Kernels
optimizer / test /run_test_per_head.sh
ca1207's picture
Claude Fable 5
feat: add Per-Head Muon (Kimi K3 §2.5) via head_keys [skip-build]
ebeb3a1
Raw History Blame Contribute Delete
83 Bytes
torchrun --nproc-per-node=8 --local-ranks-filter=0 -m pytest test_muon_per_head.py