Skip to content
GitHub Explorer

xTimeCrystal/Muon-RMS-Norm

View on GitHub ↗Related repositories →

This version of Muon converges slightly faster than the Muon from modded-nanogpt in some cases. The change is RMS-Norm after orthogonalization over the first dimension of the weight matrix (last dimension of nn.Linear). The code here assumes you store the weights like nn.Linear i.e. used like x = x @ W.T.

active 2025-06-08 → 2025-06-08 (UTC)

Partial coverage14,524 / 17,595 hourly files (83%) · 2 absent upstream · 3,071 failed, retryable2024-08-08 → 2026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
2
Pushes
1
Pull requests
0
Issues
0
Stars
0
Forks
1

Activity over time

Daily event counts in the loaded window

Line chart, 1 days from 2025-06-08 to 2025-06-08. Pushes: 1 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 0 total, peak 0 in a day. Comments: 0 total, peak 0 in a day. Stars: 0 total, peak 0 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
xTimeCrystal1100

Recent activity

Latest issues, pull requests and releases

No issue or PR events — this repo's activity is pushes only.

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.