NVIDIA paper explores SOAP, Muon and other ways to scale LLM pretraining
A_K_Nain · x · 2026-07-24
SOAP, Muon, and other optimizers for scaling LLM pretraining
A new NVIDIA paper titled “SOAP, Muon, and Beyond: Pushing LLM Pretraining Scales” focuses on how to push large-language-model pretraining to larger scales. The post points to the paper and the image shows the author list and NVIDIA affiliation.
This is research-oriented content rather than a product announcement: the key signal is the paper itself and its optimization/scaling theme.
More from Infra
- RTK Terminal Compression Cuts Tokens but Leaves Your AI Coding Bill Unchanged — Bartaseth · 2026-09-11
- SF Compute founder: buying compute is 'an absolutely awful experience' right now — IgorCarron · 2026-09-11
- SmolVM open-sources persistent computer infrastructure for agents that outlive chat sessions — aniketmaurya · 2026-09-11
- PyTorch Day Korea 2026 launches first offline conf, CFP closes Sept 13 — PyTorch · 2026-09-11
- Local LLM server dilemma: 4x CMP-170HX (price up 53% in 20 days) vs Mac Studio M5 Ultra — rumboll · 2026-09-11
- llama.cpp lands Flash Attention tuning for RDNA4, big prefill gains on AMD — pmttyji · 2026-09-11