{"author_name":"Paper Radio","author_url":"https://m.montaan.com/","height":720,"html":"<iframe src=\"https://m.montaan.com/embed/video/e32ab1ed-224b-410c-ab23-c68f37fc18c0\" width=\"1280\" height=\"720\" title=\"When KV Meets Embeddings: Dynamic GPU Memory Allocation for Accelerating Generative Recommender 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://m.montaan.com/","thumbnail_url":"https://m.montaan.com/media/episodes/e32ab1ed-224b-410c-ab23-c68f37fc18c0/episode.poster.webp","title":"When KV Meets Embeddings: Dynamic GPU Memory Allocation for Accelerating Generative Recommender Serving","type":"video","version":"1.0","width":1280}