LLM inference is becoming a distributed systems problem. Explore the architecture patterns reshaping AI infrastructure ->

⁺✦ Momento for AI
Get in Touch
split illustration showing Mo struggling to carry a chaotic pile of uneven blocks on the left, contrasted with Mo calmly organizing blocks into neat, separate lanes on the right.
  • AI/ML

Disaggregated Inference, Part 1: When & Where to Route

Hien Luu Hien Luu
  • Caching, Valkey

Why Snap Was Willing to Fork, and Why They Still Came Back

Allen Helton

Unlocked Conference – Seattle

  • May 5, 2026
  • T-Mobile Park, Seattle, WA

Unlocked Conference – San Jose

  • May 5, 2026

AWS re:Invent 2025

  • Dec 12, 2025
  • Las Vegas, NV

QCon SF: Real-World Technical Talks

  • Nov 11, 2025
  • Hyatt Regency, SF

Building Efficient Systems: Protosockets to Global Tables

  • Oct 10, 2025

Oct 2025 Meetup—Atomic Slot Migration & Modern Hash Tables

  • Oct 10, 2025

Transactions and Coordination in Aurora DSQL

  • Aug 8, 2025

IBC 2025—Amsterdam

  • Sep 9, 2025
  • RAI Amsterdam

Portland Video Tech Meetup

  • May 5, 2025

June 2025 Meetup—Presentations on Valkey Optimizations and Memcached

  • Jun 6, 2025
  • SURF Incubator

NABShow

  • Apr 4, 2025
  • Las Vegas, NV

ACM Mile High Video

  • Feb 2, 2025