Scottcjn/rpi-inference

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.

语言：C · GitHub 星标：40 · Fork：5

话题：cost-optimization · cpu-inference · edge-ai · embedded-ai · llm · llm-inference · mips · nintendo-64

在 GitHub 上查看原仓库