KServe
Kubeflow’s Graduation Is a Vote for Kubernetes as the AI Control Plane
Kubeflow’s CNCF graduation signals growing confidence in Kubernetes as a common control plane for production AI workloads, from training and pipelines to governance and inference ...
Alan Shimel | | agentic AI, AI infrastructure, AI lifecycle, AI platform, AI Workloads, cloud native AI, cncf, Distributed Training, enterprise AI, GPU scheduling, KServe, Kubeflow, Kubeflow graduation, Kubeflow Pipelines, Kubeflow Trainer, kubernetes, Kubernetes AI, MLOps, OpenTelemetry, platform engineering
Kubernetes Wasn’t Built for GPUs. Make It Behave
Kubernetes counts whole GPUs and treats pods as disposable. An LLM pod is neither. Share the silicon with MIG/MPS/time-slicing and stop paying for idle ...
Sneha Gullapalli | | A100, AI infrastructure, AI Workloads, cloud native AI, Dynamic Resource Allocation, GPU autoscaling, GPU cost reduction, GPU optimization, GPU partitioning, GPU sharing, GPU time-slicing, GPU utilization, H100, Karpenter, KServe, Kubernetes DRA, Kubernetes GPU scheduling, LLM Inference, model caching, multi-instance GPU, NVIDIA GPU Operator, NVIDIA MIG, NVIDIA MPS, scale-to-zero, VRAM
Open Source KServe AI Inference Platform Becomes CNCF Project
The CNCF adopts KServe to strengthen cloud-native AI inference on Kubernetes as platforms like Red Hat OpenShift AI expand model-as-a-service capabilities ...

