Relaxed-System-Lab/Flash-Sparse-Attention
๐๐ Efficient implementations of Native Sparse Attention
- Stars
- 591
- Forks
- 15
- Open issues
- 7
- Last push
- 1mo ago
About Flash-Sparse-Attention
Flash-Sparse-Attention is a free, open-source LLM chat app by Relaxed-System-Lab, written mainly in Python. ๐๐ Efficient implementations of Native Sparse Attention. It has 591 GitHub stars and 15 forks, and was last updated 1mo ago. It's released under the Apache-2.0 license, a standard open-source license.
- License
- Apache-2.0
- Language
- Python
- Stars
- 591
- Last update
- 1mo ago
- Runs on Mac
- Not stated
- GPU
- Not stated
- Paid API key
- Not stated
- Self-hostable
- Not stated
Similar free tools
Hands-On-Large-Language-Models30k stars ยท Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
Qwen22k stars ยท The official repo of Qwen (้ไนๅ้ฎ) chat & pretrained large language model proposed by Alibaba Cloud.
FinGPT21k stars ยท FinGPT: Open-Source Financial Large Language Models! Revolutionize ๐ฅ We release the trained model on HuggingFace.
flash-linear-attention6.0k stars ยท ๐ Efficient implementations for emerging model architectures
ml-engineering20k stars ยท Machine Learning Engineering Open Book
MOSS12k stars ยท An open-source, tool-augmented conversational language model from Fudan University
Flash-Sparse-Attention FAQ
Is Flash-Sparse-Attention free?
Yes. Flash-Sparse-Attention is open source and free to use. It's released under the Apache-2.0 license, a standard open-source license.
Does Flash-Sparse-Attention run on a Mac?
The project doesn't say. Check its installation guide before you start.
Does Flash-Sparse-Attention need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is Flash-Sparse-Attention still maintained?
It was last updated 1mo ago. Check recent issues on GitHub to judge how active it is.
What are alternatives to Flash-Sparse-Attention?
Similar free, open-source tools include Hands-On-Large-Language-Models, Qwen, FinGPT, flash-linear-attention.