Files
hao-ai-lab-FastVideo/fastvideo/train/methods
SolitaryThinker 5a8329ddf6 [bugfix]: set causal-CD timesteps before the teacher CFG forwards
training_batch.timesteps was assigned t_pf only after the two teacher
CFG passes, so their set_forward_context(current_timestep=...) carried
the stale random timesteps from prepare_batch — wrong VSA sparsity
gating when attn_kind == "vsa". Assign before any forward.
2026-07-05 15:00:47 -07:00
..
2026-07-05 14:56:08 -07:00
2026-07-05 14:56:08 -07:00