Joshua Turner
Joshua Turner
Up until a couple of weeks ago, the bindings were still close enough that you could pull the upstream llama.cpp in the vendor directory and build locally. It looks like...
This is critical for my use case as well.
Now that devstral has dropped, and has even wackier stuff in their jinja templates, I wonder if there's a general form of this issue. Would it make sense to expose...
Yup - willing to bet this is fixed in https://github.com/abetlen/llama-cpp-python/pull/1649 - there's a whole cluster of issues that will get cleared with this change.