OpenGVLab
/

InternVL-Chat-V1-5-Int8

Image-Text-to-Text

feature-extraction

8-bit precision

Model card Files Files and versions Community

好像lmdeploy无法加速推理8bit版本？

#6

by yuezhiyu - opened 20 days ago

20 days ago

目前所有model format参数都已经测试过了，无法正常部署。4bit是可以用awq部署的

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment