cd/entity/Muon Optimizer· home› entities› Muon Optimizer
grep -l @muon optimizer /news/*.json | wc -l → 1

@Muon Optimizer

mentions 1 type Person feed RSS
15:05
2026-06-03
pytorch.org
machine-learning

Using Muon Optimizer with DeepSpeed

DeepSpeed has integrated the Muon Optimizer, a memory-efficient optimizer that uses a single momentum buffer and Newton-Schulz orthogonalization to improve training convergence, particularly for 2D we…

// co-occurs with top 6 entities
DeepSpeed 1 Moonshot AI 1 Kimi-K2-Thinking 1 AdamW 1 NanoGPT 1 GPT-2 1