Ever

any one can help? Even the latest version(1.2.0) also exists this issue.

> this bug is can be reproduced How? I have the same issue. But I don't know how to reproduce it.

同问

> We will upgrade the models later after we release the v1.0.0 When will the v1.0.0 be released?

I need this feature, too. How's the cr going?

> 我无法探明OOM问题出现的原因，只能给后面遇到相似问题的人一个参考。 解决办法： 回退xinference版本，重新创建一个conda虚拟环境，然后安装：pip install "xinference[all]==0.12.0" 然后就能运行glm4v模型了   感谢，我也遇到同样问题，折腾了半天，最后用大佬这种方法才算解决。