mit-han-lab / streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
https://arxiv.org/abs/2309.17453
MIT License
6.59k stars 361 forks source link

b979594a04f1bbefe1ff21eb8affacef2a186d25 #26

Closed ghost closed 12 months ago

ghost commented 1 year ago

https://github.com/mempool/mempool/commit/b979594a04f1bbefe1ff21eb8affacef2a186d25