You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello I'm interested in your project; I think it's awesome! However, it might be a bit challenging to run it on a single GPU. I suggest using something like Punica to serve multiple lora, especially for models around 7B in size, what do you think?
Thanks :D
The text was updated successfully, but these errors were encountered:
Hello I'm interested in your project; I think it's awesome! However, it might be a bit challenging to run it on a single GPU. I suggest using something like Punica to serve multiple lora, especially for models around 7B in size, what do you think?
Thanks :D
The text was updated successfully, but these errors were encountered: