Hao Zhang
Hao Zhang
@WenchenLi Could you try the official llama from HF?
cool, Closing the issue. Please re-open if it happens again.
Folks -- this issue is likely caused because you are using a script to set up the three processes -- worker, controller, and web server. As @gujingit showed, if you...
@krzysztofantczak No, we do not have control of your (and other users') launching script. We never provided such a launching script. If you follow strictly our instructions on how to...
> @zhisbug I think you missed my point here. There is absolutely no reason for UI to not receive an event from controller that model is ready (or crashed for...
it seems your error is because of using some other service (like openAI's API). This issue is not related to Vicuna or fastchat.
A duplicated issue with #459 . It seems that flashattention has some compatibility issue with commodity GPUs. Closing this one and let's discuss in #459 instead.
Thank you @Sparetavns Does @Sparetavns 's solution solve others' problems?
@sethbruder Great, thanks for the detailed explainations!
Seems like @sethbruder 's solution would solve this problem. Closing. Please re-open if the issue persists.