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

Day 0 support for Mistral Large 4 on vLLM

10.29

Day-0 vLLM support for Mistral Large 4 with sparse MLA, cross-layer KV sharing, DSpark speculative decoding, DCP/PCP long context and NIXL P/D on NVIDIA Blackwell.

Models & releases Open weights Chips & compute model-support speculative-decoding disaggregated-serving

Read at vLLM Blog ↗

One letter a week, starting soon.

Latest

Day 0 support for Mistral Large 4 on vLLM

Related

ToolsDay 0 support for Muse Spark Open on vLLM vLLM Blog

ToolsMAGI-2 Preview on vLLM-Omni: Bringing a 114B Audio-Video MoE DiT to Moore Threads MUSA with torchada vLLM Blog

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

ToolsServing DeepSeek-V4.1-Flash at Scale: vLLM Matches DeepInfer and Scales to GB300 NVL72 vLLM Blog

ToolsvLLM Delivers Day-0 Support for MiniMax-M3.1-Flash vLLM Blog

ToolsDay-0 Support for Flint on vLLM vLLM Blog