inference workload
1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Nov 25, 2024 by Lin Qiao · across every show →
Everything said about inference workload, oldest first
Nov 25, 2024 neutral
Customer inference workloads rarely align with foundation model training distributions
“The data distribution in their inference workload doesn't align with the data distribution in the training data for the model, right? It's a given, actually. If you think about this, because researchers have to guesstimate what is important, what's not importa…”