264001
eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJid2V2ZW50cy1wdWJsaWMtYXBpIiwiYXVkIjpbInB1YmxpYy13ZWIiXSwic3ViIjoiaHR0cHM6Ly93d3cuZ29vZ2xlY2xvdWRldmVudHMuY29tIiwiaWF0IjoxNzc1NDE1MDg2LCJuYmYiOjE3NzU0MTUwODYsImV4cCI6MTc3NTQxODY4NiwiY29udGV4dCI6eyJwYXlsb2FkIjp7ImlkIjoiIiwicmVnVHlwZU5hbWUiOiIiLCJldmVudF9pZCI6IjI2NDAwMSIsImNfMzI5MDQxNiI6IiJ9fX0.4DdpDpXJDvZM1PE9nZ-9YR96DFCmJnan-Ku-6laVELI
phase 5 session info modal
Day 1 – April 22, 2026
Breakouts
BRK1-068 • Architecture, Compute • Introductory
AI Hypercomputer: Resilient AI infrastructure at scale
location_on Mandalay Bay F
schedule 4:00 PM - 4:45 PM

Generative and agentic AI inference and training demand extreme performance and uptime. Join us to explore new updates to Google Cloud’s AI Hypercomputer, an integrated supercomputing system optimized to serve your models and agents with industry-leading throughput and latency. In this session, AppLovin will share their real-world experience architecting high-scale model serving on Google Cloud. We’ll also share new capabilities for resiliency and reliability. Leave with a blueprint for building an inference infrastructure that delivers speed without sacrificing stability.

 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