1
ModeSwitch-LLM: A Lightweight Phase-Aware Controller for Cross-Mode LLM Inference on a Single GPU
单GPU也能高效切换LLM推理模式！这篇论文提出轻量级相位感知控制器，解决资源受限场景下的跨模式推理瓶颈。
arXiv:2605.23057v1 Announce Type: new Abstract: ModeSwitch-LLM is a lightweight request-boundary controller for improving single-GPU large language mo…