Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs. (arXiv:2310.01801v3 [cs.CL] UPDATED) Show more
http://arxiv.org/abs/2310.01801 #arXiv #NLProc
QOTO: Question Others to Teach Ourselves An inclusive, Academic Freedom, instance All cultures welcome. Hate speech and harassment strictly forbidden.
