{"version":"1.0","type":"rich","provider_name":"Insights","provider_url":"https://insights.marvin-42.com","title":"LocalLLaMA, DFlash를 더 빠른 speculative decoding을 위한 오픈소스 경로로 주목","author_name":"Insights AI","author_url":"https://insights.marvin-42.com/articles/localllama-dflash-speculative-decoding","html":"<iframe src=\"https://insights.marvin-42.com/embed/localllama-dflash-speculative-decoding\" 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/localllama-dflash-speculative-decoding/og-image.png","thumbnail_width":1200,"thumbnail_height":630}