Day 3 – April 24, 2026
Discussion Groups
BRK3-029A-DG • Kubernetes, Cloud Runtimes • Advanced Technical
Building an AI supercomputer: Scale Slurm workloads on GKE
location_on
Reef A
schedule
12:30 PM - 1:00 PM
Dive into the architecture of running Slurm on GKE for large-scale AI training. We will detail the new Managed Slinky architecture and its deep integration with Google’s AI Hypercomputer stack—including Cluster Director and native TPU support. Learn how to combine the raw throughput of bare-metal HPC with the operational simplicity of GKE to accelerate your model training velocity.
Read more