Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.
-
Updated
Dec 14, 2024 - Python
#
training-free-acceleration
Here are 2 public repositories matching this topic...
ICML2025: AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration
-
Updated
May 24, 2025 - Python
Improve this page
Add a description, image, and links to the training-free-acceleration topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the training-free-acceleration topic, visit your repo's landing page and select "manage topics."