The GenAI, cloud-native and pen source community is eagerly anticipating the upcoming KubeCon + CloudNativeCon + Open Source Summit + AI_dev China 2024, set to take place in Hong Kong 21-23rd August. This event promises to be a remarkable gathering of open-source luminaries, including the legendary Linus Trovalds and other star speakers. Developers will have the rare opportunity for face-to-face interactions with these influential figures, as well as with Jim Zemlin, the CEO of the Linux Foundation, and other industry leaders.
One of the standout presences will be Second State and WasmEdge, with our 2 booths and multiple talks, showcasing open source cloud-native technologies and AI solutions, and also our team member Miley as the cohost introducing Linus for his keynote! Here's a detailed look at our involvement and the exciting sessions lined up.
Keynote talks:
1. Running LLMs in the Cloud by Miley Fu https://sched.co/1flFB
- Date & Time: Thursday, August 22, 2024, 09:30 - 09:45 HKT
- Location: Level 2 | Grand Ballroom 1-2
- Summary: Miley Fu, Developer Advocate at Second State, will delve into the burgeoning demand for running large language models (LLMs) in cloud environments. Her keynote will cover the essentials of deploying open-source LLMs using three key approaches: Python-based solutions, native runtimes such as llama.cpp or vLLM, and WebAssembly (Wasm) as an abstraction layer. Attendees will gain insights into the practical aspects, benefits, and challenges of each approach, with a focus on real-world applications and the CNCF CNAI ecosystem landscape.
2. Deploying LLM Workloads on Kubernetes by Tianyang Zhang and Xiaowei Hu https://sched.co/1eYa5
- Date & Time: Friday, August 23, 2024, 09:05 - 09:20 HKT
- Location: Level 2 | Grand Ballroom 1-2
- Summary: This keynote by Tianyang Zhang from Huawei Cloud and Xiaowei Hu from Second State will highlight the integration of WasmEdge and Kuasar for deploying LLM workloads on Kubernetes. They will demonstrate the deployment of Llama3-8B on a Kubernetes cluster, showcasing the enhanced efficiency, scalability, and stability provided by these technologies.
Regular Talks
1. Project Lightning Talk: WasmEdge 0.14.0 Release Highlight by Hydai https://sched.co/1f4zL
- Date & Time: Wednesday, August 21, 2024, 11:49 - 11:54 HKT
- Location: Level 2 | Grand Ballroom 1-2
- Summary: Hydai will provide a quick update on the key features introduced in WasmEdge 0.14.0, including WasmGC, Typed Function Reference, Exception Handling, and the integration of llama.cpp as a plugin for executing LLMs. Attendees will get a glimpse of the future roadmap for WasmEdge.
2. Leveraging Wasm for Portable AI Inference Across GPUs, CPUs, OS & Cloud-Native Environments | - Miley Fu & Hung-Tung Tai, Second State https://sched.co/1eYYO
- Date & Time: Wednesday August 21, 2024 17:15 - 17:50 HKT
- Location: Level 1 | Hung Hom Room 7
- Summary: This talk will focus on the advantages of using WebAssembly for running AI inference tasks in a cloud-native ecosystem. We will explore how wasm empowers devs to develop on their own PC and have their AI inference uniformly performed across different hardware, including GPUs and CPUs, operating systems, edge cloud etc. We'll discuss how Wasm and Wasm runtime facilitates seamless integration into cloud-native frameworks, enhancing the deployment and scalability of AI applications, highlighting how Wasm provides a flexible, efficient solution suitable for diverse cloud-native architectures, including Kubernetes and docker, to allow developers to fully tap the potential of LLMs, especially open source LLMs.
3. Self-Hosted LLM Agent on Your Own Laptop or Edge Device by Michael Yuan https://sched.co/1eYXf
- Date & Time: Wednesday, August 21, 2024, 14:40 - 15:15 HKT
- Location: Level 1 | Hung Hom Room 3
- Summary: This talk will discuss the benefits of running open-source LLMs on personal or private devices. He will demonstrate how to build a complete AI agent service using the WasmEdge + Rust stack for LLM inference, highlighting its privacy, customization, and cost control advantages.
4. WebAssembly on the Server by Vivian Hu https://sched.co/1eYZR
- Date & Time: Thursday, August 22, 2024, 14:40 - 15:15 HKT
- Location: Level 1 | Hung Hom Room 6
- Summary: This talk will explore the role of WebAssembly in cloud-native environments, particularly on the server side. She will discuss the integration between Wasm and existing container tools, as well as use cases and future directions for WebAssembly in LLM applications.
5. New Advances for Cross-Platform AI Applications in Docker by Michael Yuan https://sched.co/1eYaP
- Date & Time: Friday, August 23, 2024, 11:25 - 12:00 HKT
- Location: Level 1 | Hung Hom Room 2
- Summary: This talk will focus on enhancing cross-platform GPU/AI workloads within container ecosystems using Docker's WebGPU standard. Michael Yuan will showcase how WasmEdge leverages this standard to create portable LLM inference applications in Rust.
6. Write Once Run Anywhere, but for GPUs by Michael Yuan https://sched.co/1eYaf
- Date & Time: Friday, August 23, 2024, 13:20 - 13:55 HKT
- Location: Level 1 | Hung Hom Room 3
- Summary: This talk will discuss the design and implementation of LlamaEdge, a lightweight and high-performance LLM inference runtime built on WasmEdge. He will demonstrate how LlamaEdge enables cross-platform LLM app development and deployment across various devices and environments.
Second State Sponsor Booth
Second State is proud to be a silver sponsor of KubeCon + CloudNativeCon + Open Source Summit + AI_dev China 2024. Come to Booth No.S8 to explore the solution of portable and lightweight LLM inference for GPUs and use cases of local LLMs.
We have adorable stickers, baseball caps, power banks, WasmEdge T-shirts and mini cooling fans ready for you and they will be gone fast! First come, first served!
Date & Time: Wednesday to Friday, August 21-23, 2024, 10:00 - 17:55 HKT
WasmEdge Kiosk
As a project hosted by CNCF, WasmEdge will have a kiosk time at KubeCon + CloudNativeCon + Open Source Summit + AI_dev China 2024. Come to chat with WasmEdge maintainers and learn the progress and roadmap of WasmEdge in Wednesday afternoon!
Find our kiosk in the Project Pavilion WasmEdge
Table #: T4
Table Shift: Wednesday 15:00 - 20:00 Location: Solutions Showcase | Level 2 | Grand Ballroom 3-4
Conclusion
WasmEdge is excited to be a part of KubeCon + CloudNativeCon + Open Source Summit + AI_dev China 2024, and we’re looking forward to connecting with the community. Our keynotes and talks are designed to offer practical insights into how you can effectively deploy and manage LLMs in cloud-native environments. Whether you're a developer, cloud-native enthusiast, or AI researcher, our sessions will give you straightforward advice and clear guidance on using WebAssembly and Kubernetes for your AI projects. We can’t wait to meet you, share our ideas, and show you what WasmEdge can do. Make sure to stop by and chat with us!