tp_engine: rank-0 coordinator owns the scheduler and broadcasts per-token commands (Register/Prefill/Decode/Free) to worker rank threads; the sampled token always comes from rank 0, so it's correct for greedy and stochastic sampling. Serial single-request path (sufficient for the quality benchmark). --tp N selects it; TP=1 keeps the existing single-GPU Engine unchanged. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>