memory-efficient-optimizer

Here is 1 public repository matching this topic...

mcarbonell / smo-optimizer

SMO (State Memory Optimizer) is an ultra-memory-efficient PyTorch optimizer designed to solve the "Memory Wall" problem in Deep Learning. It reduces the optimizer state memory by 60-93% while retaining accuracy.

pytorch adam-optimizer neural-network-optimization adamw memory-efficient-optimizer optimizer-state-compression

Updated Aug 26, 2026
Python

Add this topic to your repo

To associate your repository with the memory-efficient-optimizer topic, visit your repo's landing page and select "manage topics."

Learn more