Follow
Share
to
Twitter
Discord
GitHubWasmEdge is set to make a splash at two of the most awaited tech events of the year, WasmIO 2024 in Barcelona and KubeCon EU 2024 in Paris. With a series of engaging talks, workshops, and presentations lined up, these appearances highlight the increasing importance of efficient, portable AI/LLM inference and cloud-native technologies in today's fast-evolving digital landscape. From deep dives into cloud-native WebAssembly to innovative strategies for log processing and building business models around open-source projects, WasmEdge's contributions are poised to offer invaluable insights and practical solutions for developers, entrepreneurs, and tech enthusiasts looking to leverage the full potential of Wasm and AI technologies on the edge cloud and beyond.
WasmIO
EFFICIENT AND PORTABLE AI / LLM INFERENCE ON THE EDGE CLOUD [WORKSHOP]
MICHAEL YUAN - SECOND STATE
March 14 14:05 - 14:35
A workshop demonstrating how Wasm-based AI applications offer efficiency and portability across CPUs & GPUs, showcasing models and libraries for media processing, vision, and language.
https://2024.wasmio.tech/sessions/efficient-and-portable-ai-llm-inference-on-the-edge-cloud-workshop/
CREATE CLOUD NATIVE AGENTS AND EXTENSIONS FOR LLMS
VIVIAN HU - SECOND STATE
March 14 12:35 - 13:05
This talk explores the use of WasmEdge for building lightweight, portable, and secure LLM plugins and serverless applications, highlighting major use cases and technology stacks.
https://2024.wasmio.tech/sessions/create-cloud-native-agents-and-extensions-for-llms/
KubeCon EU +Cloud Native Con 2024
Main Conference Talks:
Tutorial: Cloud Native WebAssembly and How to Use It - Brooks Townsend, Cosmonic & Michael Yuan, Second State
A deep dive into WebAssembly, its standards, and how it integrates into cloud native infrastructure, including hands-on opportunities to create Wasm applications.
https://sched.co/1YeNZ
Wednesday March 20, 2024 16:30 - 18:00 CET
Pavilion 7 | Level 7.3 | N01-02
Tutorials, SDLC
Fast and Efficient Log Processing with Wasm and eBPF - Michael Yuan, Second State
Discusses advancements in lightweight log processing with Wasm and eBPF, showcasing a complete application for managing log data efficiently.
https://sched.co/1YeQM
Thursday March 21, 2024 17:25 - 18:00 CET
Pavilion 7 | Level 7.3 | S03
Track:Operations + Performance
Create Cloud Native Agents and Extensions for LLMs - Xiaowei Hu, Second State
Explores the use of WasmEdge for building lightweight, portable, and secure LLM plugins and serverless applications, highlighting major use cases and technology stacks.
https://sched.co/1YeRH
Friday March 22, 2024 14:00 - 14:35 CET
Pavilion 7 | Level 7.1 | Room A
Track: Emerging + Advanced
Lighting talk
WasmEdge, portable and lightweight runtime for AI/LLM workloads | Project Lightning Talk
Highlights the challenges of running AI/LLM workloads and how WasmEdge addresses these through lightweight, portable applications in Rust.
Tuesday March 19, 2024 16:10 - 16:17 CET
Pavilion 7 | Level 7.1 | Room D
Track:Project Opportunities
Colocated Event
Building an Open Core Business Model - Miley Fu & Michael Yuan, WasmEdge
Explores the Open Core Business Model, offering insights into commercializing open-source projects, with WasmEdge serving as a case study.
Tuesday March 19, 2024 14:00 - 14:25 CET
Pavilion 7 | Level 7.3 | Room E01
Track:Cloud Native StartupFest
Kiosk
Event Name: KC CNC EU 2024 - Project Pavilion Sandbox Kiosks (WED)
Date & Time: 10:45 - 15:00 (Central European Time) on Wednesday, March 20, 2024
Project Name: WasmEdge Runtime
The WasmEdge Runtime project has a booth in KubeCon as usual. The WasmEdge maintainers will be on-site to demonstrate how you can run any LLM on Hugging Face in GGML format across your personal computers and GPU chips using a same lightweight Wasm file! As an added feature, we'll show how to utilize container tools to manage these LLM inference applications. Rust + Wasm for LLM inference provides a way to achieve portability across heterogeneous AI hardware and platforms without sacrificing performance.
We welcome you to visit our booth (#PP16-A) to gain insights into cloud-native Wasm AI inference and also stand a chance to win exciting WasmEdge SWAGs.
For additional discussions and project updates, we invite you to join our Discord server. We look forward to seeing you at WasmIO and KubeCon!