264001
eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJid2V2ZW50cy1wdWJsaWMtYXBpIiwiYXVkIjpbInB1YmxpYy13ZWIiXSwic3ViIjoiaHR0cHM6Ly93d3cuZ29vZ2xlY2xvdWRldmVudHMuY29tIiwiaWF0IjoxNzc1MDUzOTM5LCJuYmYiOjE3NzUwNTM5MzksImV4cCI6MTc3NTA1NzUzOSwiY29udGV4dCI6eyJwYXlsb2FkIjp7ImlkIjoiIiwicmVnVHlwZU5hbWUiOiIiLCJldmVudF9pZCI6IjI2NDAwMSIsImNfMzI5MDQxNiI6IiJ9fX0.qJPt34K7hedtm02vk7kkELE385RbMk86T5QmhFuWInE
phase 5 session info modal
Day 1 – April 22, 2026
Lightning Talks
DEVLT-301 • Architecture, Compute, Storage • Advanced Technical
LLM Inference on GKE for the rest of us
location_on Developer Theater
schedule 3:00 PM - 3:25 PM

Learn to deploy LLMs efficiently without a hyperscale budget. This session explores practical strategies to optimize LLM inference on Kubernetes, balancing performance, scalability, and cost. We’ll dive into container and model optimization, accelerator management, storage, load balancing, and observability. Walk away with actionable tools to maximize the cost-to-performance ratio for your AI workloads.

 Read more
This agenda widget contains logic for handling same sessions available at multiple times
GTM Tracking Header name present
Session
contains logic for gtm tracking when modal open