SparseVLMs
Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference" proposed by Peking University and UC Berkeley.
efficiencysparsevlmsparsificationvision-language-model
Github Data
Star 55
Fork 3
Subscriber 2
Language Python
Size 5.4K
owner
created at 2024-10-04
updated at 2024-11-19
pushed at 2024-10-22
