • Date & Time: Tuesday, June 10, 2025, 17:08 HKT
  • Location: Level 16 | Grand Ballroom I

WasmEdge Kiosk

WasmEdge will also have a dedicated kiosk during KubeCon + CloudNativeCon China 2025. This is an excellent opportunity to meet directly with WasmEdge maintainers, discuss the project's progress, and get a glimpse into the exciting roadmap ahead. Make sure to stop by early as swags will be gone fast! Find our kiosk in the Project Pavilion.
Table #: P-8
Table Shift: Tuesday 10:15 - 14:30
Location: Solutions Showcase – Level 16 | Grand Ballroom II

Conclusion

Second State and WasmEdge are thrilled to be a significant part of KubeCon + CloudNativeCon China 2025. Our keynotes and talks are meticulously designed to offer practical insights into the effective deployment and management of LLMs within cloud-native environments. Whether you're a seasoned developer, a cloud-native enthusiast, or an AI researcher, our sessions will provide straightforward advice and clear guidance on leveraging WebAssembly and Kubernetes for your AI projects.

We eagerly anticipate connecting with the community, sharing our ideas, and demonstrating the transformative potential of WasmEdge. We can't wait to meet you, so be sure to stop by and chat with us!

LLMOsmosis-StructurAI inferenceRustWebAssembly
A high-performance, extensible, and hardware optimized WebAssembly Virtual Machine for automotive, cloud, AI, and blockchain applications