Infrastructure Articles

Cloudflare

31 min read

AI•2026-04-16

Building the foundation for running extra-large language models

Cloudflare explains how they built infrastructure to run extra-large language models like Kimi K2.5 on Workers AI, optimizing for agentic use cases with long contexts and frequent tool calls.

Agents Week

Agents

Developer Platform

Developers

Infrastructure

Workers AI

Infrastructure Articles

Related Tags

How Google Does It: Fleet-wide, large-scale A/B experimentation

How Imgix processes 8 billion images daily with G4 VMs powered by NVIDIA Blackwell

Introducing Virgo Network, Google’s scale-out AI data center fabric

Startups are building the next big thing with Google Cloud AI

Cross-cloud infrastructure innovation for the agentic enterprise

How WPP accelerates humanoid robot training 10x with G4 VMs

Building the foundation for running extra-large language models

Let’s Talk Agentic Development: Spotify x Anthropic Live

Improving storage efficiency in Magic Pocket, our immutable blob store

Top Infrastructure and GKE Sessions at Cloud Next '26

A one-line Kubernetes fix that saved 600 hours a year

Reducing our monorepo size to improve developer velocity

Launching Cloudflare’s Gen 13 servers: trading cache for cores for 2x edge compute performance

Inside Gen 13: how we built our most powerful server yet

Shedding old code with ecdysis: graceful restarts for Rust services at Cloudflare

How Workers powers our internal maintenance scheduling pipeline

Background Coding Agents: Context Engineering (Honk, Part 2)

With Mobius Labs' Aana models, we're bringing deeper multimodal understanding to Dropbox Dash

Hack Week 2025: How these engineers liquid-cooled a GPU server