Brian M
Brian M
It was not my mistake, I ended up replacing the contents of automount-usb.sh as my debugging environment was different than the repo I cloned.
I updated my forked repo so it only shows the changed I added
Hi all! Just wondering if there is any update regarding ARM support for OVMS?
There are two main categories that I'm seeing here - Create a playground with an already downloaded model, but no service - The playground will create a default model service...
Been testing this issue out and confirmed something interesting On windows and linux when force quitting (essentially the same process as command+q) we get this error out ``` 12:36:58 PM...
@manusa that sounds good to me!
Makes sense, I think we're looking past adding vllm support to Ramalama. Could be worth having llama.cpp do the conversation from safe sensors to gguf im not sure if this...
hi @Tojaj sorry for the late response! Ive been wrestling with this idea myself. I like what your doing here but do we want to have the same endpoint v1/chat/completions...
LGTM codewise as well! probs needs a rebase