pxa

The set-and-forget LLM engine for Pascal and Volta: PXQ codec + kernels, auto-tuned per card. Ready-to-run PXQ models in MODELS.md; benchmarks vs llama.cpp in the README.

models

View on GitHub Website

89 Stars

15 Forks

2 Watchers

C++ Language

mit License

100 SrcLog Score

Cost to Build

$3.56M

Market Value

$11.43M

How is this calculated?

Growth over time

2 data points · 2026-10-03 → 2026-10-25

Stars Forks Watchers

💬

How do you feel about this project?

Ask AI about pxa

Question copied to clipboard

What is the poisonxa16/pxa GitHub project? Description: "The set-and-forget LLM engine for Pascal and Volta: PXQ codec + kernels, auto-tuned per card. Ready-to-run PXQ models in MODELS.md; benchmarks vs llama.cpp in the README.". Written in C++. Explain what it does, its main use cases, key features, and who would benefit from using it.

Question is copied to clipboard — paste it after the AI opens.

How to clone pxa

Clone via HTTPS

git clone https://github.com/poisonxa16/pxa.git

Clone via SSH

[email protected]:poisonxa16/pxa.git

Download ZIP

Download main.zip

Found an issue?

Report bugs or request features on the pxa issue tracker:

Open GitHub Issues

Similar to pxa

django Awesome-CoreML-Models ardent laravel-model-caching Coolie acts_as_api plank vue-mc vectiler models spacy-models jsonmodels dynamic-training-bench laravel-model-cleanup sourced django-behaviors chainer-fast-neuralstyle-models NestedTypes gama.old hydro-serving felicity reobject tango vue-example Pytorch-Model-Zoo models osprey ImageRecognizer-Android COLLADAViewer2 Torch-Models