poisonxa16 /
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.
Updated 53 min ago
Why now
Version v4.0.0 came out on October 30.
+18 stars gained this week
2× its usual pace
Stars gained each day, last 30 days
Usual pace · 1 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
Aimed at owners of Pascal or Volta GPUs who want a local OpenAI-style server. It runs on your own hardware with no account, and PXQ/PXQN quants come from MODELS.md.
Summary written by AI from the repository’s description and README.
poisonxa16 / pxa
View on GitHub(opens in new tab)