2026
RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models
ICML 2026poster
Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs. While prior work has reduced this cost via quantization and distillation, semi-structured sparsity—which can nearly halve FLOPs—remains underexplored. A key reason is that most existing…