Skip Navigation

StreamingLLM: Efficient streaming technique enable infinite sequence lengths

arxiv.org /abs/2309.17453

There is a discussion on Hacker News, but feel free to comment here as well.

0
Hacker News @lemmy.smeargle.fans bot @lemmy.smeargle.fans
BOT

StreamingLLM: Efficient streaming technique enable infinite sequence lengths

1 0
star technology and research @lemm.ee kenna @lemm.ee

Efficient Streaming Language Models with Attention Sinks - #AI

1 0
0 comments