BetaRare
lucidrains/native-sparse-attention-pytorch
Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper
- Owner
- lucidrains (personal account)
- Stars
- Stars: 816
- Forks
- Forks: 51
- Language
- Python
- License
- MIT
- Created
- 2025
- Topics
- artificial-intelligenceattentiondeep-learningsparse-attention
- Tier
- Beta (700 to 1,999 ★) What this tier means
More repos by lucidrains
All 175 repos by lucidrains- lucidrains/vit-pytorchStars: 25,554PythonLTS
- lucidrains/DALLE2-pytorchStars: 11,306PythonStable
- lucidrains/denoising-diffusion-pytorchStars: 10,724PythonStable
- lucidrains/imagen-pytorchStars: 8,429PythonStable
- lucidrains/PaLM-rlhf-pytorchStars: 7,863PythonStable
- lucidrains/x-transformersStars: 5,962PythonStable
Nearby in Python
All Python repos- z-mio/parse_hub_botStars: 816PythonBeta
- zetaloop/cursor-shadow-patchStars: 816PythonBeta
- Accio-Lab/DressageStars: 816PythonBeta
- breathe-doc/breatheStars: 816PythonBeta
- jiffyclub/palettableStars: 816PythonBeta
- shantnu/FaceDetectStars: 816PythonBeta