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

b11448

October 6

cuda: BF16/FP16 conversion to f32 chunking ( #29442 ) ggml-cuda: chunk large BF16/FP16 to F32 conversions Update ggml/src/ggml-cuda/ggml-cuda.cu Co-authored-by: Johannes Gäßler [email protected]…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, in your inbox.

Latest

b11448

Related

Toolsb11447 llama.cpp releases

SiliconNVIDIA Releases GeForce 617.42 WHQL Game Ready Drivers TechPowerUp

SiliconAxelera AI: Data Center Inference Performance in the Power Envelope of Embedded Systems EE Times

ResearchSovereign AI, same landlord — thoughts on the physical AI race The Robot Report

SiliconGigabyte W775-V10-L01 Hands-on Bringing NVIDIA GB300 Deskside ServeTheHome

SiliconAICR v1.0: Open, stable, and verifiable GPU cluster configuration NVIDIA Technical Blog