Skip to content

Source paper

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Jintao Zhang, Kaiwen Zheng, Kai Jiang and 5 more

Jintao Zhang, Kaiwen Zheng, Kai Jiang, Haoxu Wang, Ion Stoica, Joseph E. Gonzalez, Jianfei Chen, Jun Zhu

arXiv 2512.16093 · 202558 upvotes on Hugging Face

Research ideas from this paper (3)

Generated by AI. The paper’s authors did not write these.

AI summary

The paper introduces TurboDiffusion, a framework designed to accelerate Wan video diffusion models by 100-200x on NVIDIA RTX 5090 GPUs. It achieves this by combining four optimizations: low-bit attention (SageAttention), sparse-linear attention (SLA), step distillation via regularized Consistency Models (rCM), and W8A8 quantization of linear layers.

How it works (AI summary)

The authors integrate a specialized sparse attention mechanism (SLA) with integer quantization (INT8 weights and activations) and algorithmic distillation (reducing sampling steps from ~100 to 3-4). They utilize custom CUDA kernels (SageAttention) and Triton implementations to maximize hardware efficiency on the Blackwell architecture.