NVIDIA study says SOAP and Muon beat AdamW on multi-billion-parameter LLM pretraining

sudoraohacker · x · 2026-07-24

NVIDIA researchers present SOAP, Muon, and beyond: a study on scaling LLM pretraining optimizers.

Related event: NVIDIA Paper Shows SOAP and Muon Optimizers Outperform AdamW in LLM Pretraining(3 posts)→

Original post →

More from Infra

Infra channel →