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

Cline BlogTools

11,840 TPS on a single GPU

10.27

NVIDIA released Nemotron 3.5 Super VL on October 15, and we reached 11,840 aggregate output tokens/sec on one GB300 with 256 concurrent requests .

Chips & compute

Read at Cline Blog ↗

One letter a week, starting soon.

Latest

11,840 TPS on a single GPU

Related

ToolsCline Agents Harness Unlocks Benchmark-Leading Performance from NVIDIA Nemotron 3.5 Super VL Cline Blog

ToolsNVIDIA Nemotron 3.5 Lightning just landed in Cline Cline Blog

SiliconNVIDIA RTX Spark Powers Neural Rendering and AI Characters in Games NVIDIA Technical Blog

JapanOracle CloudがGoogle TPU導入を発表、2027年に提供を開始。Oracle AI World 2026 Publickey

SiliconFine-Tuning NVIDIA Nemotron to Know Local Rules, Not Just Local Languages NVIDIA Technical Blog

SiliconNVIDIA and Oracle Expand NVIDIA Vera Rubin to Multi-Gigawatt Scale and Bring NVIDIA Vera CPU to Oracle Cloud Infrastructure NVIDIA Newsroom