§ feed · storyline

Inside the Together AI kernels team

Together AI's kernels team, behind FlashAttention and ThunderKittens, works to close the gap between GPU hardware capabilities and production AI performance.

Apr 1 · 02:00:00 · primary fetch1 sourceupdated Apr 1 · 02:00:00

The team behind FlashAttention and ThunderKittens — how Together AI's kernel researchers close the gap between GPU hardware and production AI.

read full article on together.ai ↗

§ sources1 publication · timeline below

together.aiInside the Together AI kernels teamprimary02:00:00