PyPI page
Home page
Author:
Todd Thomson
Summary:
The LLM stack you can read and understand: Gemma 4 and Llama on CUDA, built from explicit C++23 components.
Latest version:
0.20.0
Required dependencies:
nvidia-cublas
|
nvidia-cuda-runtime
|
nvidia-curand
Downloads last day:
0
Downloads last week:
12
Downloads last month:
360
7-day smoothing