The name is the button.

An agent writes the code now, and a human thumb hovers over Accept all a hundred times a day. The honest question of this decade is what, exactly, you just accepted. So I read the diff.

Eight years as a backend engineer in Stockholm, back in Tokyo since 2023, and I still ship something small most nights, usually badly. My one rule: the only real review of a model is the thing you built with it. That is why there is no leaderboard on this site.

Around a hundred and forty sources come through — the labs' own posts, the papers, the tools, the runtimes and languages nobody is watching yet, the chip under the demo, and the newsletters people actually forward. What is moving gets counted so the week reads at a glance, and every few days I explain one mechanism in plain words.

A story here is a headline, a short excerpt, one image and the link to whoever wrote it. We never reproduce the post; the images belong to their authors. A post written in Japanese appears in Japanese, exactly as it was published, and the link goes to the original.

— Yuki Halvorsen, Tokyo

← Accept All Archive

IBM ResearchResearch

llm-d 1.0 hardens open-source AI inference for production

10.20

The distributed inference framework makes serving large models on your own infrastructure reliable and affordable for the agentic era.

Open weights AI AI for Code Distributed Inference Generative AI

Read at IBM Research ↗

One letter a week, starting soon.

Latest

llm-d 1.0 hardens open-source AI inference for production

Related

LabsHugging Face ❤️ TorchTPU: TPUs, Natively Hugging Face Blog

LabsAnyLanguageModel 1.0: One Year of Local Models on Apple Platforms Hugging Face Blog

ToolsIntroducing vLLM TorchTPU vLLM Blog

ToolsNode.js creator ditches Deno to work on open source Cloudflare Workers DevClass

Open source and on device: the strategy behind Nvidia’s new AI models AI Business

Western open-weight models still can’t beat China Rest of World