long-tail-generation

This paper proposes PAT, an adaptive tensor parallelism method that dynamically reconfigures TP during the generation stage of synchronous RLHF training to mitigate long-tail generation bottlenecks. Evaluations on LLaMA3.1-8B and Qwen3-14B show reductions in generation latency by up to 34.6% and end-to-end iteration latency by up to 27.2%.