mit-han-lab/streaming-llm
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
PythonMIT
Stargazers
- alongubkin@aporia-ai
- ATCPInstitute of Computing Technology
- boostf
- bys0318Tsinghua University
- carbonz0
- cceydaKakaoStyle
- chumpblocckami@glassform
- ctlllll@Princeton
- dla-010609whu
- dotchenUT Austin
- GeneZC
- gitlost-murali
- happierpigUC Berkeley
- JeffCarpenterCanada
- JuneJulyAugustProgramming
- kugwzk
- Kunlun-ZhuMila-Quebec AI Institute; UdeM
- KyeongpilScatter Lab
- KyriectionThe University of Texas at Austin
- lsj2408Peking University @microsoft
- lu-m13Intel Labs China
- MARD1NOSiliconFlow
- roger1993Hong Kong
- ryantd@kwai
- SakitsMIT, EECS
- samuelrinceAlygne
- TGLTommy
- tianweiyMIT
- tomaarsenHugging Face
- umiswingNEU
- williamium3000Johns Hopkins University
- Xiuyu-LiUC Berkeley
- xmfbitBytedance
- Xu-KaiNational University of Singapore
- yifanzhang-proTsinghua University
- yukang2017NVIDIA