FasterVLM
Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.
inference-efficiencytraining-free-accelerationvision-language-modelvisual-token-pruning
Github Data
Star 80
Fork 4
Subscriber 2
Language Python
Size 30.0K
owner
created at 2024-11-27
updated at 2025-06-29
pushed at 2025-06-29
