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

Modernizing Table Batched Embeddings with FBTriton

October 6

This post explores the FBTriton kernel design for Table Batched Embedding (TBE) forward and backward passes.

Read at PyTorch Blog ↗

One letter a week, in your inbox.

Latest

Modernizing Table Batched Embeddings with FBTriton

More from PyTorch Blog on Accept All

ToolsEvolution of the PyTorch Media Processing Landscape PyTorch Blog

ToolsPyTorch Hardware Enablement: Updates from the Accelerator Integration Working Group PyTorch Blog

ToolsBuilding a High-Performance and Portable vLLM Linear Backend with Helion PyTorch Blog

ToolsNew Pathway to PyTorch Certified Associate (PTCA) Certification PyTorch Blog

ToolsOptimizing Jagged Flash Attention with TLX: The Road Toward SOTA FA4 on Blackwell PyTorch Blog

ToolsA Ray-Focused Guide to PyTorch Conference North America PyTorch Blog