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

b11403

October 5

CUDA: use MMVF for thin f16/bf16 mul_mat at small batch size ( #29633 ) CUDA: use MMVF for thin f16/bf16 mul_mat at small batch size Signed-off-by: ynankani [email protected] adjust kernel…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, in your inbox.

Latest

b11403

Related

Toolsb11399 llama.cpp releases

LabsAccelerating Spatio-Temporal Attention for Video Diffusion on TPUs Google Developers Blog

LabsReproducing Olmo 3 7B Pre-training in MaxText: case study of large scale training on TPUs Google Developers Blog

LabsColab is now part of your Google AI plan Google Developers Blog

LabsAutonomous LLM post-training with Tunix on TPUs Google Developers Blog

LabsEnterprise-Grade Precision for Long-Context Multimodal Embedding Inference on Cloud TPU Google Developers Blog