@h100envy: Dan Fu co-wrote FlashAttention with Tri Dao. Then he co-built Hyena, Monarch Mixer, and ThunderKittens. Now he's distin…

X AI KOLs Timeline News

Summary

Profiles Dan Fu, a key contributor to high-performance kernels like FlashAttention, Hyena, Monarch Mixer, and ThunderKittens, now a distinguished researcher at Together AI whose work is used in ChatGPT, Claude, and Gemini.

Dan Fu co-wrote FlashAttention with Tri Dao. Then he co-built Hyena, Monarch Mixer, and ThunderKittens. Now he's distinguished researcher at Together AI. Four kernels you can find inside the inference stack running ChatGPT, Claude, and Gemini. One person, all in your hot path. His obsession: squeeze more tokens per second out of the same GPU. ThunderKittens is a 100-line CUDA DSL that beats hand-written kernels. Everyone is renting more GPUs. He keeps making the ones you have count for more.
Original Article
View Cached Full Text

Cached at: 06/28/26, 06:13 PM

Dan Fu co-wrote FlashAttention with Tri Dao. Then he co-built Hyena, Monarch Mixer, and ThunderKittens. Now he’s distinguished researcher at Together AI.

Four kernels you can find inside the inference stack running ChatGPT, Claude, and Gemini. One person, all in your hot path.

His obsession: squeeze more tokens per second out of the same GPU. ThunderKittens is a 100-line CUDA DSL that beats hand-written kernels.

Everyone is renting more GPUs. He keeps making the ones you have count for more.

Similar Articles