{"id":"2605.23057","title":"RequestRouter: Request-Boundary Routing for Efficient Single-GPU LLM Inference","url":"https://codeofpaper.com/paper/2605.23057","arxiv_url":"https://arxiv.org/abs/2605.23057","published":"2026-05-21","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}