native-sparse-attention-pytorch

native-sparse-attention-pytorch

lucidrains

Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper

802 Stars
51 Forks
802 Watchers
Python Language
mit License
100 SrcLog Score
Cost to Build
$1.59M
Market Value
$5.61M

Growth over time

2 data points  ·  2025-03-01 → 2026-04-01
Stars Forks Watchers
💬

How do you feel about this project?

Ask AI about native-sparse-attention-pytorch

Question copied to clipboard

What is the lucidrains/native-sparse-attention-pytorch GitHub project? Description: "Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper". Written in Python. Explain what it does, its main use cases, key features, and who would benefit from using it.

Question is copied to clipboard — paste it after the AI opens.

How to clone native-sparse-attention-pytorch

Clone via HTTPS

git clone https://github.com/lucidrains/native-sparse-attention-pytorch.git

Clone via SSH

[email protected]:lucidrains/native-sparse-attention-pytorch.git

Download ZIP

Download master.zip

Found an issue?

Report bugs or request features on the native-sparse-attention-pytorch issue tracker:

Open GitHub Issues