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

b11282

September 30

musa : define CUDA_ARCH for device passes ( #29508 ) The MUSA vendor header never defined CUDA_ARCH , so every architecture test in the shared ggml-cuda sources evaluated to 0.

Chips & compute Research

Read at llama.cpp releases ↗

One letter a week, in your inbox.

Latest

b11282

Related

SiliconQualcomm’s System Level Architecture in the Snapdragon X2 Elite Chips and Cheese

SiliconAI Data Centers Make Power, Cooling Critical to Scaling EE Times

SiliconNVIDIA Vera SMT Performance Benchmarks Phoronix

SiliconEfficient MoE Training for Biological Foundation Models NVIDIA Technical Blog

SiliconScaling Federated Learning Across Docker, Kubernetes, and Slurm with NVIDIA FLARE NVIDIA Technical Blog

VoicesMoving Beyond RAG with Precomputed Context Software Engineering Daily