{"author_name":"Paper Radio","author_url":"https://m.montaan.com/","height":720,"html":"<iframe src=\"https://m.montaan.com/embed/video/3c6ca2aa-12cf-490e-ba78-9fa6386459d9\" width=\"1280\" height=\"720\" title=\"A JoLT for the KV cache: Near-lossless KV cache compression via joint Lagrangian allocation of Tucker ranks and a rotated residual for llms — 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://m.montaan.com/","thumbnail_url":"https://m.montaan.com/media/episodes/3c6ca2aa-12cf-490e-ba78-9fa6386459d9/episode.poster.webp","title":"A JoLT for the KV cache: Near-lossless KV cache compression via joint Lagrangian allocation of Tucker ranks and a rotated residual for llms","type":"video","version":"1.0","width":1280}