gpu scheduling
2 articles

Red Hat AI 3.5 Upgrade: GPU Serving and Token Showback
Assess the Red Hat AI 3.5 upgrade in 2026 with a GPU serving acceptance lab, tenant isolation matrix, token showback reconciliation, and compatibility and recovery checks.
October 14, 2026• 24 min read
red hat ai 3.5 upgradered hat aiopenshift ai

MIG vs MPS vs Time-Slicing for Kubernetes GPU Sharing
A 2026 decision guide for Kubernetes GPU sharing: compare isolation, memory behavior and scheduler resources, then use a workload worksheet, canary scorecard and rollback plan.
October 1, 2026• 26 min read
kubernetes gpu sharingmig vs mpsgpu time-slicing