{"author_name":"Paper Radio","author_url":"https://montaan.com/","height":720,"html":"<iframe src=\"https://montaan.com/embed/video/02469177-552d-4032-9aa4-c08f5709aaee\" width=\"1280\" height=\"720\" title=\"GQLA: Group-Query Latent Attention for Hardware-Adaptive Decoding — 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/02469177-552d-4032-9aa4-c08f5709aaee/episode.poster.webp","title":"GQLA: Group-Query Latent Attention for Hardware-Adaptive Decoding","type":"video","version":"1.0","width":1280}