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

vLLM BlogTools

Reducing vLLM startup time with one uv flag

09.22

Shipping Python bytecode saved about 18 seconds per startup in H100 server benchmarks, with images and models already local.

Open weights performance deployment

Read at vLLM Blog ↗

One letter a week, starting soon.

Latest

Reducing vLLM startup time with one uv flag

Related

ToolsAnnouncing vllm-metal: Concurrent Serving on Apple Silicon vLLM Blog

GitHubReconnecting with the heart of open source: Highlights from our 2026 GSoC India tour Google Open Source Blog

ToolsMigrating from closed to open source models, Together Together AI

SiliconA Brain Too Big to Carry — On-Device vs Datacenter Inference SemiAnalysis

ToolsCline Desktop: An open-source app for open-weight models Cline Blog

VoicesOpen-Source AI & Open Models Reading List Interconnects