https://www.infoq.com InfoQ Facebook Presentations feed https://www.infoq.com/presentations/llm-meta/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Facebook-presentations <img src="https://res.infoq.com/presentations/llm-meta/en/mediumimage/ye-charlotte-qi-medium-1747727365712.jpg"/><p>Ye (Charlotte) Qi overviews LLM serving infrastructure challenges: fitting & speed (Model Runners, KV cache, and distributed inference), production complexities (latency optimization and continuous evaluation), and effective scaling strategies (heterogeneous deployment and autoscaling). Learn key concepts for robust LLM deployment.</p> <i>By Ye Qi</i> Case Study Large language models Artificial Intelligence QCon San Francisco 2024 Facebook Transcripts AI, ML & Data Engineering presentation Thu, 29 May 2025 13:11:00 GMT https://www.infoq.com/presentations/llm-meta/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Facebook-presentations Ye Qi 2025-05-29T13:11:00Z /presentations/llm-meta/en