pkunlp-icler/FastV
[ECCV 2024 Oral] Code for paper: An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
Python
Stargazers
- 110awesome
- apolloluo
- Blankit
- cem2ran@lenus-ehealth
- chenllliangPeking University
- ChukowskiAki'ta Labs
- Cristhine
- Dongwoo-ImSungkyunkwan Univ.
- felixfuu
- GutianpeiByteDance
- guxm2021National University of Singapore
- HaozheZhao
- hhaAndroidnuaa
- JizhongpengShanghai
- jramapuram
- kylezhangwei
- ldmiao
- linzhenyuyuchen
- mdiephuisGeneve, La Suisse
- Njasa2k
- okotakuOrange
- planb788
- rese1fUniversity of Washington
- seshurajup@dolcera
- sjpollardUniversity of Bristol
- StarCycle@EDiRobotics
- sugatorayTruist
- taesiriPlanet Mars
- tekakutlilatent space
- TGLTommy
- ustcfd
- Wangpeiyi9979Peking University
- wavinflaghxmUniversity of Chinese Academy of Sciences
- winglianAnnapolis, MD
- YunzeManChampaign, Illinois
- zhxiemlSJTU