Codetown
Codetown ::: a software developer's community
My Friends (1)
Happy 10th year, JCertif!
Notes
Welcome to Codetown!
Codetown is a social network. It's got blogs, forums, groups, personal pages and more! You might think of Codetown as a funky camper van with lots of compartments for your stuff and a great multimedia system, too! Best of all, Codetown has room for all of your friends.
Created by Michael Levin Dec 18, 2008 at 6:56pm. Last updated by Michael Levin May 4, 2018.
Looking for Jobs or Staff?
Check out the Codetown Jobs group.
InfoQ Reading List
Article: Building an Offline-First AI Coding Tutor for Low-End Android Phones
This article is about engineering an offline-first app for low-end devices based on our experience in Nigeria and India. The interesting problems in this space are storage, quota, cold start, and failure-path design. Our approach applies to any product whose users are on constrained devices and intermittent connections, when the assumption they have a laptop and broadband access do not hold.
By Chidi NwaoguCloudflare Opens Quicksilver to Customers as Workers KV Instant, Inside a 1 MB Envelope
Cloudflare has put Quicksilver, the internal key-value store behind nearly every request it serves, into private beta as a Workers KV mode. Reads resolve in 1.62 ms at p99 against 287 ms for classic KV. The constraints decide the use case: 10,000 keys, one megabyte per namespace, and one write per namespace per second.
By Steef-Jan WiggersUber Moves beyond CPU Cores with Performance-Aware Scheduling for Stateful Workloads
Uber has introduced Normalized Compute Units (NCUs) to make CPU allocation more consistent across its highly heterogeneous server fleet.
By Craig RisiHow Anthropic Redesigned Source Control for AI-Driven Development
Anthropic recently detailed how it migrated its monorepo from Git to Scion. Scion is a source control system that moves repository operations to the server side and uses content-addressed storage and tiered caches for agent and CI workloads. The design sacrifices offline independence for less local data and shared infrastructure.
By Eran StillerPresentation: Serving LLMs at Scale: The Hidden KV Cache Advantage
Khawaja Shams shares a distributed systems perspective on scaling LLM inference stacks efficiently. He discusses practical strategies for optimizing GPU utilization, managing KV cache memory cliffs, leveraging tiered storage, reducing tail latency, and implementing disaggregated prefill and decode architectures to improve overall fleet performance, cost economics, and availability.
By Khawaja Shams
© 2026 Created by Michael Levin.
Powered by
