Update index.md

Author: jzhang38

content/blogs/fastvideo_post_training/index.md

@@ -49,7 +49,9 @@ Below, we demonstrate how each module accelerates the DiT denoising time (withou
 |         FA2 + DMD         |      4.67s      |        52s        |       2.88s       |  
 |          FA3+DMD          |      3.65s      |       37.87s      |       2.14s       | 
 | FA3 + DMD + torch compile |      2.64s      |       29.5s       |       1.49s       | 
-| VSA + DMD + torch compile |                 |        13s       |       0.98s       |  
+| VSA + DMD + torch compile |      --           |        13s       |       0.98s       | 
+
+
 All numbers can be reproduced with this [script](https://github.com/hao-ai-lab/FastVideo/blob/main/scripts/inference/v1_inference_wan_VSA_DMD.sh)
 
 ### Online Demo using FastVideo