{"version":"1.0","type":"rich","provider_name":"Insights","provider_url":"https://insights.marvin-42.com","title":"llama.cpp RDNA3 Flash Attention, KV VRAM 47% 절감 실험","author_name":"Insights AI","author_url":"https://insights.marvin-42.com/articles/llamacpp-rdna3-flash-attention-kv-vram-47","html":"<iframe src=\"https://insights.marvin-42.com/embed/llamacpp-rdna3-flash-attention-kv-vram-47\" width=\"500\" height=\"280\" style=\"border:0;border-radius:12px;\" sandbox=\"allow-scripts allow-same-origin allow-popups\" loading=\"lazy\"></iframe>","width":500,"height":280,"thumbnail_url":"https://insights.marvin-42.com/articles/llamacpp-rdna3-flash-attention-kv-vram-47/og-image.png","thumbnail_width":1200,"thumbnail_height":630}