{"author_name":"Paper Radio","author_url":"https://m.montaan.com/","height":720,"html":"<iframe src=\"https://m.montaan.com/embed/video/d212ff3a-1339-4df2-ba8e-76e963d5f6a7\" width=\"1280\" height=\"720\" title=\"HBQ: Hierarchical Scaling Block Quantization with Hardware-Efficiency-Aware Design for Accurate LLM Inference — 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/d212ff3a-1339-4df2-ba8e-76e963d5f6a7/episode.poster.webp","title":"HBQ: Hierarchical Scaling Block Quantization with Hardware-Efficiency-Aware Design for Accurate LLM Inference","type":"video","version":"1.0","width":1280}