Batched in Back: Characterizing and Optimizing Offline LLM Inference in Production with ACDC
🔗 https://www.semanticscholar.org/paper/27beb9e39db85e95cd775058bf05be93d12a17bd ↗Batched in Back: Characterizing and Optimizing Offline LLM Inference in Production with ACDC.
內容為收集當日抓取的摘要原文。