Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads. (arXiv:2401.10774v1 [cs.LG]) Show more
http://arxiv.org/abs/2401.10774 #arXiv #NLProc
CleverLibre Social is an inclusive social instance for open discussion, learning, and community. All cultures welcome. Hate speech and harassment strictly forbidden.
