
Episode 33: Tri Dao, Stanford: On FlashAttention and sparsity, quantization, and efficient inference
Generally Intelligent
The Importance of Larger Models in Research
As a researcher, sometimes you have to take these contrarian bets. You try it out and see if they're promising results. If so, you keep going. As long as you still show something that's interesting, I think that's the goal of being an academic. Lots of folks are trying to figure out different ways to do interesting things.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.