Upcoming maintenance: ProQuest will be unavailable 10:00 PM ET Saturday, Aug 9 - 6:00 AM ET Sunday, Aug 10. ReadMore

Document Preview Unavailable

The Synergy of Speculative Decoding and Batching in Serving Large Language Models

Su, Qidong; Giannoula, Christina; Pekhimenko, Gennady.  arXiv.org, Oct 28, 2023.

You might have access to this document