Triton, every mention
3 scenes · ← back to Triton
tap a year for its mentions
Verbatim, from the transcripts: the passages where Triton comes up
Multi-GPU Kernels, Intelligence per Watt, Heterogeneous Inference, and More | YC Paper Club · Y Combinator
- ▶ 33:03 unnamed speaker Ultimately, these dispatch down to individual CUDA kernels that may or may not be very fast on modern hardware, which is why we get programming languages like Triton, which are a tile-based. 3 times in the scene
- ▶ 34:44 unnamed speaker And at least, like, for this archetype of people that just want state-of-the-art perf, as far as I can tell, like, they really prefer, like, CUDA, and it was only when we were doing lots of gem-related problems that people loved using…
- ▶ 45:27 unnamed speaker So faster jets, like, more efficient, like, AOT packaging of things like Trident and QDSL are things I'm very interested in.