You can now choose from preset LLMs with images hosted by AKS and split inferencing across multiple lower-GPU count VMs […]

You can now schedule workloads in Fleet based on cost and availability of resource heuristics. Source: Microsoft Azure – aggiornamenti

You can now better understand the infra costs associated with running applications at the namespace and cluster levels and identify[…]

You can now run GPU workloads, such as machine learning, video encoding, large simulations, and gaming, on Windows nodepools in[…]

YOu can now use Gen 2 VM SKUs for Windows nodepools in AKS. Source: Microsoft Azure – aggiornamenti

You can now modify default values for kubelet parameters when using Windows nodepools in AKS. Source: Microsoft Azure – aggiornamenti

You can now take advantage of Kubernetes 1.29 version with AKS in production environment. Source: Microsoft Azure – aggiornamenti

You can now use deployment safeguards to implement Kubernetes best practices and get warnings on deployment or deny the deployment[…]

You can now scale beyond the current 65k Pod IPs and scale up to 1 Million Pods. Source: Microsoft Azure[…]

You can now deploy AKS clusters in dual stack mode which now enables resource connection through IPv4 or IPv6. Source:[…]