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

vLLM Support for NVIDIA Vera Rubin NVL72: 7.8x Throughput over GB200 NVL72

10.09

vLLM now runs on NVIDIA Vera Rubin NVL72 with day-0 model support, Rubin-tuned FlashInfer kernels, and locality-aware MoE, delivering 7.8x the per-GPU throughput of GB200 NVL72 on AgentX.

Open weights Chips & compute hardware performance

Read at vLLM Blog ↗

One letter a week, starting soon.

Latest

vLLM Support for NVIDIA Vera Rubin NVL72: 7.8x Throughput over GB200 NVL72

Related

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

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

VoicesSED News: The NVIDIA-Hugging Face Deal, China’s Proxy Economy, the Open Weight Surge Software Engineering Daily

ToolsNvidia reportedly agrees to purchase Hugging Face for $13B Weights & Biases

ToolsDeepSeek-V4.1-Flash on vLLM: 5x Agentic Throughput Since Day 0 vLLM Blog

ToolsTaking vLLM Apart: A Practical Guide to Disaggregated Serving vLLM Blog