Composer, every mention
2 scenes (said by Stuart (Stu)) · ← back to Composer
tap a year for its mentions
every year anyone Stuart (Stu) 2Garry Tan 1Francois Chaubard 1
Verbatim, from the transcripts: the passages where Composer comes up
Multi-GPU Kernels, Intelligence per Watt, Heterogeneous Inference, and More | YC Paper Club · Y Combinator
- ▶ 7:21 Stuart (Stu) I'm also a researcher at Cursor where I train composer, and today I'm here to talk about parallel kittens, which is our work on making multi-GPU AI kernels simple and fast.
- ▶ 20:57 Stuart (Stu) For example, Cursor is using it to train Composer on tens of thousands of Blackwell GPUs.