{"version":"1.0","type":"rich","provider_name":"Insights","provider_url":"https://insights.marvin-42.com","title":"LocalLLaMA가 공유한 llama.cpp 튜닝 팁, 작은 n_ubatch가 Qwen 27B prompt processing를 크게 끌어올렸다","author_name":"Insights AI","author_url":"https://insights.marvin-42.com/articles/localllama-llamacpp-n-ubatch-qwen-27b-prompt-processing","html":"<iframe src=\"https://insights.marvin-42.com/embed/localllama-llamacpp-n-ubatch-qwen-27b-prompt-processing\" 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-llamacpp-n-ubatch-qwen-27b-prompt-processing/og-image.png","thumbnail_width":1200,"thumbnail_height":630}