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

llama.cpp releasesTools

b12070: cuda : prevent premature eviction of graphs about to be used (#30662)

11.03

cuda : prevent premature eviction of graphs about to be used add last_graph_use_time for entire cuda graph map and testcase for cuda graph Assisted-by: Codex delete the…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b12070: cuda : prevent premature eviction of graphs about to be used (#30662)

Related

AsiaVisual brain-computer interface developer Nanochap raises RMB 500 million TechNode

AsiaAI inference chipmaker Moffett AI raises nearly RMB 1 billion in Series C+ funding TechNode

AsiaUS data center firm Vertiv opens Singapore AI hub Tech in Asia

AsiaTencent Hunyuan's Hyra 2.0 Research Agent Builds Its Own Tools for Proteins, Proofs and Chips Pandaily

AsiaMoore Threads' 2,112-GPU Wuxi Cluster Reaches 92.9% Utilization After Going Commercial Pandaily

SiliconDiagnose Distributed AI Workload Failures with NVIDIA Attribution NVIDIA Technical Blog