technical.cx

Lobsters · May 11, 2026 11:09

GitHub - jundot/omlx: LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar - jundot/omlx

InfoQ Development · May 11, 2026 11:00

From Java EE to Quarkus and LLMs: Adam Bien’s Playbook for Boring, Future‑Proof Systems

Adam Bien, a pioneer of zero dependencies in the enterprise world of Java, highlights the benefits of consistently using standards, regardless of whether they involve Java or existing patterns.

InfoQ Development · May 11, 2026 11:00

Local-First AI Inference: A Cloud Architecture Pattern for Cost-Effective Document Processing

A three-tier hybrid architecture routes 70–80% of documents to local deterministic extraction, cutting Azure OpenAI costs by 75% and processing time by 55% on a 4,700-document workload.

OpenAI

Lobsters · May 11, 2026 10:57

Programmable Whitelist-based Configs: Embedding Rye in Go

We will look at how to embed the Rye language into a Go app and why its capability model may make it especially suitable for configuration even if it's a general purpose language.

Lobsters · May 11, 2026 10:10

Ratty — A GPU-rendered terminal emulator with inline 3D graphics 🐀🧀

Ratty is a GPU-rendered terminal emulator with inline 3D graphics.

Lobsters · May 11, 2026 09:09

Local AI Needs to be the Norm

Local AI models should be the default.