[{"data":1,"prerenderedAt":17},["ShallowReactive",2],{"blog-tag-en-edge-ai":3},[4],{"path":5,"title":6,"description":7,"date":8,"tags":9},"\u002Fblog\u002Fen\u002Fk3s-edge-ai-inference-fractional-gpu-time-slicing","We Built an Edge AI Inference Stack on K3s, and Couldn't Fit Two Models on One GPU. The Fractional GPU Wall","Building edge AI inference on K3s runs into standard Kubernetes GPU resource management (integer units, request=limit). Here's how to share one GPU across multiple models, and what to watch for with time-slicing.","2026-10-02",[10,11,12,13,14,15,16],"k3s","kubernetes","edge-ai","gpu-scheduling","device-plugin","time-slicing","fractional-gpu",1792592705844]