AI Infrastructure SoftwareTanishq Kumar et al. (Harvard)
Tanishq Kumar et al. publish "Scaling Laws for Precision"
"Scaling Laws for Precision" published — proposed precision-aware scaling laws in which low-precision training reduces a model's effective parameter count. The more training data, the greater the degradation from post-training quantization
Why it matters
A study that tested, at the level of scaling laws, whether FP8/FP4 works. Redefined precision not as a free optimization but as a trade against capacity
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2411.04330Added in Week 35, 2026 · See that week