training
2 statements across 2 episodes · 1 bullish · 0 bearish · 2 people on the record · first statement Nov 25, 2024 by Lin Qiao · across every show →
Everything said about training, oldest first
Nov 25, 2024 bullish
AI inference matters more than training because it scales with global population
“Our prediction is for those kind of applications, the inference is much more important than training. Because inference scale is proportional to the upliminal world population. And training. Training scale is proportional to the number of researchers.”
Aug 3, 2026
Optimal inference parallelism cannot be mathematically calculated; it must be auto-tuned
“And with training, it's more of like a math, like you can run the math and see the flops and maximize it. With inference, it's more of like an auto-tuning, like GPU kernel auto-tuning... You shadow the same traffic, like real traffic, and you just see which co…”