JLKang/ViSpec-Qwen2.5-VL-3B-Instruct
Image-Text-to-Text
•
0.4B
•
Updated
•
27
ViSpec
-
-
JLKang/ViSpec-Qwen2.5-VL-7B-Instruct
Image-Text-to-Text • 0.9B • Updated • 23 -
JLKang/ViSpec-llava-v1.6-vicuna-7b-hf
Image-Text-to-Text • 0.5B • Updated • 12 -
JLKang/ViSpec-llava-v1.6-vicuna-13b-hf
Image-Text-to-Text • 0.7B • Updated • 6 -
JLKang/ViSpec-llava-1.5-7b-hf
Image-Text-to-Text • 0.5B • Updated • 4 -
ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding
Paper • 2509.15235 • Published • 1