piwheels

llama-optimus

llama-optimus is a lightweight Python tool to automatically optimize llama.cpp performance flags for maximum tg & pp token/s throughput. Powered by Bayesian optimization with Optuna

Installation

In a virtualenv (see these instructions if you need to create one):

pip3 install llama-optimus

Dependencies

• pandas
• optuna

Releases

Version	Released	Bullseye Python 3.9	Bookworm Python 3.11	Trixie Python 3.13	Files
0.1.9	2025-06-30
llama_optimus-0.1.9-py3-none-any.whl (20 KB)
0.1.8	2025-06-21
llama_optimus-0.1.8-py3-none-any.whl (19 KB)
0.1.7	2025-06-20
llama_optimus-0.1.7-py3-none-any.whl (19 KB)
0.1.6	2025-06-18
llama_optimus-0.1.6-py3-none-any.whl (19 KB)
0.1.5	2025-06-18
llama_optimus-0.1.5-py3-none-any.whl (19 KB)
0.1.4	2025-06-17
llama_optimus-0.1.4-py3-none-any.whl (19 KB)
0.1.3	2025-06-17
llama_optimus-0.1.3-py3-none-any.whl (19 KB)
0.1.1	2025-06-14
llama_optimus-0.1.1-py3-none-any.whl (13 KB)

Issues with this package?

• Search issues for this package
• Package or version missing? Open a new issue
• Something else? Open a new issue