R

rpi-inference

Project information

RPI (Resonant Permutation Inference) — Zero-multiply text generation. 18K tok/s. 868 KB models. Standalone or as speculative draft engine for LLMs. Runs on N64, POWER8, x86, ARM. (Mirror of github.com/Scottcjn/rpi-inference; full history archived 2026-10-20.)

20 Commits
2 Branches
2 Tags

README
GNU AGPLv3
CONTRIBUTING

Created on

October 21, 2026

Loading