Preprint
Aug 2026
TurboT2VA: Fast Large-Scale Text-to-Video-Audio Generation via Score-Regularized Consistency Distillation
An architecture-aware inference stack that combines guarded W8A8 and fused operators, padded-text compaction, and modality-aware sparse attention while preserving dense cross-modal and text-conditioning paths is developed.
Xiao-Da Yang, Yu-Xian Liu, Kaiwen Zheng et al.
· 0 citations