QwenPU: An LLM running inside another LLM's weights

QwenPU, released by Divyansh Agrawal, compiles a 32-bit RISC-V CPU and a vector unit into the weights of Qwen3.5-4B, so that Karpathy's 260K-parameter stories model runs as a program inside the model's forward passes and produces the same output as plain C.