auto-tuning
1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Aug 3, 2026 by Ali Taha · across every show →
Everything said about auto-tuning, oldest first
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…”