{"author_name":"Paper Radio","author_url":"https://montaan.com/","height":720,"html":"<iframe src=\"https://montaan.com/embed/video/fdb8318e-98ae-4849-a556-f791176c08d2\" width=\"1280\" height=\"720\" title=\"Load Balancing with Evolving Workloads in Large-Scale Language Model Serving — Paper Radio\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture\" allowfullscreen loading=\"lazy\" style=\"border:0;display:block;max-width:100%;\"></iframe>","provider_name":"Paper Radio","provider_url":"https://montaan.com/","thumbnail_url":"https://montaan.com/media/episodes/fdb8318e-98ae-4849-a556-f791176c08d2/episode.poster.webp","title":"Load Balancing with Evolving Workloads in Large-Scale Language Model Serving","type":"video","version":"1.0","width":1280}