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

PyTorch BlogTools

Accelerating PyTorch on AMD GPUs with FlyDSL

10.21

PyTorch users on AMD MI350-series GPUs can now use FlyDSL through existing operator APIs for dense and grouped GEMM, fused multi-head attention (FMHA/Attention), MXFP8/MXFP4 scaled GEMM, RMSNorm, and…

Chips & compute

Read at PyTorch Blog ↗

One letter a week, starting soon.

Latest

Accelerating PyTorch on AMD GPUs with FlyDSL

Related

ToolsIntroducing TorchTPU PyTorch Blog

ToolsFrom KTIR to SpyreCode: An MLIR Dataflow Backend for IBM Spyre PyTorch Blog

ToolsOne Search, Two Layers: Compiler Controls Inside PyTorch Helion using NVIDIA CompileIQ PyTorch Blog

LabsHow Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77% in Real Applications Hugging Face Blog

SiliconNVIDIA Releases GeForce 621.01 WHQL Game Ready Drivers TechPowerUp

SiliconNVIDIA GTC Berlin 2026 NVIDIA Intros DSX PODs and More ServeTheHome