tspeterkim/paged-attention-minimal
a minimal cache manager for PagedAttention, on top of llama3.
PythonApache-2.0
Stargazers
- alex-xia-xiashenzhen
- baochi0212@VinAIResearch
- ChenghaoMouDocusign
- clabrugere
- cwh1981LG Electronics
- eclouder
- felixdsml
- gc-fuIntel
- goodhamguptaSingapore
- iCSawyerZhejiang University
- L2zzRepublic of Korea
- larme@bentoml
- MaateusSilvaUberlândia, Brasil
- makdoudNPalaiseau, France
- MancheryTsinghua University
- mirceamironencoAmsterdam, Netherlands
- msaroufim@PyTorch
- NonvolatileMemoryAN IRON-HAN-HAN
- nopromptFriant, CA
- omarmahamidLondon
- platers
- SandalotsVolcanak
- scturtle
- sicario001
- sjjeong94Seoul, South Korea
- Sleepyhead01Kharagpur
- SonDongHwee1 Gwanak-ro, Gwanak-gu, Seoul 08826, Republic of Korea
- TARSdotgz
- Tongkaio
- violet-quartz
- vwxyzjn@huggingface
- weixin00
- yashasolutionsRemote
- yzwang2000Tianjin University
- zzmtsvv