Sink-Sparse Hybrid Attention for Efficient Inference in T2I/T2V Diffusion Transformers
推理加速方法，无开源权重，暂不可用
Diffusion Transformers (DiTs) have become a common backbone for high-quality text-to-image and text-to-video generation, but repeated dense self-attention remains a major inference bottleneck as token sequences grow and the same operator is invoked across many denoising steps. Ou
判断口径 agnes-3.0-flash · 入库 #87 · 回首页