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

b11293

September 30

ggml : add BF16 unary, GLU, binary and scale ops (CPU, CUDA) ( #29675 ) ggml : add BF16 unary, GLU, binary and scale ops (CPU, CUDA) ggml-cpu : use per-op _bf16 functions for BF16 unary and GLU ops…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, in your inbox.

Latest

b11293

Related

Toolsb11282 llama.cpp releases

SiliconAMD iGPUs To Get Promising Performance Boost on Linux via PerfOpt Patch TechPowerUp

Meta dodges billions in US taxes by calling its AI data centers experiments The Decoder

Silicon(PR) Panasonic Connect Launches the TOUGHBOOK 34 and TOUGHBOOK G3, Fully Rugged 2-in-1 Mobile Computers TechPowerUp

SiliconNVIDIA Opens Applications for 2027–2028 Graduate Fellowships With Awards Up to $60,000 NVIDIA Blog

SiliconIntel Media Driver Gets "Crescent Island" Xe3P GPU Support TechPowerUp