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

b11405

October 5

cuda: tile the lightning indexer over keys and tokens for 4 heads ( #29901 ) cuda: tile the lightning indexer over keys and tokens for 4 heads With too few heads for a wmma tile, a block scores 64…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, in your inbox.

Latest

b11405

Related

Toolsb11403 llama.cpp releases

SiliconExtreme Environments Push Chips To Their Breaking Point SemiEngineering

Silicon(PR) INNO3D Announces 6U RTX PRO 6000BSE GPU Server TechPowerUp

AsiaCloud Gaming Firm haimacloud Launches GEAR Hybrid Handheld With Snapdragon 865 and Cloud RTX GPUs Pandaily

JapanRTX 4090で125B超大型LLMを高速駆動するStrata解説 Zenn (AI)

SiliconTITAN Xp Finally Runs on Windows XP Thanks to a Modded NVIDIA Driver TechPowerUp