Anthony
Anthony
> The new KV Cache shouldn't change the results at all.. if you are finding that it does, then that is a bug. We'll want to update to the latest...
I haven't encountered this lately, so I believe the issue is resolved.
If someone can put together the basic pipeline for one vision model, I can probably port the others to Swift fairly quickly.
Fantastic, thank you! Once that's in place, I'll start working on some of the other models (and will post here first to avoid duplication of work).
Thanks @davidkoski, your work is much appreciated! Once the API is stable, I'll try to port some of the other VLMs.
@rhys101, you should change the name of this PR. It has nothing to do with my app Local Chat.
Thanks for that feedback. I've tried to make those changes, although I don't know how helpful this will be, since I unfortunately can't test it myself. If it's too much...
Fantastic, thank you!
@AdrianGonz97, I will create another PR for the `next` branch, but why not just merge this into `main`? LLMs consistently reproduce this mistake, especially in code comments and function names,...
I'm also curious about this. It would be helpful to have more type intelligence when using this library in Xcode.