Pi harness adapter ships as a LoRA runnable on vLLM, llama.cpp, and MLX

yb2698 · x · 2026-11-17

The author notes the Pi harness adapter is a LoRA that runs anywhere: transformers serve, vLLM, sglang, llama.cpp, MLX on macOS, or merged into the base model — all documented in the model card.

Original post →

More from coding & agent

coding & agent channel →