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 two hundred 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

InfoQ AIGitHub

Google Open-Sources TPU Sync for KV Cache and Weight Transfer on TPUs

11.12

Google Cloud has open-sourced TPU Sync, a native C++ library that moves KV cache blocks and model weights between TPU HBM, host DRAM, shared storage, and the data center network. By Daniel…

Open weights Chips & compute Python Artificial Intelligence Google Cloud Hardware

Read at InfoQ AI ↗

One letter a week, starting soon.

Latest

Google Open-Sources TPU Sync for KV Cache and Weight Transfer on TPUs

Related

SiliconNVIDIA Expands Open Source Commitment With OpenShell Contribution and New AI Infrastructure NVIDIA Blog

SiliconHow NVIDIA Open Source Tools Are Helping Researchers Build Next-Generation 6G Networks NVIDIA Blog

ToolsDay 0 support for Mistral Large 4 on vLLM vLLM Blog

ToolsvLLM Delivers Day-0 Support for MiniMax-M3.1-Flash vLLM Blog

LabsHugging Face ❤️ TorchTPU: TPUs, Natively Hugging Face Blog

ToolsIntroducing vLLM TorchTPU vLLM Blog