2:00-3:00pm, 3rd September 2026

Online

Overview

Join this webinar to discover how Slinky brings Slurm’s HPC scheduling strengths into Kubernetes for large-scale AI and multi-node GPU workloads. You will see where Kubernetes alone can struggle with resource planning, how the Slurm Operator enables Slurm-managed workflows in Kubernetes, and how topology-aware scheduling with NVIDIA systems and tools like Topograph helps place jobs efficiently across modern NVLink and InfiniBand clusters. We will also briefly discuss native scheduling tools such as NVIDIA Run:ai and Slurm Bridge.

During the webinar there will be an opportunity to ask questions.

Who is the webinar for?

Anyone working in research computing infrastructure who is interested in learning more about Slurm on Kubernetes.

Speaker

Steve Blow is a technical leader at NVIDIA focused on AI infrastructure, scheduling, and Kubernetes-based accelerated computing. His work bridges traditional Slurm-managed supercomputing environments with cloud-native workflows, helping teams run large-scale GPU workloads more efficiently. He specialises in scheduling, topology-aware placement, and practical systems design for modern NVIDIA architectures

Register Now

All ACIT hub events are covered by our code of conduct by registering and attending you agree to support us in making our events professional, comfortable, safe and accessible for all participants.