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

b11786

10.21

ggml-cpu : compute f32 gelu_quick and geglu_quick without the fp16 table ( #30737 ) ggml-cpu : compute f32 gelu_quick and geglu_quick without the fp16 table ggml-cpu : keep the GGML_GELU_QUICK_FP16…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11786

Related

Toolsb11784 llama.cpp releases

AsiaDeepSeek open-sources inference framework with support for Nvidia and Huawei chips TechNode

Japan日立がGPU冷却用コールドプレート開発、独自のU字構造で消費電力を約30％削減 ITmedia AI+

SiliconEdge AI MCU Features Multimodal Compute, Tiered Memory EE Times

GitHubAnnouncing the GPU notification group and Linker Working Area Lobsters

SiliconScaling Data Movement For Physical AI SemiEngineering