AI Briefing#aws-eks
The latest AI and developer news about #aws-eks, with the original source and a short summary.
The latest AI and developer news about #aws-eks, with the original source and a short summary.
Using a Warm Pool reduces gVisor sandbox startup time to approximately 57ms, eliminating runtime differences.
F&F built an in-house LLM platform combining **Amazon Bedrock** and **LiteLLM** to manage everything from key issuance to cost blocking.
Lotte On introduced SentryOn, an RCA agent that automates root cause analysis for its AWS EKS-based MSA environment.
Using PodAffinity and do-not-disrupt, we auto-scaled EKS node groups for Job workloads.
A case study on introducing EKS Node Group autoscaling tailored to Job workloads.
Yogiyo summarized the issues it encountered while starting chaos experiments on membership-yo with AWS FIS.
Using Bottlerocket data volume snapshots, image pull time was reduced from 15 minutes to around 10 seconds.
By separating Karpenter from the ASG and applying constraints and reservation settings, they achieved both stability and cost savings.
Kurly's Data Service Development Team built a zero-downtime real-time serving system for its cart recommendation model through TorchServe tuning and GracefulShutdown implementation.
A chatbot service operations team adopted NetApp Spot to reduce AWS EKS operating costs by about 40% while maintaining uninterrupted service through an SLA guarantee.
Devsisters introduced Pod Identity Webhook instead of kube2iam in its EKS environment to grant least-privilege IAM permissions on a per-pod basis.