Files
hao-ai-lab-FastVideo/fastvideo
SolitaryThinker 345d2acb19 [fix]: init PackedExpertLinear params with zeros, not empty (review)
Addresses review thread on fastvideo/models/dits/magi_human.py:263. torch.empty leaves memory uninitialized; if a future caller skips load_state_dict or strict=False loses entries silently, the network would output NaNs. zero-init costs nothing at runtime (overwritten by load) and matches sibling MultiModalityRMSNorm which also uses torch.zeros.
2026-05-12 14:09:55 -07:00
..
2026-01-05 15:47:05 -06:00