Security Slam North America 2022
Security Slam North America 2022 Published: February 1, 2023 The Cloud Native Computing Foundation (CNCF), in partnership with Sonatype, completed its 2022 Security Slam virtual event on November 21, 2022. The inaugural event featured the participation…
Kubernetes Operators: what are they? Some examples
Guest post originally published on the SparkFabrik blog Kubernetes offers limited initial functionality to ensure flexibility and scalability. K8s Operators are software extensions that make use of Kubernetes APIs to extend behavior. What do we need…
Helm Chart Repository Deprecation Update
Cross-post from Helm’s blog Back in 2019, when the Helm v2 support timeline and end of life plan was announced, the deprecation of the helm/charts GitHub repository was announced, as well. The primary reason for the deprecation is the significant…
Helm Project Update: New Location For Stable and Incubator Charts
Post originally published on Helm’s blog by Matt Farina As previously announced, the stable and incubator repositories have moved to a new location. This post will update you on the new locations and provide directions to…
Please join us in wishing Helm and its community a very happy 5th birthday! Helm is a popular package manager that provides an easy way to find, share, and use software built for Kubernetes. Our most…
Peer-to-Peer acceleration for AI model distribution with Dragonfly
The problem: AI model distribution is broken at scale Large-scale AI model distribution presents challenges in performance, efficiency, and cost. Consider a typical scenario: an ML platform team manages a Kubernetes cluster with 200 GPU nodes….
LLMs on Kubernetes Part 1: Understanding the threat model
Let’s say you’ve got an LLM running on Kubernetes. Pods are healthy, logs are clean, users are chatting. Everything looks fine. But here’s the thing: Kubernetes is great at scheduling workloads and keeping them isolated. It…
The weight of AI models: Why infrastructure always arrives slowly
As AI adoption accelerates across industries, organizations face a critical bottleneck that is often overlooked until it becomes a serious obstacle: reliably managing and distributing large model weight files at scale. A model’s weights serve as…
The platform under the model: How cloud native powers AI engineering in production
AI workloads are increasingly running on Kubernetes in production, but for many teams, the path from a working model to a reliable system remains unclear. The cloud native ecosystem – its projects, patterns, and community –…
Cloud native agentic standards
An application, composed of one or more containers as dictated by system architecture, that operates either independently or as part of a distributed collaboration—interacting with at least one other entity (container) or achieving quorum-based consensus. It…