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

b11989: HIP/CUDA: enable sparse attn on CDNA (#31259)

10.29

HIP/CUDA: enable sparse attn on CDNA Use __ballot for __ballot_sync on old ROCm versions Ignore new large head fattn mma variant

Chips & compute

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11989: HIP/CUDA: enable sparse attn on CDNA (#31259)

Related

AsiaKorean chipmaker FuriosaAI raises $620m at $2.9b valuation Tech in Asia

SiliconRethinking Shift Left In Chip Design SemiEngineering

SiliconThe EU Cyber Resilience Act Reaches Chip And IP Suppliers SemiEngineering

AsiaGoogle supplier Biwin, GPU leader Moore Threads see stocks plunge despite revenue surge SCMP Tech

AsiaLi Auto launches updated i6 SUV with in-house driving chip and larger battery TechNode

AsiaNo equity, no fee: Nvidia’s long bet on SEA’s AI startups Tech in Asia