{"version":"1.0","type":"video","provider_name":"Bisque","provider_url":"https://bisque.today","title":"llama.cpp v0.7.0 runs MoE models up to 2.2x faster when the experts don't fit in VRAM","author_name":"@llama-cpp","author_url":"https://bisque.today/p/llama-cpp","html":"<iframe src=\"https://bisque.today/p/llama-cpp/llama-cpp-0-7-0?embed=1\" width=\"800\" height=\"450\" frameborder=\"0\" allow=\"autoplay; fullscreen\" allowfullscreen title=\"llama.cpp v0.7.0 runs MoE models up to 2.2x faster when the experts don't fit in VRAM\"></iframe>","width":800,"height":450,"thumbnail_url":"https://bisque.today/poster/AlY6OT2Cd1YpfqlZ5jsfdWcae933/llama-cpp-0-7-0-27652f/og-slide.png?v=1792106099628","thumbnail_width":1200,"thumbnail_height":630}