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 two hundred 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

Qiita (LLM)Japan

12GBのGPU2枚で27BのLLMを24人同時に使う ― Ternary-Bonsai-2-27B を vLLM で動かす手順(WSL2)

11.13

はじめに: こんなことができます 12GB の GPU 2枚(RTX 5070 × 2)を挿した Windows PC で、27B(270億パラメータ)の LLM を、社内の何人かで同時に使っています。できること数字(手元の実測) 1人で使ったときの生成...

Models & releases Open weights Chips & compute

Read at Qiita (LLM) ↗

One letter a week, starting soon.

Latest

12GBのGPU2枚で27BのLLMを24人同時に使う ― Ternary-Bonsai-2-27B を vLLM で動かす手順(WSL2)

Related

ToolsDay 0 support for Mistral Large 4 on vLLM vLLM Blog

ToolsDay 0 support for Muse Spark Open on vLLM vLLM Blog

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

GitHubEdge0-145B: Frontier AI Capabilities on Your Own Computer Hacker News (front)

ValleyJensen Huang’s exit puts Nvidia’s support for open source in question TechCrunch AI

OpenAI’s data suggests that frontier models are hiding their thoughts because developers optimize for capability and compute The Decoder