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

llama.cpp releasesTools

b11530

October 9

llama: keep the backend sampling graph static across ubatches ( #30223 ) The reserve builds n_outputs_max_per_seq sampling chains per sampler, while a decode built one per output row, so the graph…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11530

Related

SiliconNVIDIA Throws RTX Spark Launch Party in Berlin on October 16. You Can Be There, it's Public TechPowerUp

LabsImpactful scheduling for GPU clusters Hugging Face Blog

GitHubAmazon ECS now auto-repairs failing GPUs and instances. Here’s why it matters for SREs. The New Stack

SiliconPC shipments tumble over 20% in 3Q26 as chip shortages bite Tom's Hardware

SiliconBoro: NVIDIA's Open-Source Effort For AI-Assisted Linux Kernel Development Phoronix

EuropeNvidia defends open source AI alliance, saying hundreds and hundreds of companies being vetted Tech.eu