Operations | Monitoring | ITSM | DevOps | Cloud

17: There's No Life Without AI: Agents, MCP, and the Future of Automation With Viktor Farcic

Sep 22, 2026 By Kubex In Densify
On this episode of Kubex Talks, technology critic Viktor Farcic returns to talk with Andrew Hillier about the rapidly changing landscape in tech. Viktor has gone from AI skeptic to believer, claiming that there really is no life without AI anymore, from a professional standpoint.
View Video
Kubex

Open Sourcing Kubex's GPU Process Exporter: Gain Visibility in Your Shared GPUs

Sep 17, 2026 By Kubex In Densify
Table of Contents GPU sharing with NVIDIA hardware is becoming easier to adopt in Kubernetes but it hasn’t been easier to observe. Time-slicing lets multiple workloads share the same GPU. MPS allows CUDA workloads to execute concurrently. Schedulers like KAI make it easier to manage these shared environments. But sharing a GPU introduces a problem that is easy to underestimate.
Read Post
Kubex

Making Shared GPUs Even Safer with Kubex and HAMi-core

Sep 3, 2026 By Kubex In Densify
Table of Contents A few months ago, we introduced Kubex support for the KAI Scheduler to improve GPU sharing for production inference workloads. The basic model is simple: The KAI Scheduler handles placement and GPU sharing. Kubex continuously observes usage and adjusts those allocations as demand changes. KAI provides the scheduling foundation. It lets multiple workloads share a GPU while accounting for the amount of GPU each workload requests. Kubex then closes the loop.
Read Post
Kubex

Moving Beyond OOM Kills: Introducing Memory QoS in Kubernetes 1.37

Sep 2, 2026 By Kubex In Densify
Table of Contents For most of Kubernetes’ history, memory management has been a blunt instrument. Cross your limit, and the kernel kills your container. There has been no equivalent to CPU throttling, no graceful backpressure, just a hard stop. With Kubernetes 1.37, that changes: Memory QoS, built on cgroups v2, graduates to Beta and is enabled by default.
Read Post
Kubex

Kubernetes Resource Optimization Platforms: Top Vendor Comparison

Aug 25, 2026 By Kubex In Densify
Table of Contents Kubernetes resource optimization appears to be a single problem, but the platforms that address it disagree on almost every design decision, starting with how they analyze workload demands. Some set CPU and memory requests from live signals, while others learn a workload’s historical pattern and provision ahead of it.
Read Post

Sharing GPUs without Flying Blind: Kubernetes Patterns for AI Inference

Aug 13, 2026 By Kubex In Densify
GPU sharing is quickly becoming a practical requirement for Kubernetes-based AI inference, as many modern workloads don’t need a full GPU to deliver value. But safely placing multiple containers on the same accelerator brings new challenges: scheduling, fairness, isolation, observability, and noisy-neighbor behavior. This 20 min session explore the GPU sharing landscape across Kubernetes: time-slicing, MPS, MIG, KAI Scheduler, and HAMi, and dives into the harder problem: operating shared GPUs in production, from tracking usage to enforcing fairness as demand shifts.
View Video
Kubex

Inference Optimization Techniques. Ray vs. vLLM vs. KubeRay

Aug 7, 2026 By Kubex In Densify
Serving large language models at scale is fundamentally a distributed systems problem. A single GPU, or even a single node, is rarely enough once you need multiple models, multiple replicas, tensor-parallel sharding across GPUs, or high-availability rollouts. Kubernetes solves general container orchestration well, but it has no native concept of a GPU-aware, actor-based compute cluster.
Read Post
Kubex

Kubernetes GPU Scheduling for MLOps and GPU Sharing

Aug 6, 2026 By Kubex In Densify
The default Kubernetes scheduler was built for stateless services: web servers, APIs, databases. It schedules a pod, checks that a node has enough of whatever resources were requested, and binds it. For CPU and memory, that model works fine. For GPUs, it falls apart in three specific ways. First, GPUs are treated as an opaque integer resource.
Read Post
Kubex

Don't Trust the Diff: Making AI-Generated Code Reviewable And Maintainable

Jul 23, 2026 By Kubex In Densify
Coding agents changed implementation economics faster than they changed confidence. They let us produce more code, more quickly, but they did not make reviewers any better at understanding system-wide consequences. In our Kubernetes automation stack, that gap became impossible to ignore once AI started generating meaningful amounts of controller code.
Read Post

Copyright © 2026 OpsMatters™. All rights reserved.