Luiz Miguel
Luiz Miguel
thats true, i can try to add it.
whats "ETA"?
Yes, and the cross compiling to MacOS is really a pain, its toolchain is not provided, so we just cant include this OS as target on the workflow. And what...
> but this would require writing the core algorithm in C++/Cuda first. Since this is a new approach to vector-matrix multiplication, my experience was that higher level frameworks hinder more...
This is interesting, can i help on develop?
Sure, can you update this issue when all this is done?
@andrewhavck and this option seems to be removed.
> LLM Scaling and Load Balancing I haven't saw the talks yet, but it is an interesting topic. Have you saw [Paddler](https://github.com/intentee/paddler) before? It is a AI app builder and...
yes, it wanna abort before trying other request without having results from the previous one.
Thanks for using paddler and contributing to this project. A development setup is fine, but there are some caveats to consider: - CUDA toolchain is relatively big download. It probably...