Observing and monitoring Large Language Model workloads with Ray
Ambassador post by Swastik Gour Introduction The emergence of Large Language Models (LLMs) such as GPT-4, PHI2, BERT, and T5 revolutionized natural language processing, with these models empowering high-end applications, including chatbots, recommendation systems, and analytics….
Platform engineering at KubeCon + CloudNative NA 2024 in Salt Lake City
Ambassador post originally published on Medium by Mathieu Benoit, CNCF Ambassador KubeCon NA 2024 in Salt Lake City was a blast! Like always, I met with old friends, I made new friends and I had deep…
CEL-ebrating simplicity: mastering Kubernetes policy enforcement with CEL
Community post by Kevin Conner, Chief Engineer, Getup Cloud and co-author of Kubernetes in Action 2nd Edition As Kubernetes deployments grow in scale and complexity, policy enforcement becomes a critical aspect of maintaining secure and reliable…
Unlocking cloud native security with Cilium and eBPF
Ambassador post originally published on Dev.to by Syed Asad Raza Introduction 🌐🔒🚀 As cloud-native applications scale, securing workloads while maintaining performance becomes critical. This is where Cilium, an open-source networking, observability, and security tool, shines. Backed…
Cloud Native Live: Enabling self-service for developers using Kubernetes operators
The Kubernetes Operator pattern is one of the most powerful features of Kubernetes, allowing you to extend your cluster with any functionality you need. Many vendors and CNCF projects have made their APIs accessible through operators….
Solving Android app issues with OpenTelemetry: Beyond local profiling
Member post originally published on the Embrace blog by Francisco Prieto Cardelle OpenTelemetry is a powerful observability framework that can help engineers monitor and resolve common Android performance issues. We’ll dive into a few of these…
Running a production-ready Raspbery Pi Kubernetes cluster at home
Ambassador post originally published on Gerald on IT by Gerald Venzl In this guide, I’ll cover how to run a production-ready Raspberry Pi Kubernetes Cluster using K3s. Background If you are like me, you probably have…
CNCF On demand webinar: Security and performance optimization with the API gateway
In today’s distributed systems, APIs form the backbone of software architecture. This presentation will explore how Kong Gateway’s powerful tools can be leveraged to ensure API management security, scalability, and performance optimization.
What is Inference Parallelism and how it works
Member post originally published on the InfraCloud blog by Aman Juneja, Principal Solutions Engineer at InfraCloud Technologies In recent years, we’ve witnessed two recurring trends: the release of increasingly powerful GPUs and the introduction of Large…
Implementing Cilium for Superior Cloud Native Networking QingCloud’s journey with Cilium began in 2019 when their team noticed the project and recognized its superior networking performance over similar CNI solutions. “In 2019, some of our customers…