Periodic alignment with upstream #2076
Description
Is your feature request related to a problem? Please describe.
I make lots of use of these bindings, but frequently find that new models depend on changes in the upstream llama-cpp project that have not yet made their way to the python bindings.
Describe the solution you'd like
Would it be possible to automate or schedule version bumps to align with upstream? I'm aware that API changes can be unpredictable, but it would be fantastic to have version bumps not needing manual changes make their way downstream.
Describe alternatives you've considered
I've considered decoupling from llama-cpp-python and calling a separate process using a high-level web API, but some of the low-level features when inferring tokens piecewise are critical to my use case.
Additional context
N/A