Rank #1,994 3,971 starsCuda

SageAttention

by thu-ml (organization)

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models. (description from the project’s GitHub page)

View on GitHub Homepage

Repository facts

Stars: 3,971
Forks: 531
Open issues and pull requests: 213
Primary language: Cuda
License: Apache License 2.0 (Apache-2.0)
Owner: thu-ml · Organization
Created: Oct 3, 2024
Last push: Jan 17, 2026

Topics

Rank #1,994 of 9,507 in AI on GitHub, by stars. Data from the GitHub API, fetched Oct 18, 2026; star counts change daily. Stars measure popularity, not quality or safety, and a listing is not an endorsement. How this list is made

Add this badge to your README

Ranked #1,994 in AI on GitHub Shows this repository’s rank in AI on GitHub and links back to this page. Ranks are by stars and change when the list is refreshed. The badge is not an endorsement or a rating. About the badges

Markdown (for a README)

[![Ranked #1,994 in AI on GitHub](https://unitedstatesofamericasuperintelligence.com/badges/github/thu-ml--sageattention.svg)](https://unitedstatesofamericasuperintelligence.com/github/thu-ml--sageattention/)

HTML

<a href="https://unitedstatesofamericasuperintelligence.com/github/thu-ml--sageattention/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/github/thu-ml--sageattention.svg" alt="Ranked #1,994 in AI on GitHub" height="20"></a>

Projects that share this one’s GitHub topics.

Rank 2,688: nunchux-ai/ComfyUI-nunchaku
ComfyUI Plugin of Nunchaku
2,933 starsPythonApache-2.0Last push Sep 6, 2026
Rank 4,385: RightNow-AI/autokernel
Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
1,599 starsPythonMITLast push Mar 19, 2026
Rank 8,477: BobMcDear/attorch
A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.
605 starsPythonMITLast push Aug 14, 2026
Rank 185: sgl-project/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
37,276 starsPythonApache-2.0Last push Oct 18, 2026
Rank 6,027: mw00/project-maya
Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-co…
1,023 starsC++MITLast push Oct 16, 2026
Rank 1,209: flashinfer-ai/flashinfer
FlashInfer: Kernel Library for LLM Serving
6,687 starsCudaApache-2.0Last push Oct 18, 2026

Repository facts

Topics

Add this badge to your README

Related projects

Rank 2,688: nunchux-ai/ComfyUI-nunchaku

Rank 4,385: RightNow-AI/autokernel

Rank 8,477: BobMcDear/attorch

Rank 185: sgl-project/sglang

Rank 6,027: mw00/project-maya

Rank 1,209: flashinfer-ai/flashinfer

Support Us