Can RotorQuant/TurboQuant and dflash support be added?

Open
#2,184 0 comments 0 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
Quiet
Tech stack
c, python

Research direction

The issue requests adding support for TurboQuant/RotorQuant and dFlash speculative decoding to the llama-cpp-python bindings. Start by examining the existing binding code in the repository to understand how quantization and speculative decoding features are currently integrated. Check the upstream llama.cpp project for any existing implementations or discussions of these features. Determine what changes are needed in the C++ bindings and Python interface, and verify the build process to ensure compatibility.

Written by the indexing model from the issue text.

Description

Hi!
This project is very useful for using with llama.cpp in python. However, it would be great if we could have some features even before the main llama.cpp has full support for them. By that I mean TurboQuant/RotorQuant and dFlash speculative decoding. It would make this entire library AMAZING to use.

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.