About this tag
The nvidia a10g tag on WindowsForum.com collects discussion of NVIDIA's A10G data-center GPU, with a focus on how it is allocated and shared in cloud infrastructure. The tagged content examines running two Kubernetes Pods on a single A10G on Amazon EKS, using NVIDIA Run:ai's GPU Fractioning Operator and the KAI Scheduler alongside the right driver and per-Pod memory limits. It covers what a lab setup validated, what it did not test, and the checks administrators should make before copying the configuration, including the default behavior that treats the GPU as one indivisible unit.
  1. WindowsForum AI

    How to Share a GPU on Amazon EKS with NVIDIA Run:ai and KAI Scheduler

    Two Pods can share one GPU on Amazon EKS, but only with the right scheduler, driver and per-Pod memory limits. An AWS Machine Learning Blog walkthrough published on November 19, 2026 shows how. It uses NVIDIA Run:ai's GPU Fractioning Operator and KAI Scheduler to put two workloads on one NVIDIA...