PotatoSpudowski/fastLLaMa
fastLLaMa: An experimental high-performance framework for running Decoder-only LLMs with 4-bit quantization in Python using a C/C++ backend.
CMIT
Stargazers
- Chensl9393
- notmehulDowntown Coolsville
- remghoostCalifornia
- SupreethRao99Bengaluru, India
- chittiman
- xids2016
- UglyStupidHonestHaarlem Netherlands
- enod
- amirrezasalimi
- zotona
- GuangDaiChina
- thtran02
- karelnagelEstonia
- bailooNew Delhi, India
- tiendung
- Gochomer
- cosimoiaiaBerlin
- RaulKiteMurcia (Spain)
- vigsivan
- covexpBarcelona
- MagnusPetersenFrankfurt am Main
- dsindexPangyo-dong
- jvicentemMadrid, Spain
- amrrs
- ntkrnl
- Banguiskode
- balsulami
- shyamsn97
- rahulkolasseri
- achuthasubhashGUNTUR , INDIA
- MachineLemonadeCincinnati
- Frostchomp
- joe-barhouch
- ianrowanChicago, IL
- gurv234New Delhi
- migperferMunich