Decentralized Federated Machine Learning: Empowering Edge Devices with Kubernetes
Discover how to implement Federated Machine Learning with Kubernetes for privacy-preserving model training across edge devices, enabling efficient image classification and scaled computations.
Edge DC Energy Efficiency: A Kubernetes Workload Allocation Optimizer with Generic Server Power Model
Discover how to achieve 50%+ power savings in edge data centers using K8s-compatible Workload Allocation Optimizer (WAO), featuring real-world implementation across 200+ servers and sustainable computing practices.
From Sensors to Servers: Efficient Edge Computing with Akri and WebAssembly
Discover how to optimize edge computing using Akri and WebAssembly for efficient IoT device management, data processing, and serverless applications in Kubernetes environments.
The Perfect Storm - Production Kubernetes Running on Ocean Vessels
Discover how a global shipping company implemented Kubernetes on ocean vessels, addressing unique challenges of edge computing at sea while managing distributed clusters and intermittent connectivity.
EfficientML.AI - Introduction to Efficient Machine Learning
Master efficient machine learning techniques and optimization strategies for deploying ML models in resource-constrained environments, focusing on practical implementation and performance tuning.
EfficientML.AI - Introduction to Efficient Machine Learning
Master efficient machine learning techniques and optimization strategies for deploying ML models in resource-constrained environments, focusing on practical implementation methods and performance enhancement.
Exploring KubeEdge: Architecture, Use Cases, and Project Graduation Updates
Discover KubeEdge's architecture and real-world applications in edge computing, from smart cities to industrial IoT, while exploring its integration with Kubernetes for efficient edge workload management.
Zero Downtime Development - Building Resilient and Scalable Systems
Discover techniques for developing resilient, distributed systems locally with zero downtime deployment, using live coding demonstrations and practical examples for modern cloud-native applications.
Eclipse sensiNact: IoT Device Modeling and Digital Twins
Discover how Eclipse sensiNact enables flexible IoT device modeling and digital twin creation, with practical examples from Jena Smart City demonstrating dynamic connectivity and modular architecture implementation.
What Can Storage Do for AI? - Optimizing NVMe Storage for Large Language Models
Explore how NVMe flash storage enables AI model deployment at scale, from data center training to edge device inference, with focus on optimization techniques and performance improvements.
The Wasm Wilderness: Technological Peaks We've Reached with WebAssembly
Explore WebAssembly's evolution beyond browsers, discovering its impact on cloud computing, IoT, and plugin systems while understanding the foundation of open standards.
Protecting WebAssembly Workloads with Confidential Computing and Trusted Execution Environments
Explore how to secure WebAssembly workloads using Confidential Computing and Trusted Execution Environments, focusing on WASI implementation, privacy-preserving AI, and practical applications in cloud/edge computing.
Unleash the Power of Open Source WASM on a Hyper-Distributed Cloud
Discover how Adobe leverages WebAssembly and edge computing with wasmCloud and Akamai to create secure, efficient, and integrated distributed applications across multiple data centers.
Choose Your Own Adventure: WebAssembly Deployment Workshop
Dive into WebAssembly deployment with an interactive workshop exploring wasmCloud, WASI-virt, and wasm-tools for flexible, cross-platform application development and deployment strategies.
Cloud-Native AI: Wasm in Portable, Secure AI/ML Workloads
Discover how WebAssembly enables portable and secure AI/ML workloads in cloud environments, focusing on deploying models like Llama3 and Mixtral across diverse platforms with optimal performance.
The Disruptive Potential of On-Device LLMs
Explore the transformative world of on-device LLMs, their advantages over traditional models, real-world applications, and future potential in AI technology through practical demonstrations and case studies.
WebAssembly: Everything, Everywhere, All at Once - An Introduction to the WebAssembly Ecosystem
Discover how WebAssembly enables true "build once, run everywhere" development across IoT, edge computing, cloud, and serverless architectures with hands-on demos and practical implementation.