Oct 19, 2026
Muon Optimizer: From wx+b to Matrix Updates
From scalar wx+b through housing GEMM, AdamW and Muon, a nonlinear FFN, and a measured scaling spectrum.
Read post →Tagged With
2 posts connected to this tag.
Oct 19, 2026
From scalar wx+b through housing GEMM, AdamW and Muon, a nonlinear FFN, and a measured scaling spectrum.
Read post →
Jun 28, 2026
Muon vs AdamW explained from update mathematics to optimizer state, PyTorch's BF16 Newton-Schulz implementation, matrix-aware training kernels, memory cost, and a proposed C-Kernel-Engine pa...
Read post →I write about the maths, the kernels, and what happens when I try to make them work. Join me for the investigations, including the bits that go wrong.
Get the illustrated field guide by email, followed by engineering notes as I write them.