4 papers
Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models
Jindi Lv, Aoyu Li, Yuhao Zhou +6
Mamba demonstrates strong efficiency in modeling long visual sequences. However, when token reduction is applied to structurally enhanced Mamba variants, these models exhibit a sev…
PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference
Jiarui Fang, Jinzhe Pan, Aoyu Li +2
This paper presents PipeFusion, an innovative parallel methodology to tackle the high latency issues associated with generating high-resolution images using diffusion transformers…
Unveiling Redundancy in Diffusion Transformers (DiTs): A Systematic Study
Xibo Sun, Jiarui Fang, Aoyu Li +1
The increased model capacity of Diffusion Transformers (DiTs) and the demand for generating higher resolutions of images and videos have led to a significant rise in inference late…
xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
Jiarui Fang, Jinzhe Pan, Xibo Sun +2
Diffusion models are pivotal for generating high-quality images and videos. Inspired by the success of OpenAI's Sora, the backbone of diffusion models is evolving from U-Net to Tra…