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

Serving Reflection Beam on vLLM from Day 0

10.16

vLLM supports Reflection's Beam-1.0 (501B total, 23B active) from day 0, with agent-driven optimization that cut decode latency 2.71× and DFlash2 speculative decoding with adaptive verification.

Models & releases Open weights reflection performance kernels speculative-decoding

Read at vLLM Blog ↗

One letter a week, starting soon.

Latest

Serving Reflection Beam on vLLM from Day 0

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

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

LabsWelcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta Hugging Face Blog

LabsRun fast, private agents on-device with LFM2.5-24B-A2B Hugging Face Blog

EuropeMistral raises €3B to make sovereign, open-weight AI the technology frontier Mistral AI