goodmaney

Well, I soved it with removing the DIR /tmp/triton_cache And the TORCH INDUCTOR CACHE DIR like "/tmp/torchinductor_username/", then restart the terminal. And I dont know why, dont konw which step...

Same problem . it's seem like the latest Lightrage's bug

same problem here. wsl2 Ubuntu 22.4. with Xinference's environment GPU:2*4090 Model:qwen2.5 32B AWQ int4 When I start 6 concurrency error occurre . But didnt occurre when useing 1 GPU run...

> 让模型输出空字符串很不合理，可以让模型输出Yes或者No. > > 如果仍然出现问题，可以把对应的prompt发出来看看 谢谢，解决了。我在qwen2和2.5上没遇到过所以没考虑到这个问题

> Could you share a full input? > >  I made a script to process about 100 text files ,The text all looks like this ``` Don't Miss Out!...

same. I use the py script app.py .Maybe it's about the int and str variable. Error embedding chunk {'OpenAIEmbedding': "Error code: 422 - {'detail': [{'type': 'string_type', 'loc': ['body', 'input', 0],...

> > > > > The same. It seems like the base64 and strings problem. The picture was the LMStudio.  > > > > > > > > >...

> > The same. It seems like the base64 and strings problem. The picture was the LMStudio.  > > It seems that it is really a problem with LMstudio....

一样 之前有次成功global search，之后就复现不了了

> > 一样 之前有次成功global search，之后就复现不了了 > > 你是用什么工具部署嵌入模型，嵌入模型是什么 xinference glm4-chat bce-embedding-base-v1