hanxiaomeow commited on
Commit
79031cb
·
verified ·
1 Parent(s): 934e935

Trim org card

Browse files
Files changed (1) hide show
  1. README.md +0 -40
README.md CHANGED
@@ -20,43 +20,3 @@ pinned: false
20
  </div>
21
 
22
  **Veda** is a learned sparse-attention method for video DiTs. A lightweight tile-score predictor, distilled from full attention, keeps only the attention tiles that matter and skips the rest with a hardware-aligned tile-sparse kernel.
23
-
24
- - 🎯 **90% sparsity at perceptual parity** with full attention (WaverBench1.0 human side-by-side).
25
- - 🚀 **95% sparse 720P generation: 19.4 min → 3.8 min** — **5.1× end-to-end** and **10.5× self-attention** acceleration vs. FlashAttention-3 (Waver-T2V-12B, 720P, 241 frames).
26
- - 📈 **Near-linear scaling**: at 245K tokens, per-layer latency drops from 1576 ms to 309 ms.
27
- - 🔌 **Plug-and-play**: Veda only changes how attention is computed. Backbone weights and style stay untouched, so it works with LoRAs and fine-tuned variants.
28
-
29
- <table>
30
- <tr>
31
- <td align="center"><img src="https://veda-sparse.github.io/static/posters/race/race_full.webp" width="100%"/><br/><sub>FlashAttention-3 · full attention · 19.4 min</sub></td>
32
- <td align="center"><img src="https://veda-sparse.github.io/static/posters/race/race_veda.webp" width="100%"/><br/><sub><b>Veda</b> · 95% sparsity · 3.8 min</sub></td>
33
- </tr>
34
- </table>
35
-
36
- ## How it works
37
-
38
- 1. **Full-attention structure distillation.** Max-pooled full attention serves as a tile-level teacher; a KL objective aligns the predictor with the dense attention geometry before Top-k selection.
39
- 2. **Head-conditioned tile geometry.** Per-layer, per-head tile shapes (p<sub>t</sub>, p<sub>h</sub>, p<sub>w</sub>) adapt to heterogeneous spatial and temporal heads under a fixed hardware budget.
40
- 3. **Tile-sparse kernel.** A ThunderKittens kernel fetches only the selected K/V tiles via TMA and overlaps sparse gathers with WGMMA compute, turning sparsity into wall-clock speedup.
41
-
42
- ## Releases
43
-
44
- | | Description |
45
- |---|---|
46
- | 🤗 [Minimax-H3-T2VA-Veda-8NFE-600Step-Preview](https://huggingface.co/Veda-Sparse/Minimax-H3-T2VA-Veda-8NFE-600Step-Preview) | Veda predictor for MiniMax-H3 text-to-audio-video generation (8-step, with Turbo LoRA) |
47
- | 💻 [Miowtion](https://github.com/veda-sparse/Miowtion) | Sparse acceleration and LoRA fine-tuning of MiniMax-H3 on resource-constrained machines |
48
- | 💻 [Veda-on-ComfyUI](https://github.com/veda-sparse/Veda-on-ComfyUI) | ComfyUI integration |
49
- | 💻 [vllm-omni](https://github.com/veda-sparse/vllm-omni) | Efficient inference for omni-modality models |
50
-
51
- ## Citation
52
-
53
- ```bibtex
54
- @inproceedings{han2026veda,
55
- title = {Veda: Scalable Video Diffusion via Distilled Sparse Attention},
56
- author = {Han, Shihao and Yang, Hao and Mei, Xiaofeng and Hu, Xinting and Jiang, Yi and Qi, Xiaojuan},
57
- booktitle = {International Conference on Machine Learning (ICML)},
58
- year = {2026}
59
- }
60
- ```
61
-
62
- <sub>ByteDance · The University of Hong Kong · USTC</sub>
 
20
  </div>
21
 
22
  **Veda** is a learned sparse-attention method for video DiTs. A lightweight tile-score predictor, distilled from full attention, keeps only the attention tiles that matter and skips the rest with a hardware-aligned tile-sparse kernel.