Periodic alignment with upstream

Open
#2,076 0 comments 3 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
35/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Stale
Tech stack
c, cpp, python

Research direction

Look at the project's CI/CD configuration, likely in .github/workflows/, and the scripts or makefiles that handle building and versioning. Understand how the bindings currently sync with the upstream llama.cpp repository. The goal is to automate version bumps when upstream changes are compatible, so investigate existing automation and dependency management.

Written by the indexing model from the issue text.

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

Dominant language
Python
Stars
10.7k
Forks
1.5k
Avg merge
1h 40m
Merged PRs (30d)
5

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from abetlen/llama-cpp-python

All issues in abetlen/llama-cpp-python

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.