Peer Relays + Kubernetes, minus the headache. Kubernetes Operator 1.102 brings Peer Relays directly into Kubernetes, expands IPv6 support, and improves certificate handling for larger deployments. Start simplifying connectivity between your clusters →

Chen Goldberg took Kubernetes from open-source project to the backbone of modern cloud. Now our EVP of Product & Engineering, she's doing it again for AI. Catch @GoldbergChen keynoting #FullyConnected26#. Sept 29–Oct 1, SF. Register here:

Multi-cloud Kubernetes inventory sounds simple… until you add an AI agent to the mix. 🪿 @pavanmadduri27 shares a reference design for using goose to collect Kubernetes inventory from OKE and AKS. The design uses read-only cloud credentials and human approval, so the model can coordinate the work without controlling access.

Most production inference services run on Kubernetes, where declarative configuration helps coordinate distributed services. Running one inference server in a Slurm job is easy; running a production-style topology across multiple containers and nodes is not. NVIDIA’s open-source srt-slurm ( provides a YAML-based orchestration layer for these deployments. It coordinates sbatch and srun, GPU placement, networking, readiness checks, and cleanup for systems involving prefill/decode disaggregation, multiple workers, Dynamo frontends, KV-cache-aware routers, and KV-cache offloading services. It’s useful for quickly deploying representative inference systems for testing or benchmarking on GPU clusters that already run Slurm. Great work to @0xishand and the rest of the @NVIDIAAI team on this!

Supermicro is simplifying Edge AI deployments with validated Kubernetes solutions powered by @RedHat and @EverpureData! By combining Supermicro's edge computing infrastructure with Red Hat OpenShift and the Portworx by Everpure data management platform for AI workloads, organizations can more easily deploy, manage, scale, and secure AI applications across distributed edge environments. Check out the full post by @storagereview:

talked to an agency running 23 customer environments on their own kubernetes and docker setup. they hit a wall hard. turns out the build vs buy inflection point for agent infra is way lower than most people think. somewhere around 20 environments is where it breaks. you can manage 5, maybe 10 yourself. past that you're spending more time babysitting infrastructure than actually building agents for clients.

Need dynamic configuration for Swift services running on Kubernetes? Swift Configuration supports hot reloading, watching specific values, and more. Learn more on the CNCF blog:

Nutanix is overhauling its Elevate Partner Program with new rebates for cross-selling Kubernetes, database, storage and AI products. In today's episode of CRN In Depth, @CRN's @MarkHaranas breaks down how @nutanix partners can turn these changes into profit, as well as details on the AI-powered Deal Coach tool and a formal role for system integrators. You can watch the entire episode here: @NutanixPartners