{"type":"link","version":"1.0","title":"Memory fragmentation, not compute, is the primary throughput bottleneck in LLM serving","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/memory-fragmentation-is-the-llm-serving-bottleneck","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}