Beyond Round-Robin: GPU-Aware Load Balancing for LLM Inference in Kubernetes - Seokhwan Kong, NETLOX

315 views

About this video

Advanced · Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidence

Teaches GPU-aware load balancing for LLM inference on Kubernetes, moving beyond round-robin. Performance optimization technique for accelerated workloads.

A 32-minute video from The Linux Foundation: “Beyond Round-Robin: GPU-Aware Load Balancing for LLM Inference in Kubernetes - Seokhwan Kong, NETLOX”.

Video by The Linux Foundation, played through YouTube's embedded player.

Part of Open Source Summit Korea 2026