Semantic Scholar

Batched in Back: Characterizing and Optimizing Offline LLM Inference in Production with ACDC

作者:Le-Ping Yang, Xue Li, Kun Qian, Er-Ci Xu, Ming-Zhe Han, Hao-Ran Zhu, Tao He, Zuo-Long Yin

🔗 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。