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

Introducing vLLM TorchTPU

10.20

vllm-torchtpu is a new vLLM backend for Google Cloud TPUs built on TorchTPU, with Pallas kernels, multi-host parallelism, KV cache offloading, and disaggregated serving.

Open weights Chips & compute hardware

Read at vLLM Blog ↗

One letter a week, starting soon.

Latest

Introducing vLLM TorchTPU

Related

ToolsHyper Optimizing Kimi K3 in vLLM: Moving Fast and Responsibly vLLM Blog

ToolsDay 0 support for Muse Spark Open on vLLM vLLM Blog

ToolsAnnouncing Day 0 Support for NVIDIA Nemotron 3.5 Super VL on vLLM vLLM Blog

ToolsImprove TTFT for Multi-Turn Agentic Workloads with Bi-Directional KV Transfer in vLLM vLLM Blog

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

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